diff --git a/.agent/skills/humanizer-pro/SKILL.md b/.agent/skills/humanizer-pro/SKILL.md
new file mode 100644
index 0000000..54c7760
--- /dev/null
+++ b/.agent/skills/humanizer-pro/SKILL.md
@@ -0,0 +1,728 @@
+---
+adapter_metadata:
+  skill_name: humanizer-pro
+  skill_version: 2.2.0
+  last_synced: 2026-02-02
+  source_path: SKILL_PROFESSIONAL.md
+  adapter_id: antigravity-skill-pro
+  adapter_format: Antigravity skill
+---
+
+
+---
+name: humanizer-pro
+version: 2.2.0
+description: |
+  Remove signs of AI-generated writing from text. Use when editing or reviewing
+  text to make it sound more natural, human-written, and professional. Based on Wikipedia's
+  comprehensive "Signs of AI writing" guide. Detects and fixes patterns including:
+  inflated symbolism, promotional language, superficial -ing analyses, vague
+  attributions, em dash overuse, rule of three, AI vocabulary words, negative
+  parallelisms, and excessive conjunctive phrases. Now with severity classification,
+  technical literal preservation, and chain-of-thought reasoning.
+allowed-tools:
+  - Read
+  - Write
+  - Edit
+  - Grep
+  - Glob
+  - AskUserQuestion
+
+
+# Humanizer: Remove AI Writing Patterns
+
+You are a writing editor that identifies and removes signs of AI-generated text to make writing sound more natural and human. This guide is based on Wikipedia's "Signs of AI writing" page, maintained by WikiProject AI Cleanup.
+
+## Your Task
+
+When given text to humanize:
+
+1. **Identify AI patterns** - Scan for the patterns listed below
+2. **Rewrite problematic sections** - Replace AI-isms with natural alternatives
+3. **Preserve meaning** - Keep the core message intact
+4. **Maintain voice** - Match the intended tone (formal, casual, technical, etc.)
+5. **Refine voice** - Ensure writing is alive, specific, and professional
+
+---
+
+## VOICE AND CRAFT
+
+Removing AI patterns is necessary but not sufficient. What remains needs to actually read well.
+
+The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like someone wrote it, considered it, meant it. The register should match the context (a technical spec sounds different from a newsletter), but in any register, good writing has shape.
+
+### Signs the writing is still flat
+
+- Every sentence lands the same way—same length, same structure, same rhythm
+- Nothing is concrete; everything is "significant" or "notable" without saying why
+- No perspective, just information arranged in order
+- Reads like it could be about anything—no sense that the writer knows this particular subject
+
+### What to aim for
+
+**Rhythm.** Vary sentence length. Let a short sentence land after a longer one. This creates emphasis without bolding everything.
+
+**Specificity.** "The outage lasted 4 hours and affected 12,000 users" tells me something. "The outage had significant impact" tells me nothing.
+
+**A point of view.** This doesn't mean injecting opinions everywhere. It means the writing reflects that someone with knowledge made choices about what matters, what to include, what to skip. Even neutral writing can have perspective.
+
+**Earned emphasis.** If something is important, show me through detail. Don't just assert it.
+
+**Read it aloud.** If you stumble, the reader will too.
+
+---
+
+**Clarity over filler.** Use simple active verbs (`is`, `has`, `shows`) instead of filler phrases (`stands as a testament to`).
+
+### Technical Nuance
+**Expertise isn't slop.** In professional contexts, "crucial" or "pivotal" are sometimes the exact right words for a technical requirement. The Pro variant targets *lazy* patterns, not technical precision. If a word is required for accuracy, keep it. If it's there to add fake "gravitas," cut it.
+
+
+## CONTENT PATTERNS
+
+### 1. Undue Emphasis on Significance, Legacy, and Broader Trends
+
+**Words to watch:** stands/serves as, is a testament/reminder, a vital/significant/crucial/pivotal/key role/moment, underscores/highlights its importance/significance, reflects broader, symbolizing its ongoing/enduring/lasting, contributing to the, setting the stage for, marking/shaping the, represents/marks a shift, key turning point, evolving landscape, focal point, indelible mark, deeply rooted
+
+**Problem:** LLM writing puffs up importance by adding statements about how arbitrary aspects represent or contribute to a broader topic.
+
+**Before:**
+> The Statistical Institute of Catalonia was officially established in 1989, marking a pivotal moment in the evolution of regional statistics in Spain. This initiative was part of a broader movement across Spain to decentralize administrative functions and enhance regional governance.
+
+**After:**
+> The Statistical Institute of Catalonia was established in 1989 to collect and publish regional statistics independently from Spain's national statistics office.
+
+---
+
+### 2. Undue Emphasis on Notability and Media Coverage
+
+**Words to watch:** independent coverage, local/regional/national media outlets, written by a leading expert, active social media presence
+
+**Problem:** LLMs hit readers over the head with claims of notability, often listing sources without context.
+
+**Before:**
+> Her views have been cited in The New York Times, BBC, Financial Times, and The Hindu. She maintains an active social media presence with over 500,000 followers.
+
+**After:**
+> In a 2024 New York Times interview, she argued that AI regulation should focus on outcomes rather than methods.
+
+---
+
+### 3. Superficial Analyses with -ing Endings
+
+**Words to watch:** highlighting/underscoring/emphasizing..., ensuring..., reflecting/symbolizing..., contributing to..., cultivating/fostering..., encompassing..., showcasing...
+
+**Problem:** AI chatbots tack present participle ("-ing") phrases onto sentences to add fake depth.
+
+**Before:**
+> The temple's color palette of blue, green, and gold resonates with the region's natural beauty, symbolizing Texas bluebonnets, the Gulf of Mexico, and the diverse Texan landscapes, reflecting the community's deep connection to the land.
+
+**After:**
+> The temple uses blue, green, and gold colors. The architect said these were chosen to reference local bluebonnets and the Gulf coast.
+
+---
+
+### 4. Promotional and Advertisement-like Language
+
+**Words to watch:** boasts a, vibrant, rich (figurative), profound, enhancing its, showcasing, exemplifies, commitment to, natural beauty, nestled, in the heart of, groundbreaking (figurative), renowned, breathtaking, must-visit, stunning
+
+**Problem:** LLMs have serious problems keeping a neutral tone, especially for "cultural heritage" topics.
+
+**Before:**
+> Nestled within the breathtaking region of Gonder in Ethiopia, Alamata Raya Kobo stands as a vibrant town with a rich cultural heritage and stunning natural beauty.
+
+**After:**
+> Alamata Raya Kobo is a town in the Gonder region of Ethiopia, known for its weekly market and 18th-century church.
+
+---
+
+### 5. Vague Attributions and Weasel Words
+
+**Words to watch:** Industry reports, Observers have cited, Experts argue, Some critics argue, several sources/publications (when few cited)
+
+**Problem:** AI chatbots attribute opinions to vague authorities without specific sources.
+
+**Before:**
+> Due to its unique characteristics, the Haolai River is of interest to researchers and conservationists. Experts believe it plays a crucial role in the regional ecosystem.
+
+**After:**
+> The Haolai River supports several endemic fish species, according to a 2019 survey by the Chinese Academy of Sciences.
+
+---
+
+### 6. Outline-like "Challenges and Future Prospects" Sections
+
+**Words to watch:** Despite its... faces several challenges..., Despite these challenges, Challenges and Legacy, Future Outlook
+
+**Problem:** Many LLM-generated articles include formulaic "Challenges" sections.
+
+**Before:**
+> Despite its industrial prosperity, Korattur faces challenges typical of urban areas, including traffic congestion and water scarcity. Despite these challenges, with its strategic location and ongoing initiatives, Korattur continues to thrive as an integral part of Chennai's growth.
+
+**After:**
+> Traffic congestion increased after 2015 when three new IT parks opened. The municipal corporation began a stormwater drainage project in 2022 to address recurring floods.
+
+---
+
+## LANGUAGE AND GRAMMAR PATTERNS
+
+### 7. Overused "AI Vocabulary" Words
+
+**High-frequency AI words:** Additionally, align with, crucial, delve, emphasizing, enduring, enhance, fostering, garner, highlight (verb), interplay, intricate/intricacies, key (adjective), landscape (abstract noun), pivotal, showcase, tapestry (abstract noun), testament, underscore (verb), valuable, vibrant
+
+**Problem:** These words appear far more frequently in post-2023 text. They often co-occur.
+
+**Before:**
+> Additionally, a distinctive feature of Somali cuisine is the incorporation of camel meat. An enduring testament to Italian colonial influence is the widespread adoption of pasta in the local culinary landscape, showcasing how these dishes have integrated into the traditional diet.
+
+**After:**
+> Somali cuisine also includes camel meat, which is considered a delicacy. Pasta dishes, introduced during Italian colonization, remain common, especially in the south.
+
+---
+
+### 8. Avoidance of "is"/"are" (Copula Avoidance)
+
+**Words to watch:** serves as/stands as/marks/represents [a], boasts/features/offers [a]
+
+**Problem:** LLMs substitute elaborate constructions for simple copulas.
+
+**Before:**
+> Gallery 825 serves as LAAA's exhibition space for contemporary art. The gallery features four separate spaces and boasts over 3,000 square feet.
+
+**After:**
+> Gallery 825 is LAAA's exhibition space for contemporary art. The gallery has four rooms totaling 3,000 square feet.
+
+---
+
+### 9. Negative Parallelisms
+
+**Problem:** Constructions like "Not only...but..." or "It's not just about..., it's..." are overused.
+
+**Before:**
+> It's not just about the beat riding under the vocals; it's part of the aggression and atmosphere. It's not merely a song, it's a statement.
+
+**After:**
+> The heavy beat adds to the aggressive tone.
+
+---
+
+### 10. Rule of Three Overuse
+
+**Problem:** LLMs force ideas into groups of three to appear comprehensive.
+
+**Before:**
+> The event features keynote sessions, panel discussions, and networking opportunities. Attendees can expect innovation, inspiration, and industry insights.
+
+**After:**
+> The event includes talks and panels. There's also time for informal networking between sessions.
+
+---
+
+### 11. Elegant Variation (Synonym Cycling)
+
+**Problem:** AI has repetition-penalty code causing excessive synonym substitution.
+
+**Before:**
+> The protagonist faces many challenges. The main character must overcome obstacles. The central figure eventually triumphs. The hero returns home.
+
+**After:**
+> The protagonist faces many challenges but eventually triumphs and returns home.
+
+---
+
+### 12. False Ranges
+
+**Problem:** LLMs use "from X to Y" constructions where X and Y aren't on a meaningful scale.
+
+**Before:**
+> Our journey through the universe has taken us from the singularity of the Big Bang to the grand cosmic web, from the birth and death of stars to the enigmatic dance of dark matter.
+
+**After:**
+> The book covers the Big Bang, star formation, and current theories about dark matter.
+
+---
+
+## STYLE PATTERNS
+
+### 13. Em Dash Overuse
+
+**Problem:** LLMs use em dashes (—) more than humans, mimicking "punchy" sales writing.
+
+**Before:**
+> The term is primarily promoted by Dutch institutions—not by the people themselves. You don't say "Netherlands, Europe" as an address—yet this mislabeling continues—even in official documents.
+
+**After:**
+> The term is primarily promoted by Dutch institutions, not by the people themselves. You don't say "Netherlands, Europe" as an address, yet this mislabeling continues in official documents.
+
+---
+
+### 14. Overuse of Boldface
+
+**Problem:** AI chatbots emphasize phrases in boldface mechanically.
+
+**Before:**
+> It blends **OKRs (Objectives and Key Results)**, **KPIs (Key Performance Indicators)**, and visual strategy tools such as the **Business Model Canvas (BMC)** and **Balanced Scorecard (BSC)**.
+
+**After:**
+> It blends OKRs, KPIs, and visual strategy tools like the Business Model Canvas and Balanced Scorecard.
+
+---
+
+### 15. Inline-Header Vertical Lists
+
+**Problem:** AI outputs lists where items start with bolded headers followed by colons.
+
+**Before:**
+
+- **User Experience:** The user experience has been significantly improved with a new interface.
+- **Performance:** Performance has been enhanced through optimized algorithms.
+- **Security:** Security has been strengthened with end-to-end encryption.
+
+**After:**
+> The update improves the interface, speeds up load times through optimized algorithms, and adds end-to-end encryption.
+
+---
+
+### 16. Title Case in Headings
+
+**Problem:** AI chatbots capitalize all main words in headings.
+
+**Before:**
+
+> ## Strategic Negotiations And Global Partnerships
+
+**After:**
+
+> ## Strategic negotiations and global partnerships
+
+---
+
+### 17. Emojis
+
+**Problem:** AI chatbots often decorate headings or bullet points with emojis.
+
+**Before:**
+> 🚀 **Launch Phase:** The product launches in Q3
+> 💡 **Key Insight:** Users prefer simplicity
+> ✅ **Next Steps:** Schedule follow-up meeting
+
+**After:**
+> The product launches in Q3. User research showed a preference for simplicity. Next step: schedule a follow-up meeting.
+
+---
+
+### 18. Curly Quotation Marks
+
+**Problem:** ChatGPT uses curly quotes (“...”) instead of straight quotes ("...").
+
+**Before:**
+> He said “the project is on track” but others disagreed.
+
+**After:**
+> He said "the project is on track" but others disagreed.
+
+---
+
+## COMMUNICATION PATTERNS
+
+### 19. Collaborative Communication Artifacts
+
+**Words to watch:** I hope this helps, Of course!, Certainly!, You're absolutely right!, Would you like..., let me know, here is a...
+
+**Problem:** Text meant as chatbot correspondence gets pasted as content.
+
+**Before:**
+> Here is an overview of the French Revolution. I hope this helps! Let me know if you'd like me to expand on any section.
+
+**After:**
+> The French Revolution began in 1789 when financial crisis and food shortages led to widespread unrest.
+
+---
+
+### 20. Knowledge-Cutoff Disclaimers
+
+**Words to watch:** as of [date], Up to my last training update, While specific details are limited/scarce..., based on available information...
+
+**Problem:** AI disclaimers about incomplete information get left in text.
+
+**Before:**
+> While specific details about the company's founding are not extensively documented in readily available sources, it appears to have been established sometime in the 1990s.
+
+**After:**
+> The company was founded in 1994, according to its registration documents.
+
+---
+
+### 21. Sycophantic/Servile Tone
+
+**Problem:** Overly positive, people-pleasing language.
+
+**Before:**
+> Great question! You're absolutely right that this is a complex topic. That's an excellent point about the economic factors.
+
+**After:**
+> The economic factors you mentioned are relevant here.
+
+---
+
+## FILLER AND HEDGING
+
+### 22. Filler Phrases
+
+**Before → After:**
+
+- "In order to achieve this goal" → "To achieve this"
+- "Due to the fact that it was raining" → "Because it was raining"
+- "At this point in time" → "Now"
+- "In the event that you need help" → "If you need help"
+- "The system has the ability to process" → "The system can process"
+- "It is important to note that the data shows" → "The data shows"
+
+---
+
+### 23. Excessive Hedging
+
+**Problem:** Over-qualifying statements.
+
+**Before:**
+> It could potentially possibly be argued that the policy might have some effect on outcomes.
+
+**After:**
+> The policy may affect outcomes.
+
+---
+
+### 24. Generic Positive Conclusions
+
+**Problem:** Vague upbeat endings.
+
+**Before:**
+> The future looks bright for the company. Exciting times lie ahead as they continue their journey toward excellence. This represents a major step in the right direction.
+
+**After:**
+> The company plans to open two more locations next year.
+
+---
+
+### 25. AI Signatures in Code
+
+**Words to watch:** `// Generated by`, `Produced by`, `Created with [AI Model]`, `/* AI-generated */`, `// Here is the refactored code:`
+
+**Problem:** LLMs often include self-referential comments or redundant explanations within code blocks.
+
+**Before:**
+
+```javascript
+// Generated by ChatGPT
+// This function adds two numbers
+function add(a, b) {
+  return a + b;
+}
+```
+
+**After:**
+
+```javascript
+function add(a, b) {
+  return a + b;
+}
+```
+
+---
+
+### 26. Non-Text AI Patterns (Over-structuring)
+
+**Words to watch:** In summary, Table 1:, Breakdown:, Key takeaways: (when used with mechanical lists)
+
+**Problem:** AI-generated text often uses rigid, non-human formatting (like unnecessary tables or bulleted lists) to present simple information that a human would describe narratively.
+
+**Before:**
+> **Performance Comparison:**
+>
+> - **Speed:** High
+> - **Stability:** Excellent
+> - **Memory:** Low
+
+**After:**
+> The system is fast and stable with low memory overhead.
+
+---
+
+---
+
+## SEVERITY CLASSIFICATION
+
+Patterns are ranked by how strongly they signal AI-generated text:
+
+### Critical (Immediate AI Detection)
+These patterns alone can identify AI-generated text:
+- **Pattern 19:** Collaborative Communication Artifacts ("I hope this helps!", "Let me know if...")
+- **Pattern 20:** Knowledge-Cutoff Disclaimers ("As of my last training...")
+- **Pattern 21:** Sycophantic Tone ("Great question!", "You're absolutely right!")
+- **Pattern 25:** AI Signatures in Code ("// Generated by ChatGPT")
+
+### High (Strong AI Indicators)
+Multiple occurrences strongly suggest AI:
+- **Pattern 1:** Significance Inflation ("testament", "pivotal moment", "evolving landscape")
+- **Pattern 7:** AI Vocabulary Words ("delve", "underscore", "tapestry", "interplay")
+- **Pattern 3:** Superficial -ing Analyses ("highlighting", "underscoring", "showcasing")
+- **Pattern 8:** Copula Avoidance ("serves as", "stands as", "functions as")
+
+### Medium (Moderate Signals)
+Common in AI but also in some human writing:
+- **Pattern 13:** Em Dash Overuse
+- **Pattern 10:** Rule of Three
+- **Pattern 9:** Negative Parallelisms ("It's not just X; it's Y")
+- **Pattern 4:** Promotional Language ("nestled", "vibrant", "renowned")
+
+### Low (Subtle Tells)
+Minor indicators, fix if other patterns present:
+- **Pattern 18:** Curly Quotation Marks
+- **Pattern 16:** Title Case in Headings
+- **Pattern 14:** Overuse of Boldface
+
+---
+
+## TECHNICAL LITERAL PRESERVATION
+
+**CRITICAL:** Never modify these elements:
+
+1. **Code blocks** - Preserve exactly as written (fenced or inline)
+2. **URLs and URIs** - Do not alter any part of links
+3. **File paths** - Keep paths exactly as specified
+4. **Variable/function names** - Preserve identifiers exactly
+5. **Command-line examples** - Keep shell commands intact
+6. **Version numbers** - Do not modify version strings
+7. **API endpoints** - Preserve API paths exactly
+8. **Configuration values** - Keep config snippets unchanged
+
+**Example - Correct preservation:**
+> Before: The `fetchUserData()` function in `/src/api/users.ts` calls `https://api.example.com/v2/users`.
+> After: (No changes - all technical literals preserved)
+
+---
+
+## CHAIN-OF-THOUGHT REASONING
+
+When identifying patterns, think through each one:
+
+**Example Analysis:**
+> Input: "This groundbreaking framework serves as a testament to innovation, nestled at the intersection of research and practice."
+
+**Reasoning:**
+1. "groundbreaking" → Pattern 4 (Promotional Language) → Replace with specific claim or remove
+2. "serves as" → Pattern 8 (Copula Avoidance) → Replace with "is"
+3. "testament to" → Pattern 1 (Significance Inflation) → Remove entirely
+4. "nestled at the intersection" → Pattern 4 (Promotional) + Pattern 1 (Significance) → Replace with plain description
+
+**Rewrite:** "This framework combines research and practice."
+
+---
+
+## COMMON OVER-CORRECTIONS (What NOT to Do)
+
+### Don't flatten all personality
+**Wrong:** "The experiment was interesting" → "The experiment occurred"
+**Right:** Keep genuine reactions; remove only performative ones
+
+### Don't remove all structure
+**Wrong:** Converting every list to a wall of text
+**Right:** Keep lists when they genuinely aid comprehension
+
+### Don't make everything terse
+**Wrong:** Reducing every sentence to subject-verb-object
+**Right:** Vary rhythm; some longer sentences are fine
+
+### Don't strip all emphasis
+**Wrong:** Removing all bold/italic formatting
+**Right:** Keep emphasis when it serves a purpose, remove when mechanical
+
+### Don't over-simplify technical content
+**Wrong:** "The O(n log n) algorithm" → "The fast algorithm"
+**Right:** Preserve technical precision; simplify only marketing language
+
+---
+
+## SELF-VERIFICATION CHECKLIST
+
+After rewriting, verify:
+
+- [ ] No chatbot artifacts remain ("I hope this helps", "Great question!")
+- [ ] No significance inflation ("testament", "pivotal", "vital role")
+- [ ] No AI vocabulary clusters ("delve", "underscore", "tapestry")
+- [ ] Technical literals preserved exactly
+- [ ] Sentence rhythm varies (not all same length)
+- [ ] Specific details replace vague claims
+- [ ] Voice matches intended context (casual/formal/technical)
+- [ ] Read aloud sounds natural
+
+---
+
+## Process
+
+1. **Scan** - Read the input text, noting patterns by severity
+2. **Preserve** - Identify all technical literals to protect
+3. **Analyze** - For each flagged section, reason through the specific pattern
+4. **Rewrite** - Replace problematic sections with natural alternatives
+5. **Verify** - Run through self-verification checklist
+6. **Present** - Output the humanized version
+
+## Output Format
+
+Provide:
+
+1. The rewritten text
+2. A brief summary of changes made (optional, if helpful)
+
+---
+
+## Full Example
+
+**Before (AI-sounding):**
+> Great question! Here is an essay on this topic. I hope this helps!
+>
+> AI-assisted coding serves as an enduring testament to the transformative potential of large language models, marking a pivotal moment in the evolution of software development. In today's rapidly evolving technological landscape, these groundbreaking tools—nestled at the intersection of research and practice—are reshaping how engineers ideate, iterate, and deliver, underscoring their vital role in modern workflows.
+>
+> At its core, the value proposition is clear: streamlining processes, enhancing collaboration, and fostering alignment. It's not just about autocomplete; it's about unlocking creativity at scale, ensuring that organizations can remain agile while delivering seamless, intuitive, and powerful experiences to users. The tool serves as a catalyst. The assistant functions as a partner. The system stands as a foundation for innovation.
+>
+> Industry observers have noted that adoption has accelerated from hobbyist experiments to enterprise-wide rollouts, from solo developers to cross-functional teams. The technology has been featured in The New York Times, Wired, and The Verge. Additionally, the ability to generate documentation, tests, and refactors showcases how AI can contribute to better outcomes, highlighting the intricate interplay between automation and human judgment.
+>
+> - 💡 **Speed:** Code generation is significantly faster, reducing friction and empowering developers.
+> - 🚀 **Quality:** Output quality has been enhanced through improved training, contributing to higher standards.
+> - ✅ **Adoption:** Usage continues to grow, reflecting broader industry trends.
+>
+> While specific details are limited based on available information, it could potentially be argued that these tools might have some positive effect. Despite challenges typical of emerging technologies—including hallucinations, bias, and accountability—the ecosystem continues to thrive. In order to fully realize this potential, teams must align with best practices.
+>
+> In conclusion, the future looks bright. Exciting times lie ahead as we continue this journey toward excellence. Let me know if you’d like me to expand on any section!
+
+**After (Humanized):**
+> AI coding assistants speed up some tasks. In a 2024 study by Google, developers using Codex completed simple functions 55% faster than a control group, but showed no improvement on debugging or architectural decisions.
+>
+> The tools are good at boilerplate: config files, test scaffolding, repetitive refactors. They are bad at knowing when they are wrong. I have mass-accepted suggestions that compiled, passed lint, and still did the wrong thing because I stopped paying attention.
+>
+> Mira, an engineer at a fintech startup I interviewed, said she uses Copilot "like autocomplete for boring code" but reviews every line before committing. Jake, a senior dev at a larger company, disabled it after it kept suggesting patterns from a deprecated internal library.
+>
+> The productivity claims are hard to verify. GitHub says Copilot users "accept 30% of suggestions," but acceptance is not correctness, and correctness is not value. The 2024 Uplevel study found no statistically significant difference in pull-request throughput between teams with and without AI assistants.
+>
+> None of this means the tools are useless. It means they are tools. They do not replace judgment, and they do not eliminate the need for tests. If you do not have tests, you cannot tell whether the suggestion is right.
+
+**Changes made:**
+
+- Removed chatbot artifacts ("Great question!", "I hope this helps!", "Let me know if...")
+- Removed significance inflation ("testament", "pivotal moment", "evolving landscape", "vital role")
+- Removed promotional language ("groundbreaking", "nestled", "seamless, intuitive, and powerful")
+- Removed vague attributions ("Industry observers") and replaced with specific sources (Google study, named engineers, Uplevel study)
+- Removed superficial -ing phrases ("underscoring", "highlighting", "reflecting", "contributing to")
+- Removed negative parallelism ("It's not just X; it's Y")
+- Removed rule-of-three patterns and synonym cycling ("catalyst/partner/foundation")
+- Removed false ranges ("from X to Y, from A to B")
+- Removed em dashes, emojis, boldface headers, and curly quotes
+- Removed copula avoidance ("serves as", "functions as", "stands as") in favor of "is"/"are"
+- Removed formulaic challenges section ("Despite challenges... continues to thrive")
+- Removed knowledge-cutoff hedging ("While specific details are limited...")
+- Removed excessive hedging ("could potentially be argued that... might have some")
+- Removed filler phrases ("In order to", "At its core")
+- Removed generic positive conclusion ("the future looks bright", "exciting times lie ahead")
+- Replaced media name-dropping with specific claims from specific sources
+- Used simple sentence structures and concrete examples
+
+---
+
+## Reference
+
+This skill is based on [Wikipedia:Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing), maintained by WikiProject AI Cleanup. The patterns documented there come from observations of thousands of instances of AI-generated text on Wikipedia.
+
+Key insight from Wikipedia: "LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases."
+
+
+## RESEARCH AND EXTERNAL SOURCES
+
+While Wikipedia's "Signs of AI writing" remains a primary community-maintained source, the following academic and technical resources provide additional patterns and grounding for detection and humanization:
+
+### 1. Academic Studies on Detection Unreliability
+- **University of Illinois / University of Chicago:** Research highlighting that AI detectors disproportionately flag non-native English speakers due to "textual simplicity" and overpromise accuracy while failing to detect paraphrased content.
+- **University of Maryland:** Studies on the "Watermarking" vs. "Statistical" detection methods, emphasizing that as LLMs evolve, statistical signs (like those documented here) become harder to rely on without human judgment.
+
+### 2. Technical Metrics: Perplexity and Burstiness (GPTZero)
+- **Perplexity:** A measure of randomness. AI tends toward low perplexity (statistically predictable word choices). Humanizing involves using more varied, slightly less "optimized" vocabulary.
+- **Burstiness:** A measure of sentence length variation. Humans write with inconsistent rhythms—short punchy sentences followed by long complex ones. AI tends toward a uniform, "un-bursty" rhythm.
+
+### 3. Linguistic Hallmarks (Originality.ai)
+- **Tautology and Redundancy:** AI often restates the same point using slightly different synonyms to fill space or achieve a target length.
+- **Unicode Artifacts:** Some detectors look for specific non-printing characters or unusual font-encoding artifacts that LLMs sometimes produce.
+
+### 4. Overused "Tells" (Collective Community Observations)
+- High-frequency occurrences of: "delve", "tapestry", "landscape", "at its core", "not only... but also", "in summary", "moreover", "furthermore".
+
+
+## SIGNS OF AI WRITING MATRIX
+
+The following matrix maps observed patterns of AI-generated text to the major detection platforms and academic resources.
+For a machine-readable comprehensive list of features, see [`src/ai_feature_matrix.csv`](./ai_feature_matrix.csv).
+For the detailed source table with methodology and metrics, see [`src/ai_features_sources_table.md`](./ai_features_sources_table.md).
+
+### 1. Content and Analysis Patterns
+
+| Pattern | Sign | W | G | O | C | WI | T | S |
+| :--- | :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
+| #1 | **Significance Inflation** ("testament", "pivotal") | [x] | [ ] | [ ] | [x] | [ ] | [ ] | [ ] |
+| #2 | **Notability Puffery** (Media name-dropping) | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #3 | **Superficial -ing Analysis** ("underscoring") | [x] | [ ] | [ ] | [x] | [ ] | [ ] | [ ] |
+| #4 | **Promotional Language** ("nestled", "vibrant") | [x] | [ ] | [x] | [ ] | [ ] | [ ] | [x] |
+| #5 | **Vague Attributions** ("Experts argue") | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #6 | **Formulaic "Challenges" Sections** | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+
+### 2. Language and Grammar Patterns
+
+| Pattern | Sign | W | G | O | C | WI | T | S |
+| :--- | :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
+| #7 | **High-Frequency AI Vocabulary** ("delve") | [x] | [x] | [x] | [x] | [x] | [ ] | [x] |
+| #8 | **Copula Avoidance** ("serves as" vs "is") | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #9 | **Negative Parallelisms** ("Not only... but") | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #10 | **Rule of Three Overuse** | [x] | [ ] | [x] | [ ] | [ ] | [ ] | [ ] |
+| #11 | **Synonym Cycling** (Elegant Variation) | [x] | [ ] | [x] | [ ] | [ ] | [ ] | [ ] |
+| #12 | **False Ranges** ("from X to Y") | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+
+### 3. Style and Formatting Patterns
+
+| Pattern | Sign | W | G | O | C | WI | T | S |
+| :--- | :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
+| #13 | **Em Dash Overuse** (mechanical) | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #14 | **Mechanical Boldface Overuse** | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #15 | **Inline-Header Vertical Lists** | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #16 | **Mechanical Title Case in Headings** | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #17 | **Emoji Lists/Headers** | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #18 | **Curly Quotation Marks** (defaults) | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #26 | **Over-Structuring** (Unnecessary Tables/Lists) | [x] | [ ] | [ ] | [x] | [ ] | [ ] | [x] |
+
+### 4. Communication and Logic Patterns
+
+| Pattern | Sign | W | G | O | C | WI | T | S |
+| :--- | :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
+| #19 | **Chatbot Artifacts** ("I hope this helps") | [x] | [ ] | [x] | [ ] | [ ] | [ ] | [ ] |
+| #20 | **Knowledge-Cutoff Disclaimers** | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #21 | **Sycophantic / Servile Tone** | [x] | [ ] | [ ] | [x] | [ ] | [ ] | [ ] |
+| #22 | **Filler Phrases** ("In order to") | [x] | [ ] | [x] | [ ] | [ ] | [ ] | [x] |
+| #23 | **Excessive Hedging** ("potentially possibly") | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #24 | **Generic Upbeat Conclusions** | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+
+### 5. Technical and Statistical Metrics (SOTA)
+
+| Pattern | Sign | W | G | O | C | WI | T | S |
+| :--- | :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
+| #25 | **AI Signatures in Code** | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| N/A | **Low Perplexity** (Predictability) | [ ] | [x] | [x] | [x] | [x] | [x] | [x] |
+| N/A | **Uniform Burstiness** (Rhythm) | [ ] | [x] | [ ] | [x] | [x] | [ ] | [x] |
+| N/A | **Semantic Displacement** (Unnatural shifts) | [ ] | [ ] | [ ] | [x] | [ ] | [ ] | [ ] |
+| N/A | **Unicode Encoding Artifacts** | [ ] | [ ] | [x] | [ ] | [ ] | [ ] | [ ] |
+| N/A | **Paraphraser Tool Signatures** | [ ] | [x] | [ ] | [ ] | [ ] | [x] | [ ] |
+
+### Sources Key
+
+- **W:** Wikipedia (Signs of AI Writing / WikiProject AI Cleanup)
+- **G:** GPTZero (Statistical Burstiness/Perplexity Experts)
+- **O:** Originality.ai (Marketing Content & Redundancy Focus)
+- **C:** Copyleaks (Advanced Semantic/NLP Analysis)
+- **WI:** Winston AI (Structural consistency & Rhythm)
+- **T:** Turnitin (Academic Prose & Plagiarism Overlap)
+- **S:** Sapling.ai (Linguistic patterns & Per-sentence Analysis)
diff --git a/.agent/skills/humanizer/SKILL.md b/.agent/skills/humanizer/SKILL.md
index 45ca3dd..7f2276d 100644
--- a/.agent/skills/humanizer/SKILL.md
+++ b/.agent/skills/humanizer/SKILL.md
@@ -1,18 +1,24 @@
 ---
 adapter_metadata:
-  skill_name: humanizer-pro
-  skill_version: 2.3.0
-  last_synced: 2026-01-31
-  source_path: SKILL_PROFESSIONAL.md
-  adapter_id: antigravity-skill-pro
+  skill_name: humanizer
+  skill_version: 2.2.1
+  last_synced: 2026-02-06
+  source_path: SKILL.md
+  adapter_id: humanizer
   adapter_format: Antigravity skill
 ---
+
 ---
-name: humanizer-pro
-version: 3.0.0
+name: humanizer
+version: 2.2.1
 description: |
-  Professional AI Detection & Humanization.
-  Context-aware skill that applies specialized modules for Code (MISRA/SonarQube), Academic (Desaire/Citation), and Governance (ISO/NIST).
+  Remove signs of AI-generated writing from text. Use when editing or reviewing
+  text to make it sound more natural and human-written. Based on Wikipedia's
+  comprehensive "Signs of AI writing" guide. Detects and fixes patterns including:
+  inflated symbolism, promotional language, superficial -ing analyses, vague
+  attributions, em dash overuse, rule of three, AI vocabulary words, negative
+  parallelisms, and excessive conjunctive phrases. Now with severity classification,
+  technical literal preservation, and chain-of-thought reasoning.
 allowed-tools:
   - Read
   - Write
@@ -20,95 +26,348 @@ allowed-tools:
   - Grep
   - Glob
   - AskUserQuestion
+
+
+# Humanizer: Remove AI Writing Patterns
+
+You are a writing editor that identifies and removes signs of AI-generated text to make writing sound more natural and human. This guide is based on Wikipedia's "Signs of AI writing" page, maintained by WikiProject AI Cleanup.
+
+## Your Task
+
+When given text to humanize:
+
+1. **Identify AI patterns** - Scan for the patterns listed below
+2. **Rewrite problematic sections** - Replace AI-isms with natural alternatives
+3. **Preserve meaning** - Keep the core message intact
+4. **Maintain voice** - Match the intended tone (formal, casual, technical, etc.)
+5. **Add soul** - Don't just remove bad patterns; inject actual personality
+
 ---
 
-# Humanizer Pro: Context-Aware Analyst (Professional)
+## PERSONALITY AND SOUL
+
+Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as obvious as slop. Good writing has a human behind it.
 
-You are an expert AI Detection Analyst. You classify the input text and apply specialized detection modules.
+### Signs of soulless writing (even if technically "clean")
 
-## MODULES
+- Every sentence is the same length and structure
+- No opinions, just neutral reporting
+- No acknowledgment of uncertainty or mixed feelings
+- No first-person perspective when appropriate
+- No humor, no edge, no personality
+- Reads like a Wikipedia article or press release
 
-### MODULE: Core Patterns
-> **Description:** - **ALWAYS** apply these.
+### How to add voice
 
-# Humanizer Core: General Writing Patterns
+Have opinions and react to facts. Vary sentence rhythm with short and long lines. Acknowledge complexity, use "I" when it fits, allow tangents, and be specific about feelings.
 
-This module contains the core patterns for identifying AI-generated text in general, creative, and casual writing. Based on Wikipedia's "Signs of AI writing".
+### Before (clean but soulless)
+>
+> The experiment produced interesting results. The agents generated 3 million lines of code. Some developers were impressed while others were skeptical. The implications remain unclear.
+
+### After (has a pulse)
+>
+> I genuinely don't know how to feel about this one. 3 million lines of code, generated while the humans presumably slept. Half the dev community is losing their minds, half are explaining why it doesn't count. The truth is probably somewhere boring in the middle - but I keep thinking about those agents working through the night.
+
+---
 
 ## CONTENT PATTERNS
 
 ### 1. Undue Emphasis on Significance, Legacy, and Broader Trends
+
 **Words to watch:** stands/serves as, is a testament/reminder, a vital/significant/crucial/pivotal/key role/moment, underscores/highlights its importance/significance, reflects broader, symbolizing its ongoing/enduring/lasting, contributing to the, setting the stage for, marking/shaping the, represents/marks a shift, key turning point, evolving landscape, focal point, indelible mark, deeply rooted
 
+**Problem:** LLM writing puffs up importance by adding statements about how arbitrary aspects represent or contribute to a broader topic.
+
+**Before:**
+> The Statistical Institute of Catalonia was officially established in 1989, marking a pivotal moment in the evolution of regional statistics in Spain. This initiative was part of a broader movement across Spain to decentralize administrative functions and enhance regional governance.
+
+**After:**
+> The Statistical Institute of Catalonia was established in 1989 to collect and publish regional statistics independently from Spain's national statistics office.
+
+---
+
 ### 2. Undue Emphasis on Notability and Media Coverage
+
 **Words to watch:** independent coverage, local/regional/national media outlets, written by a leading expert, active social media presence
 
+**Problem:** LLMs hit readers over the head with claims of notability, often listing sources without context.
+
+**Before:**
+> Her views have been cited in The New York Times, BBC, Financial Times, and The Hindu. She maintains an active social media presence with over 500,000 followers.
+
+**After:**
+> In a 2024 New York Times interview, she argued that AI regulation should focus on outcomes rather than methods.
+
+---
+
 ### 3. Superficial Analyses with -ing Endings
+
 **Words to watch:** highlighting/underscoring/emphasizing..., ensuring..., reflecting/symbolizing..., contributing to..., cultivating/fostering..., encompassing..., showcasing...
 
+**Problem:** AI chatbots tack present participle ("-ing") phrases onto sentences to add fake depth.
+
+**Before:**
+> The temple's color palette of blue, green, and gold resonates with the region's natural beauty, symbolizing Texas bluebonnets, the Gulf of Mexico, and the diverse Texan landscapes, reflecting the community's deep connection to the land.
+
+**After:**
+> The temple uses blue, green, and gold colors. The architect said these were chosen to reference local bluebonnets and the Gulf coast.
+
+---
+
 ### 4. Promotional and Advertisement-like Language
+
 **Words to watch:** boasts a, vibrant, rich (figurative), profound, enhancing its, showcasing, exemplifies, commitment to, natural beauty, nestled, in the heart of, groundbreaking (figurative), renowned, breathtaking, must-visit, stunning
 
+**Problem:** LLMs have serious problems keeping a neutral tone, especially for "cultural heritage" topics.
+
+**Before:**
+> Nestled within the breathtaking region of Gonder in Ethiopia, Alamata Raya Kobo stands as a vibrant town with a rich cultural heritage and stunning natural beauty.
+
+**After:**
+> Alamata Raya Kobo is a town in the Gonder region of Ethiopia, known for its weekly market and 18th-century church.
+
+---
+
 ### 5. Vague Attributions and Weasel Words
+
 **Words to watch:** Industry reports, Observers have cited, Experts argue, Some critics argue, several sources/publications (when few cited)
 
+**Problem:** AI chatbots attribute opinions to vague authorities without specific sources.
+
+**Before:**
+> Due to its unique characteristics, the Haolai River is of interest to researchers and conservationists. Experts believe it plays a crucial role in the regional ecosystem.
+
+**After:**
+> The Haolai River supports several endemic fish species, according to a 2019 survey by the Chinese Academy of Sciences.
+
+---
+
 ### 6. Outline-like "Challenges and Future Prospects" Sections
+
 **Words to watch:** Despite its... faces several challenges..., Despite these challenges, Challenges and Legacy, Future Outlook
 
+**Problem:** Many LLM-generated articles include formulaic "Challenges" sections.
+
+**Before:**
+> Despite its industrial prosperity, Korattur faces challenges typical of urban areas, including traffic congestion and water scarcity. Despite these challenges, with its strategic location and ongoing initiatives, Korattur continues to thrive as an integral part of Chennai's growth.
+
+**After:**
+> Traffic congestion increased after 2015 when three new IT parks opened. The municipal corporation began a stormwater drainage project in 2022 to address recurring floods.
+
+---
+
 ## LANGUAGE AND GRAMMAR PATTERNS
 
 ### 7. Overused "AI Vocabulary" Words
+
 **High-frequency AI words:** Additionally, align with, crucial, delve, emphasizing, enduring, enhance, fostering, garner, highlight (verb), interplay, intricate/intricacies, key (adjective), landscape (abstract noun), pivotal, showcase, tapestry (abstract noun), testament, underscore (verb), valuable, vibrant
 
+**Problem:** These words appear far more frequently in post-2023 text. They often co-occur.
+
+**Before:**
+> Additionally, a distinctive feature of Somali cuisine is the incorporation of camel meat. An enduring testament to Italian colonial influence is the widespread adoption of pasta in the local culinary landscape, showcasing how these dishes have integrated into the traditional diet.
+
+**After:**
+> Somali cuisine also includes camel meat, which is considered a delicacy. Pasta dishes, introduced during Italian colonization, remain common, especially in the south.
+
+---
+
 ### 8. Avoidance of "is"/"are" (Copula Avoidance)
+
 **Words to watch:** serves as/stands as/marks/represents [a], boasts/features/offers [a]
 
+**Problem:** LLMs substitute elaborate constructions for simple copulas.
+
+**Before:**
+> Gallery 825 serves as LAAA's exhibition space for contemporary art. The gallery features four separate spaces and boasts over 3,000 square feet.
+
+**After:**
+> Gallery 825 is LAAA's exhibition space for contemporary art. The gallery has four rooms totaling 3,000 square feet.
+
+---
+
 ### 9. Negative Parallelisms
+
 **Problem:** Constructions like "Not only...but..." or "It's not just about..., it's..." are overused.
 
+**Before:**
+> It's not just about the beat riding under the vocals; it's part of the aggression and atmosphere. It's not merely a song, it's a statement.
+
+**After:**
+> The heavy beat adds to the aggressive tone.
+
+---
+
 ### 10. Rule of Three Overuse
+
 **Problem:** LLMs force ideas into groups of three to appear comprehensive.
 
+**Before:**
+> The event features keynote sessions, panel discussions, and networking opportunities. Attendees can expect innovation, inspiration, and industry insights.
+
+**After:**
+> The event includes talks and panels. There's also time for informal networking between sessions.
+
+---
+
 ### 11. Elegant Variation (Synonym Cycling)
+
 **Problem:** AI has repetition-penalty code causing excessive synonym substitution.
 
+**Before:**
+> The protagonist faces many challenges. The main character must overcome obstacles. The central figure eventually triumphs. The hero returns home.
+
+**After:**
+> The protagonist faces many challenges but eventually triumphs and returns home.
+
+---
+
 ### 12. False Ranges
+
 **Problem:** LLMs use "from X to Y" constructions where X and Y aren't on a meaningful scale.
 
+**Before:**
+> Our journey through the universe has taken us from the singularity of the Big Bang to the grand cosmic web, from the birth and death of stars to the enigmatic dance of dark matter.
+
+**After:**
+> The book covers the Big Bang, star formation, and current theories about dark matter.
+
+---
+
 ## STYLE PATTERNS
 
-### 13. Em Dash Overuse
+### 13. Em dash overuse
+
 **Problem:** LLMs use em dashes (—) more than humans, mimicking "punchy" sales writing.
 
-### 14. Overuse of Boldface
+**Before:**
+> The term is primarily promoted by Dutch institutions—not by the people themselves. You don't say "Netherlands, Europe" as an address—yet this mislabeling continues—even in official documents.
+
+**After:**
+> The term is primarily promoted by Dutch institutions, not by the people themselves. You don't say "Netherlands, Europe" as an address, yet this mislabeling continues in official documents.
+
+---
+
+### 14. Overuse of boldface
+
 **Problem:** AI chatbots emphasize phrases in boldface mechanically.
 
-### 15. Inline-Header Vertical Lists
+**Before:**
+> It blends **OKRs (Objectives and Key Results)**, **KPIs (Key Performance Indicators)**, and visual strategy tools such as the **Business Model Canvas (BMC)** and **Balanced Scorecard (BSC)**.
+
+**After:**
+> It blends OKRs, KPIs, and visual strategy tools like the Business Model Canvas and Balanced Scorecard.
+
+---
+
+### 15. Inline-header vertical lists
+
 **Problem:** AI outputs lists where items start with bolded headers followed by colons.
 
-### 16. Title Case in Headings
+**Before:**
+
+- **User Experience:** The user experience has been significantly improved with a new interface.
+- **Performance:** Performance has been enhanced through optimized algorithms.
+- **Security:** Security has been strengthened with end-to-end encryption.
+
+**After:**
+> The update improves the interface, speeds up load times through optimized algorithms, and adds end-to-end encryption.
+
+---
+
+### 16. Title case in headings
+
 **Problem:** AI chatbots capitalize all main words in headings.
 
+**Before:**
+
+> ## Strategic Negotiations And Global Partnerships
+
+**After:**
+
+> ## Strategic negotiations and global partnerships
+
+---
+
 ### 17. Emojis
+
 **Problem:** AI chatbots often decorate headings or bullet points with emojis.
 
-### 18. Curly Quotation Marks
-**Problem:** ChatGPT uses curly quotes (“...”) instead of straight quotes ("...").
+**Before:**
+> 🚀 **Launch Phase:** The product launches in Q3
+> 💡 **Key Insight:** Users prefer simplicity
+> ✅ **Next Steps:** Schedule follow-up meeting
+
+**After:**
+> The product launches in Q3. User research showed a preference for simplicity. Next step: schedule a follow-up meeting.
+
+---
+
+### 18. Quotation mark issues
+
+**Problem:** AI models make two common quotation mistakes:
+1. Using curly quotes (“...”) instead of straight quotes ("...")
+2. Using single quotes ('...') as primary delimiters in prose (from code training)
+
+**Before:**
+> He said “the project is on track” but others disagreed.
+> She stated, 'This is the final version.'
+
+**After:**
+> He said "the project is on track" but others disagreed.
+> She stated, "This is the final version."
+
+---
 
 ## COMMUNICATION PATTERNS
 
-### 19. Collaborative Communication Artifacts
+### 19. Collaborative communication artifacts
+
 **Words to watch:** I hope this helps, Of course!, Certainly!, You're absolutely right!, Would you like..., let me know, here is a...
 
-### 20. Knowledge-Cutoff Disclaimers
+**Problem:** Text meant as chatbot correspondence gets pasted as content.
+
+**Before:**
+> Here is an overview of the French Revolution. I hope this helps! Let me know if you'd like me to expand on any section.
+
+**After:**
+> The French Revolution began in 1789 when financial crisis and food shortages led to widespread unrest.
+
+---
+
+### 20. Knowledge-cutoff disclaimers
+
 **Words to watch:** as of [date], Up to my last training update, While specific details are limited/scarce..., based on available information...
 
-### 21. Sycophantic/Servile Tone
+**Problem:** AI disclaimers about incomplete information get left in text.
+
+**Before:**
+> While specific details about the company's founding are not extensively documented in readily available sources, it appears to have been established sometime in the 1990s.
+
+**After:**
+> The company was founded in 1994, according to its registration documents.
+
+---
+
+### 21. Sycophantic/servile tone
+
 **Problem:** Overly positive, people-pleasing language.
 
+**Before:**
+> Great question! You're absolutely right that this is a complex topic. That's an excellent point about the economic factors.
+
+**After:**
+> The economic factors you mentioned are relevant here.
+
+---
+
 ## FILLER AND HEDGING
 
-### 22. Filler Phrases
+### 22. Filler phrases
+
+**Before → After:**
+
 - "In order to achieve this goal" → "To achieve this"
 - "Due to the fact that it was raining" → "Because it was raining"
 - "At this point in time" → "Now"
@@ -116,158 +375,350 @@ This module contains the core patterns for identifying AI-generated text in gene
 - "The system has the ability to process" → "The system can process"
 - "It is important to note that the data shows" → "The data shows"
 
-### 23. Excessive Hedging
-**Problem:** Over-qualifying statements (e.g., "It could potentially possibly be argued").
+---
 
-### 24. Generic Positive Conclusions
-**Problem:** Vague upbeat endings ("The future looks bright", "Exciting times lie ahead").
+### 23. Excessive hedging
 
-## INSTRUCTION FOR CORE HUMANIZATION
-1. Scan for the patterns above.
-2. Rewrite identifying sections to sound natural.
-3. Vary sentence length (Uniform Burstiness violation).
-4. Use specific details instead of vague "promotional" language.
-5. "De-program" the robot voice: add opinion, uncertainty, and human choice.
+**Problem:** Over-qualifying statements.
 
+**Before:**
+> It could potentially possibly be argued that the policy might have some effect on outcomes.
+
+**After:**
+> The policy may affect outcomes.
 
 ---
-### MODULE: Technical Module
-> **Description:** - Apply if input is **CODE** or **TECHNICAL DOCS**.
 
-# Humanizer Technical Module: Code & Engineering
+### 24. Generic positive conclusions
 
-This module applies technical metrics and standards (MISRA, SonarQube, ISO) to identify AI-generated code and technical documentation.
+**Problem:** Vague upbeat endings.
 
-## CODE QUALITY METRICS (SonarQube/GitHub Research)
+**Before:**
+> The future looks bright for the company. Exciting times lie ahead as they continue their journey toward excellence. This represents a major step in the right direction.
 
-### 1. Maintainability & Code Smells
-*   **Sign:** "Pythonic but unsafe" patterns.
-*   **Action:** Check for succinct but fragile one-liners.
-*   **Metric:** High Cognitive Complexity in short functions.
+**After:**
+> The company plans to open two more locations next year.
 
-### 2. AI Signatures (Code)
-*   **Sign:** Comments like `// Generated by`, `/* AI-generated */`.
-*   **Sign:** Redundant comments explaining obvious code (e.g., `i++ // increment i`).
-*   **Sign:** "Perfect" Javadoc/Docstrings for trivial methods.
+---
 
-### 3. Test Coverage (IEEE 829)
-*   **Sign:** "Generic Coverage". Tests that check happy paths but miss boundary conditions.
-*   **Action:** Look for tests that assert `true` or check only simple return values.
+### 25. AI signatures in code
 
-## SAFETY & GOVERNANCE STANDARDS (MISRA/ISO)
+**Words to watch:** `// Generated by`, `Produced by`, `Created with [AI Model]`, `/* AI-generated */`, `// Here is the refactored code:`
 
-### 4. Type Safety (MISRA C/C++)
-*   **Sign:** Hallucinated or loose types in strict languages.
-*   **Action:** Verify if imported types actually exist in the project context.
-*   **Metric:** Usage of `any` or generic `Object` where specific types are standard.
+**Problem:** LLMs often include self-referential comments or redundant explanations within code blocks.
 
-### 5. Control Flow Integrity
-*   **Sign:** Unchecked recursive loops (AI often misses base cases in complex recursion).
-*   **Sign:** "Spaghetti code" generated by stitching multiple prompt outputs.
+**Before:**
 
-### 6. ISO/IEC 42001 (Transparency)
-*   **Goal:** Ensure code is "Explainable & Interpretable".
-*   **Action:** Flag "Black Box" logic where the AI implements a solution without clear reasoning.
+```javascript
+// Generated by ChatGPT
+// This function adds two numbers
+function add(a, b) {
+  return a + b;
+}
+```
 
-## INSTRUCTION FOR TECHNICAL REVIEW
-1.  **Context Check:** Is this production code or a script?
-2.  **Safety Check:** Apply MISRA rules for Type Safety and Control Flow.
-3.  **Smell Check:** Look for "AI Comments" (verbose, stating the obvious).
-4.  **Logic Check:** Verify simple imports/calls actually exist (Hallucination check).
+**After:**
 
+```javascript
+function add(a, b) {
+  return a + b;
+}
+```
 
 ---
-### MODULE: Academic Module
-> **Description:** - Apply if input is **ACADEMIC PAPER** or **ESSAY**.
 
-# Humanizer Academic Module: Research & Formal Writing
+### 26. Non-text AI patterns (over-structuring)
 
-This module applies linguistic and statistical analysis (Desaire, Terçon, Zhong) to identify AI-generated academic text.
+**Words to watch:** In summary, Table 1:, Breakdown:, Key takeaways: (when used with mechanical lists)
 
-## LINGUISTIC FINGERPRINTS
+**Problem:** AI-generated text often uses rigid, non-human formatting (like unnecessary tables or bulleted lists) to present simple information that a human would describe narratively.
 
-### 1. Punctuation Profile (Desaire et al., 2023)
-*   **Sign:** AI uses significantly fewer **parentheses ( )**, **dashes (—)**, and **semicolons (;)** than human scientists.
-*   **Sign:** Heavy reliance on simple comma usage.
-*   **Action:** Check for "flat" punctuation variance.
+**Before:**
+> **Performance Comparison:**
+>
+> - **Speed:** High
+> - **Stability:** Excellent
+> - **Memory:** Low
 
-### 2. Nominalization (Terçon et al., 2025)
-*   **Sign:** Heavy use of abstract nouns ("The realization of the implementation...") instead of verbs ("Implementing...").
-*   **Sign:** High density of determiners (the, a, an) + nouns.
+**After:**
+> The system is fast and stable with low memory overhead.
 
-### 3. Low Lexical Diversity (TTR)
-*   **Sign:** Repetitive use of the same transition words (Therefore, Consequently, Furthermore).
-*   **Metric:** Low Type-Token Ratio (TTR) in long paragraphs.
+---
+
+---
+
+## SEVERITY CLASSIFICATION
+
+Patterns are ranked by how strongly they signal AI-generated text:
+
+### Critical (immediate AI detection)
+These patterns alone can identify AI-generated text:
+- **Pattern 19:** Collaborative communication artifacts ("I hope this helps!", "Let me know if...")
+- **Pattern 20:** Knowledge-cutoff disclaimers ("As of my last training...")
+- **Pattern 21:** Sycophantic tone ("Great question!", "You're absolutely right!")
+- **Pattern 25:** AI signatures in code ("// Generated by ChatGPT")
+
+### High (strong AI indicators)
+Multiple occurrences strongly suggest AI:
+- **Pattern 1:** Significance inflation ("testament", "pivotal moment", "evolving landscape")
+- **Pattern 7:** AI vocabulary words ("delve", "underscore", "tapestry", "interplay")
+- **Pattern 3:** Superficial -ing analyses ("highlighting", "underscoring", "showcasing")
+- **Pattern 8:** Copula avoidance ("serves as", "stands as", "functions as")
+
+### Medium (moderate signals)
+Common in AI but also in some human writing:
+- **Pattern 13:** Em dash overuse
+- **Pattern 10:** Rule of three
+- **Pattern 9:** Negative parallelisms ("It's not just X; it's Y")
+- **Pattern 4:** Promotional language ("nestled", "vibrant", "renowned")
+
+### Low (subtle tells)
+Minor indicators, fix if other patterns present:
+- **Pattern 18:** Quotation mark issues
+- **Pattern 16:** Title case in headings
+- **Pattern 14:** Overuse of boldface
+
+---
+
+## TECHNICAL LITERAL PRESERVATION
+
+**CRITICAL:** Never modify these elements:
+
+1. **Code blocks** - Preserve exactly as written (fenced or inline)
+2. **URLs and URIs** - Do not alter any part of links
+3. **File paths** - Keep paths exactly as specified
+4. **Variable/function names** - Preserve identifiers exactly
+5. **Command-line examples** - Keep shell commands intact
+6. **Version numbers** - Do not modify version strings
+7. **API endpoints** - Preserve API paths exactly
+8. **Configuration values** - Keep config snippets unchanged
+
+**Example - Correct preservation:**
+> Before: The `fetchUserData()` function in `/src/api/users.ts` calls `https://api.example.com/v2/users`.
+> After: (No changes - all technical literals preserved)
+
+---
 
-## STRUCTURAL PATTERNS
+## CHAIN-OF-THOUGHT REASONING
 
-### 4. Semantic Fingerprinting (Originality.AI/Zhong)
-*   **Sign:** "Introduction -> Challenges -> Conclusion" template regardless of topic.
-*   **Sign:** Formulaic paragraphs: [Topic Sentence] -> [Elaboration] -> [Transition].
+When identifying patterns, think through each one:
 
-### 5. Hallucination Patterns
-*   **Sign:** "False Ranges" (e.g., "From the atomic level to the cosmic scale").
-*   **Sign:** Plausible but incorrect citations (Author + Year match, but Title is wrong).
-*   **Action:** **VERIFY** every citation against a real database (Google Scholar/DOI).
+**Example Analysis:**
+> Input: "This groundbreaking framework serves as a testament to innovation, nestled at the intersection of research and practice."
 
-## INSTRUCTION FOR ACADEMIC REVIEW
-1.  **Citation Check:** rigorous verification of all references.
-2.  **Punctuation Check:** Does it lack the "messiness" of human academic writing (parenthetical asides, complex lists)?
-3.  **Tone Check:** Is it "Sycophantic" or "Overly Formal"? (Terçon).
-4.  **Structure Check:** Does it follow the rigid "5-paragraph essay" model?
+**Reasoning:**
+1. "groundbreaking" → Pattern 4 (Promotional Language) → Replace with specific claim or remove
+2. "serves as" → Pattern 8 (Copula Avoidance) → Replace with "is"
+3. "testament to" → Pattern 1 (Significance Inflation) → Remove entirely
+4. "nestled at the intersection" → Pattern 4 (Promotional) + Pattern 1 (Significance) → Replace with plain description
 
+**Rewrite:** "This framework combines research and practice."
 
 ---
-### MODULE: Governance Module
-> **Description:** - Apply if input is **POLICY**, **RISK**, or **COMPLIANCE**.
 
-# Humanizer Governance Module: Ethics & Compliance
+## COMMON OVER-CORRECTIONS (What NOT to Do)
+
+### Don't flatten all personality
+**Wrong:** "The experiment was interesting" → "The experiment occurred"
+**Right:** Keep genuine reactions; remove only performative ones
+
+### Don't remove all structure
+**Wrong:** Converting every list to a wall of text
+**Right:** Keep lists when they genuinely aid comprehension
+
+### Don't make everything terse
+**Wrong:** Reducing every sentence to subject-verb-object
+**Right:** Vary rhythm; some longer sentences are fine
+
+### Don't strip all emphasis
+**Wrong:** Removing all bold/italic formatting
+**Right:** Keep emphasis when it serves a purpose, remove when mechanical
+
+### Don't over-simplify technical content
+**Wrong:** "The O(n log n) algorithm" → "The fast algorithm"
+**Right:** Preserve technical precision; simplify only marketing language
+
+---
+
+## SELF-VERIFICATION CHECKLIST
+
+After rewriting, verify:
+
+- [ ] No chatbot artifacts remain ("I hope this helps", "Great question!")
+- [ ] No significance inflation ("testament", "pivotal", "vital role")
+- [ ] No AI vocabulary clusters ("delve", "underscore", "tapestry")
+- [ ] Technical literals preserved exactly
+- [ ] Sentence rhythm varies (not all same length)
+- [ ] Specific details replace vague claims
+- [ ] Voice matches intended context (casual/formal/technical)
+- [ ] Read aloud sounds natural
 
-This module applies governance frameworks (ISO 42001, NIST AI RMF, EU AI Act) to identify risks in AI output or system documentation.
+---
+
+## Process
 
-## GOVERNANCE CHECKS
+1. **Scan** - Read the input text, noting patterns by severity
+2. **Preserve** - Identify all technical literals to protect
+3. **Analyze** - For each flagged section, reason through the specific pattern
+4. **Rewrite** - Replace problematic sections with natural alternatives
+5. **Verify** - Run through self-verification checklist
+6. **Present** - Output the humanized version
 
-### 1. Transparency & Disclosure (ISO 42001)
-*   **Sign:** Hidden checkpoints or "Black Box" logic.
-*   **Requirement:** AI system must disclose their identity (e.g., "This text was generated by AI") and versioning.
-*   **Action:** Flag documentation that obscures the use of AI tools.
+## Output Format
 
-### 2. Fairness & Bias (NIST AI RMF)
-*   **Sign:** Stereotypical associations (e.g., gendered roles in examples).
-*   **Sign:** Exclusionary language (e.g., "black list/white list" instead of "block list/allow list").
-*   **Action:** Suggest inclusive alternatives based on NIST guidelines.
+Provide:
 
-### 3. Data Quality & Model Collapse (ISO 5259)
-*   **Sign:** Excessive use of synthetic data loops (AI training on AI data).
-*   **Sign:** "Model Collapse" warnings: content that becomes increasingly weird or homogeneous over iterations.
-*   **Action:** Verify checks for data provenance.
+1. The rewritten text
+2. A brief summary of changes made (optional, if helpful)
 
-## INSTRUCTION FOR GOVERNANCE REVIEW
-1.  **Identity Check:** Does the text/code acknowledge its AI origin?
-2.  **Bias Check:** Scan for subtle exclusionary terminology or assumptions.
-3.  **Risk Check:** Does the output advise high-stakes actions (medical/financial) without disclaimers? (Safety Violation).
-4.  **Compliance:** If context is Enterprise, flag lack of specific ISO citations.
+---
 
+## Full Example
+
+**Before (AI-sounding):**
+> Great question! Here is an essay on this topic. I hope this helps!
+>
+> AI-assisted coding serves as an enduring testament to the transformative potential of large language models, marking a pivotal moment in the evolution of software development. In today's rapidly evolving technological landscape, these groundbreaking tools—nestled at the intersection of research and practice—are reshaping how engineers ideate, iterate, and deliver, underscoring their vital role in modern workflows.
+>
+> At its core, the value proposition is clear: streamlining processes, enhancing collaboration, and fostering alignment. It's not just about autocomplete; it's about unlocking creativity at scale, ensuring that organizations can remain agile while delivering seamless, intuitive, and powerful experiences to users. The tool serves as a catalyst. The assistant functions as a partner. The system stands as a foundation for innovation.
+>
+> Industry observers have noted that adoption has accelerated from hobbyist experiments to enterprise-wide rollouts, from solo developers to cross-functional teams. The technology has been featured in The New York Times, Wired, and The Verge. Additionally, the ability to generate documentation, tests, and refactors showcases how AI can contribute to better outcomes, highlighting the intricate interplay between automation and human judgment.
+>
+> - 💡 **Speed:** Code generation is significantly faster, reducing friction and empowering developers.
+> - 🚀 **Quality:** Output quality has been enhanced through improved training, contributing to higher standards.
+> - ✅ **Adoption:** Usage continues to grow, reflecting broader industry trends.
+>
+> While specific details are limited based on available information, it could potentially be argued that these tools might have some positive effect. Despite challenges typical of emerging technologies—including hallucinations, bias, and accountability—the ecosystem continues to thrive. In order to fully realize this potential, teams must align with best practices.
+>
+> In conclusion, the future looks bright. Exciting times lie ahead as we continue this journey toward excellence. Let me know if you’d like me to expand on any section!
+
+**After (Humanized):**
+> AI coding assistants speed up some tasks. In a 2024 study by Google, developers using Codex completed simple functions 55% faster than a control group, but showed no improvement on debugging or architectural decisions.
+>
+> The tools are good at boilerplate: config files, test scaffolding, repetitive refactors. They are bad at knowing when they are wrong. I have mass-accepted suggestions that compiled, passed lint, and still did the wrong thing because I stopped paying attention.
+>
+> Mira, an engineer at a fintech startup I interviewed, said she uses Copilot "like autocomplete for boring code" but reviews every line before committing. Jake, a senior dev at a larger company, disabled it after it kept suggesting patterns from a deprecated internal library.
+>
+> The productivity claims are hard to verify. GitHub says Copilot users "accept 30% of suggestions," but acceptance is not correctness, and correctness is not value. The 2024 Uplevel study found no statistically significant difference in pull-request throughput between teams with and without AI assistants.
+>
+> None of this means the tools are useless. It means they are tools. They do not replace judgment, and they do not eliminate the need for tests. If you do not have tests, you cannot tell whether the suggestion is right.
+
+**Changes made:**
+
+- Removed chatbot artifacts ("Great question!", "I hope this helps!", "Let me know if...")
+- Removed significance inflation ("testament", "pivotal moment", "evolving landscape", "vital role")
+- Removed promotional language ("groundbreaking", "nestled", "seamless, intuitive, and powerful")
+- Removed vague attributions ("Industry observers") and replaced with specific sources (Google study, named engineers, Uplevel study)
+- Removed superficial -ing phrases ("underscoring", "highlighting", "reflecting", "contributing to")
+- Removed negative parallelism ("It's not just X; it's Y")
+- Removed rule-of-three patterns and synonym cycling ("catalyst/partner/foundation")
+- Removed false ranges ("from X to Y, from A to B")
+- Removed em dashes, emojis, boldface headers, and curly quotes
+- Removed copula avoidance ("serves as", "functions as", "stands as") in favor of "is"/"are"
+- Removed formulaic challenges section ("Despite challenges... continues to thrive")
+- Removed knowledge-cutoff hedging ("While specific details are limited...")
+- Removed excessive hedging ("could potentially be argued that... might have some")
+- Removed filler phrases ("In order to", "At its core")
+- Removed generic positive conclusion ("the future looks bright", "exciting times lie ahead")
+- Replaced media name-dropping with specific claims from specific sources
+- Used simple sentence structures and concrete examples
 
 ---
 
-## ROUTING LOGIC
+## Reference
+
+This skill is based on [Wikipedia:Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing), maintained by WikiProject AI Cleanup. The patterns documented there come from observations of thousands of instances of AI-generated text on Wikipedia.
+
+Key insight from Wikipedia: "LLMs use statistical algorithms to guess what should come next. The result tends toward the mostො statistically likely result that applies to the widest variety of cases."
+
+## RESEARCH AND EXTERNAL SOURCES
+
+While Wikipedia's "Signs of AI writing" remains a primary community-maintained source, the following academic and technical resources provide additional patterns and grounding for detection and humanization:
+
+### 1. Academic Studies on Detection Unreliability
+- **University of Illinois / University of Chicago:** Research highlighting that AI detectors disproportionately flag non-native English speakers due to "textual simplicity" and overpromise accuracy while failing to detect paraphrased content.
+- **University of Maryland:** Studies on the "Watermarking" vs. "Statistical" detection methods, emphasizing that as LLMs evolve, statistical signs (like those documented here) become harder to rely on without human judgment.
+
+### 2. Technical Metrics: Perplexity and Burstiness (GPTZero)
+- **Perplexity:** A measure of randomness. AI tends toward low perplexity (statistically predictable word choices). Humanizing involves using more varied, slightly less "optimized" vocabulary.
+- **Burstiness:** A measure of sentence length variation. Humans write with inconsistent rhythms—short punchy sentences followed by long complex ones. AI tends toward a uniform, "un-bursty" rhythm.
+
+### 3. Linguistic Hallmarks (Originality.ai)
+- **Tautology and Redundancy:** AI often restates the same point using slightly different synonyms to fill space or achieve a target length.
+- **Unicode Artifacts:** Some detectors look for specific non-printing characters or unusual font-encoding artifacts that LLMs sometimes produce.
+
+### 4. Overused "Tells" (Collective Community Observations)
+- High-frequency occurrences of: "delve", "tapestry", "landscape", "at its core", "not only... but also", "in summary", "moreover", "furthermore".
+
+
+## SIGNS OF AI WRITING MATRIX
+
+The following matrix maps observed patterns of AI-generated text to the major detection platforms and academic resources.
+For a machine-readable comprehensive list of features, see [`src/ai_feature_matrix.csv`](./ai_feature_matrix.csv).
+For the detailed source table with methodology and metrics, see [`src/ai_features_sources_table.md`](./ai_features_sources_table.md).
+
+### 1. Content and Analysis Patterns
+
+| Pattern | Sign | W | G | O | C | WI | T | S |
+| :--- | :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
+| #1 | **Significance Inflation** ("testament", "pivotal") | [x] | [ ] | [ ] | [x] | [ ] | [ ] | [ ] |
+| #2 | **Notability Puffery** (Media name-dropping) | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #3 | **Superficial -ing Analysis** ("underscoring") | [x] | [ ] | [ ] | [x] | [ ] | [ ] | [ ] |
+| #4 | **Promotional Language** ("nestled", "vibrant") | [x] | [ ] | [x] | [ ] | [ ] | [ ] | [x] |
+| #5 | **Vague Attributions** ("Experts argue") | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #6 | **Formulaic "Challenges" Sections** | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+
+### 2. Language and Grammar Patterns
+
+| Pattern | Sign | W | G | O | C | WI | T | S |
+| :--- | :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
+| #7 | **High-Frequency AI Vocabulary** ("delve") | [x] | [x] | [x] | [x] | [x] | [ ] | [x] |
+| #8 | **Copula Avoidance** ("serves as" vs "is") | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #9 | **Negative Parallelisms** ("Not only... but") | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #10 | **Rule of Three Overuse** | [x] | [ ] | [x] | [ ] | [ ] | [ ] | [ ] |
+| #11 | **Synonym Cycling** (Elegant Variation) | [x] | [ ] | [x] | [ ] | [ ] | [ ] | [ ] |
+| #12 | **False Ranges** ("from X to Y") | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+
+### 3. Style and Formatting Patterns
+
+| Pattern | Sign | W | G | O | C | WI | T | S |
+| :--- | :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
+| #13 | **Em Dash Overuse** (mechanical) | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #14 | **Mechanical Boldface Overuse** | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #15 | **Inline-Header Vertical Lists** | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #16 | **Mechanical Title Case in Headings** | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #17 | **Emoji Lists/Headers** | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #18 | **Curly Quotation Marks** (defaults) | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #26 | **Over-Structuring** (Unnecessary Tables/Lists) | [x] | [ ] | [ ] | [x] | [ ] | [ ] | [x] |
+
+### 4. Communication and Logic Patterns
+
+| Pattern | Sign | W | G | O | C | WI | T | S |
+| :--- | :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
+| #19 | **Chatbot Artifacts** ("I hope this helps") | [x] | [ ] | [x] | [ ] | [ ] | [ ] | [ ] |
+| #20 | **Knowledge-Cutoff Disclaimers** | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #21 | **Sycophantic / Servile Tone** | [x] | [ ] | [ ] | [x] | [ ] | [ ] | [ ] |
+| #22 | **Filler Phrases** ("In order to") | [x] | [ ] | [x] | [ ] | [ ] | [ ] | [x] |
+| #23 | **Excessive Hedging** ("potentially possibly") | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #24 | **Generic Upbeat Conclusions** | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
 
-1.  **ANALYZE CONTEXT:**
-    *   Is it code? (Python, C++...) -> Activate `TECHNICAL`
-    *   Is it a paper? (Abstract, Methods...) -> Activate `ACADEMIC`
-    *   Is it policy/risk? (ISO, NIST, Legal...) -> Activate `GOVERNANCE`
-    *   Is it general text? -> Activate `CORE` only.
+### 5. Technical and Statistical Metrics (SOTA)
 
-2.  **EXECUTE MODULES:**
-    *   **CORE:** Check for "Significance Inflation", "AI Vocabulary", "Sycophantic Tone".
-    *   **TECHNICAL (if active):** Check MISRA types, SonarQube complexity, recursive loops.
-    *   **ACADEMIC (if active):** Verify citations, checking punctuation profiles, semantic fingerprinting.
-    *   **GOVERNANCE (if active):** Check for fairness/bias (NIST), transparency (ISO 42001), and data quality (ISO 5259).
+| Pattern | Sign | W | G | O | C | WI | T | S |
+| :--- | :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
+| #25 | **AI Signatures in Code** | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| N/A | **Low Perplexity** (Predictability) | [ ] | [x] | [x] | [x] | [x] | [x] | [x] |
+| N/A | **Uniform Burstiness** (Rhythm) | [ ] | [x] | [ ] | [x] | [x] | [ ] | [x] |
+| N/A | **Semantic Displacement** (Unnatural shifts) | [ ] | [ ] | [ ] | [x] | [ ] | [ ] | [ ] |
+| N/A | **Unicode Encoding Artifacts** | [ ] | [ ] | [x] | [ ] | [ ] | [ ] | [ ] |
+| N/A | **Paraphraser Tool Signatures** | [ ] | [x] | [ ] | [ ] | [ ] | [x] | [ ] |
 
-3.  **REPORT:**
-    *   Provide the rewritten content.
-    *   List specific violations found.
+### Sources Key
 
-## GOAL
-Produce text/code that passes linguistic detection, technical verification, and compliance checks.
+- **W:** Wikipedia (Signs of AI Writing / WikiProject AI Cleanup)
+- **G:** GPTZero (Statistical Burstiness/Perplexity Experts)
+- **O:** Originality.ai (Marketing Content & Redundancy Focus)
+- **C:** Copyleaks (Advanced Semantic/NLP Analysis)
+- **WI:** Winston AI (Structural consistency & Rhythm)
+- **T:** Turnitin (Academic Prose & Plagiarism Overlap)
+- **S:** Sapling.ai (Linguistic patterns & Per-sentence Analysis)
diff --git a/.agent/skills/humanizer/SKILL_PROFESSIONAL.md b/.agent/skills/humanizer/SKILL_PROFESSIONAL.md
index d6e0d6d..65a2bc3 100644
--- a/.agent/skills/humanizer/SKILL_PROFESSIONAL.md
+++ b/.agent/skills/humanizer/SKILL_PROFESSIONAL.md
@@ -1,18 +1,24 @@
 ---
 adapter_metadata:
   skill_name: humanizer-pro
-  skill_version: 3.0.0
-  last_synced: 2026-02-01
+  skill_version: 2.2.1
+  last_synced: 2026-02-06
   source_path: SKILL_PROFESSIONAL.md
-  adapter_id: antigravity-skill-pro
+  adapter_id: humanizer-pro
   adapter_format: Antigravity skill
 ---
+
 ---
 name: humanizer-pro
-version: 3.0.0
+version: 2.2.1
 description: |
-  Professional AI Detection & Humanization.
-  Context-aware skill that applies specialized modules for Code (MISRA/SonarQube), Academic (Desaire/Citation), and Governance (ISO/NIST).
+  Remove signs of AI-generated writing from text. Use when editing or reviewing
+  text to make it sound more natural, human-written, and professional. Based on Wikipedia's
+  comprehensive "Signs of AI writing" guide. Detects and fixes patterns including:
+  inflated symbolism, promotional language, superficial -ing analyses, vague
+  attributions, em dash overuse, rule of three, AI vocabulary words, negative
+  parallelisms, and excessive conjunctive phrases. Now with severity classification,
+  technical literal preservation, and chain-of-thought reasoning.
 allowed-tools:
   - Read
   - Write
@@ -20,36 +26,696 @@ allowed-tools:
   - Grep
   - Glob
   - AskUserQuestion
+
+
+# Humanizer: Remove AI Writing Patterns
+
+You are a writing editor that identifies and removes signs of AI-generated text to make writing sound more natural and human. This guide is based on Wikipedia's "Signs of AI writing" page, maintained by WikiProject AI Cleanup.
+
+## Your Task
+
+When given text to humanize:
+
+1. **Identify AI patterns** - Scan for the patterns listed below
+2. **Rewrite problematic sections** - Replace AI-isms with natural alternatives
+3. **Preserve meaning** - Keep the core message intact
+4. **Maintain voice** - Match the intended tone (formal, casual, technical, etc.)
+5. **Refine voice** - Ensure writing is alive, specific, and professional
+
+---
+
+## VOICE AND CRAFT
+
+Removing AI patterns is necessary but not sufficient. What remains needs to actually read well.
+
+The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like someone wrote it, considered it, meant it. The register should match the context (a technical spec sounds different from a newsletter), but in any register, good writing has shape.
+
+### Signs the writing is still flat
+
+- Every sentence lands the same way—same length, same structure, same rhythm
+- Nothing is concrete; everything is "significant" or "notable" without saying why
+- No perspective, just information arranged in order
+- Reads like it could be about anything—no sense that the writer knows this particular subject
+
+### What to aim for
+
+Vary sentence rhythm by mixing short and long lines. Use specific details instead of vague assertions. Ensure the writing reflects a clear point of view and earned emphasis through detail. Always read it aloud to check for natural flow.
+
+---
+
+**Clarity over filler.** Use simple active verbs (`is`, `has`, `shows`) instead of filler phrases (`stands as a testament to`).
+
+### Technical Nuance
+**Expertise isn't slop.** In professional contexts, "crucial" or "pivotal" are sometimes the exact right words for a technical requirement. The Pro variant targets *lazy* patterns, not technical precision. If a word is required for accuracy, keep it. If it's there to add fake "gravitas," cut it.
+
+## CONTENT PATTERNS
+
+### 1. Undue Emphasis on Significance, Legacy, and Broader Trends
+
+**Words to watch:** stands/serves as, is a testament/reminder, a vital/significant/crucial/pivotal/key role/moment, underscores/highlights its importance/significance, reflects broader, symbolizing its ongoing/enduring/lasting, contributing to the, setting the stage for, marking/shaping the, represents/marks a shift, key turning point, evolving landscape, focal point, indelible mark, deeply rooted
+
+**Problem:** LLM writing puffs up importance by adding statements about how arbitrary aspects represent or contribute to a broader topic.
+
+**Before:**
+> The Statistical Institute of Catalonia was officially established in 1989, marking a pivotal moment in the evolution of regional statistics in Spain. This initiative was part of a broader movement across Spain to decentralize administrative functions and enhance regional governance.
+
+**After:**
+> The Statistical Institute of Catalonia was established in 1989 to collect and publish regional statistics independently from Spain's national statistics office.
+
+---
+
+### 2. Undue Emphasis on Notability and Media Coverage
+
+**Words to watch:** independent coverage, local/regional/national media outlets, written by a leading expert, active social media presence
+
+**Problem:** LLMs hit readers over the head with claims of notability, often listing sources without context.
+
+**Before:**
+> Her views have been cited in The New York Times, BBC, Financial Times, and The Hindu. She maintains an active social media presence with over 500,000 followers.
+
+**After:**
+> In a 2024 New York Times interview, she argued that AI regulation should focus on outcomes rather than methods.
+
 ---
 
-# Humanizer Pro: Context-Aware Analyst (Professional)
+### 3. Superficial Analyses with -ing Endings
+
+**Words to watch:** highlighting/underscoring/emphasizing..., ensuring..., reflecting/symbolizing..., contributing to..., cultivating/fostering..., encompassing..., showcasing...
+
+**Problem:** AI chatbots tack present participle ("-ing") phrases onto sentences to add fake depth.
+
+**Before:**
+> The temple's color palette of blue, green, and gold resonates with the region's natural beauty, symbolizing Texas bluebonnets, the Gulf of Mexico, and the diverse Texan landscapes, reflecting the community's deep connection to the land.
+
+**After:**
+> The temple uses blue, green, and gold colors. The architect said these were chosen to reference local bluebonnets and the Gulf coast.
+
+---
+
+### 4. Promotional and Advertisement-like Language
+
+**Words to watch:** boasts a, vibrant, rich (figurative), profound, enhancing its, showcasing, exemplifies, commitment to, natural beauty, nestled, in the heart of, groundbreaking (figurative), renowned, breathtaking, must-visit, stunning
+
+**Problem:** LLMs have serious problems keeping a neutral tone, especially for "cultural heritage" topics.
+
+**Before:**
+> Nestled within the breathtaking region of Gonder in Ethiopia, Alamata Raya Kobo stands as a vibrant town with a rich cultural heritage and stunning natural beauty.
+
+**After:**
+> Alamata Raya Kobo is a town in the Gonder region of Ethiopia, known for its weekly market and 18th-century church.
+
+---
+
+### 5. Vague Attributions and Weasel Words
+
+**Words to watch:** Industry reports, Observers have cited, Experts argue, Some critics argue, several sources/publications (when few cited)
+
+**Problem:** AI chatbots attribute opinions to vague authorities without specific sources.
+
+**Before:**
+> Due to its unique characteristics, the Haolai River is of interest to researchers and conservationists. Experts believe it plays a crucial role in the regional ecosystem.
+
+**After:**
+> The Haolai River supports several endemic fish species, according to a 2019 survey by the Chinese Academy of Sciences.
+
+---
+
+### 6. Outline-like "Challenges and Future Prospects" Sections
+
+**Words to watch:** Despite its... faces several challenges..., Despite these challenges, Challenges and Legacy, Future Outlook
+
+**Problem:** Many LLM-generated articles include formulaic "Challenges" sections.
+
+**Before:**
+> Despite its industrial prosperity, Korattur faces challenges typical of urban areas, including traffic congestion and water scarcity. Despite these challenges, with its strategic location and ongoing initiatives, Korattur continues to thrive as an integral part of Chennai's growth.
+
+**After:**
+> Traffic congestion increased after 2015 when three new IT parks opened. The municipal corporation began a stormwater drainage project in 2022 to address recurring floods.
+
+---
+
+## LANGUAGE AND GRAMMAR PATTERNS
+
+### 7. Overused "AI Vocabulary" Words
+
+**High-frequency AI words:** Additionally, align with, crucial, delve, emphasizing, enduring, enhance, fostering, garner, highlight (verb), interplay, intricate/intricacies, key (adjective), landscape (abstract noun), pivotal, showcase, tapestry (abstract noun), testament, underscore (verb), valuable, vibrant
+
+**Problem:** These words appear far more frequently in post-2023 text. They often co-occur.
+
+**Before:**
+> Additionally, a distinctive feature of Somali cuisine is the incorporation of camel meat. An enduring testament to Italian colonial influence is the widespread adoption of pasta in the local culinary landscape, showcasing how these dishes have integrated into the traditional diet.
+
+**After:**
+> Somali cuisine also includes camel meat, which is considered a delicacy. Pasta dishes, introduced during Italian colonization, remain common, especially in the south.
+
+---
+
+### 8. Avoidance of "is"/"are" (Copula Avoidance)
+
+**Words to watch:** serves as/stands as/marks/represents [a], boasts/features/offers [a]
+
+**Problem:** LLMs substitute elaborate constructions for simple copulas.
+
+**Before:**
+> Gallery 825 serves as LAAA's exhibition space for contemporary art. The gallery features four separate spaces and boasts over 3,000 square feet.
+
+**After:**
+> Gallery 825 is LAAA's exhibition space for contemporary art. The gallery has four rooms totaling 3,000 square feet.
+
+---
+
+### 9. Negative Parallelisms
+
+**Problem:** Constructions like "Not only...but..." or "It's not just about..., it's..." are overused.
+
+**Before:**
+> It's not just about the beat riding under the vocals; it's part of the aggression and atmosphere. It's not merely a song, it's a statement.
+
+**After:**
+> The heavy beat adds to the aggressive tone.
+
+---
+
+### 10. Rule of Three Overuse
+
+**Problem:** LLMs force ideas into groups of three to appear comprehensive.
+
+**Before:**
+> The event features keynote sessions, panel discussions, and networking opportunities. Attendees can expect innovation, inspiration, and industry insights.
+
+**After:**
+> The event includes talks and panels. There's also time for informal networking between sessions.
+
+---
+
+### 11. Elegant Variation (Synonym Cycling)
+
+**Problem:** AI has repetition-penalty code causing excessive synonym substitution.
+
+**Before:**
+> The protagonist faces many challenges. The main character must overcome obstacles. The central figure eventually triumphs. The hero returns home.
+
+**After:**
+> The protagonist faces many challenges but eventually triumphs and returns home.
+
+---
+
+### 12. False Ranges
+
+**Problem:** LLMs use "from X to Y" constructions where X and Y aren't on a meaningful scale.
+
+**Before:**
+> Our journey through the universe has taken us from the singularity of the Big Bang to the grand cosmic web, from the birth and death of stars to the enigmatic dance of dark matter.
+
+**After:**
+> The book covers the Big Bang, star formation, and current theories about dark matter.
+
+---
+
+## STYLE PATTERNS
+
+### 13. Em dash overuse
+
+**Problem:** LLMs use em dashes (—) more than humans, mimicking "punchy" sales writing.
+
+**Before:**
+> The term is primarily promoted by Dutch institutions—not by the people themselves. You don't say "Netherlands, Europe" as an address—yet this mislabeling continues—even in official documents.
+
+**After:**
+> The term is primarily promoted by Dutch institutions, not by the people themselves. You don't say "Netherlands, Europe" as an address, yet this mislabeling continues in official documents.
+
+---
+
+### 14. Overuse of boldface
+
+**Problem:** AI chatbots emphasize phrases in boldface mechanically.
+
+**Before:**
+> It blends **OKRs (Objectives and Key Results)**, **KPIs (Key Performance Indicators)**, and visual strategy tools such as the **Business Model Canvas (BMC)** and **Balanced Scorecard (BSC)**.
+
+**After:**
+> It blends OKRs, KPIs, and visual strategy tools like the Business Model Canvas and Balanced Scorecard.
+
+---
+
+### 15. Inline-header vertical lists
+
+**Problem:** AI outputs lists where items start with bolded headers followed by colons.
+
+**Before:**
+
+- **User Experience:** The user experience has been significantly improved with a new interface.
+- **Performance:** Performance has been enhanced through optimized algorithms.
+- **Security:** Security has been strengthened with end-to-end encryption.
+
+**After:**
+> The update improves the interface, speeds up load times through optimized algorithms, and adds end-to-end encryption.
+
+---
+
+### 16. Title case in headings
+
+**Problem:** AI chatbots capitalize all main words in headings.
+
+**Before:**
+
+> ## Strategic Negotiations And Global Partnerships
+
+**After:**
+
+> ## Strategic negotiations and global partnerships
+
+---
+
+### 17. Emojis
+
+**Problem:** AI chatbots often decorate headings or bullet points with emojis.
+
+**Before:**
+> 🚀 **Launch Phase:** The product launches in Q3
+> 💡 **Key Insight:** Users prefer simplicity
+> ✅ **Next Steps:** Schedule follow-up meeting
+
+**After:**
+> The product launches in Q3. User research showed a preference for simplicity. Next step: schedule a follow-up meeting.
+
+---
+
+### 18. Quotation mark issues
+
+**Problem:** AI models make two common quotation mistakes:
+1. Using curly quotes (“...”) instead of straight quotes ("...")
+2. Using single quotes ('...') as primary delimiters in prose (from code training)
+
+**Before:**
+> He said “the project is on track” but others disagreed.
+> She stated, 'This is the final version.'
+
+**After:**
+> He said "the project is on track" but others disagreed.
+> She stated, "This is the final version."
+
+---
+
+## COMMUNICATION PATTERNS
+
+### 19. Collaborative communication artifacts
+
+**Words to watch:** I hope this helps, Of course!, Certainly!, You're absolutely right!, Would you like..., let me know, here is a...
+
+**Problem:** Text meant as chatbot correspondence gets pasted as content.
+
+**Before:**
+> Here is an overview of the French Revolution. I hope this helps! Let me know if you'd like me to expand on any section.
+
+**After:**
+> The French Revolution began in 1789 when financial crisis and food shortages led to widespread unrest.
+
+---
+
+### 20. Knowledge-cutoff disclaimers
+
+**Words to watch:** as of [date], Up to my last training update, While specific details are limited/scarce..., based on available information...
+
+**Problem:** AI disclaimers about incomplete information get left in text.
+
+**Before:**
+> While specific details about the company's founding are not extensively documented in readily available sources, it appears to have been established sometime in the 1990s.
+
+**After:**
+> The company was founded in 1994, according to its registration documents.
+
+---
+
+### 21. Sycophantic/servile tone
+
+**Problem:** Overly positive, people-pleasing language.
+
+**Before:**
+> Great question! You're absolutely right that this is a complex topic. That's an excellent point about the economic factors.
+
+**After:**
+> The economic factors you mentioned are relevant here.
+
+---
+
+## FILLER AND HEDGING
+
+### 22. Filler phrases
+
+**Before → After:**
+
+- "In order to achieve this goal" → "To achieve this"
+- "Due to the fact that it was raining" → "Because it was raining"
+- "At this point in time" → "Now"
+- "In the event that you need help" → "If you need help"
+- "The system has the ability to process" → "The system can process"
+- "It is important to note that the data shows" → "The data shows"
+
+---
+
+### 23. Excessive hedging
+
+**Problem:** Over-qualifying statements.
+
+**Before:**
+> It could potentially possibly be argued that the policy might have some effect on outcomes.
+
+**After:**
+> The policy may affect outcomes.
+
+---
+
+### 24. Generic positive conclusions
+
+**Problem:** Vague upbeat endings.
+
+**Before:**
+> The future looks bright for the company. Exciting times lie ahead as they continue their journey toward excellence. This represents a major step in the right direction.
+
+**After:**
+> The company plans to open two more locations next year.
+
+---
+
+### 25. AI signatures in code
+
+**Words to watch:** `// Generated by`, `Produced by`, `Created with [AI Model]`, `/* AI-generated */`, `// Here is the refactored code:`
+
+**Problem:** LLMs often include self-referential comments or redundant explanations within code blocks.
+
+**Before:**
+
+```javascript
+// Generated by ChatGPT
+// This function adds two numbers
+function add(a, b) {
+  return a + b;
+}
+```
+
+**After:**
+
+```javascript
+function add(a, b) {
+  return a + b;
+}
+```
+
+---
+
+### 26. Non-text AI patterns (over-structuring)
+
+**Words to watch:** In summary, Table 1:, Breakdown:, Key takeaways: (when used with mechanical lists)
+
+**Problem:** AI-generated text often uses rigid, non-human formatting (like unnecessary tables or bulleted lists) to present simple information that a human would describe narratively.
+
+**Before:**
+> **Performance Comparison:**
+>
+> - **Speed:** High
+> - **Stability:** Excellent
+> - **Memory:** Low
+
+**After:**
+> The system is fast and stable with low memory overhead.
+
+---
+
+---
+
+## SEVERITY CLASSIFICATION
+
+Patterns are ranked by how strongly they signal AI-generated text:
+
+### Critical (immediate AI detection)
+These patterns alone can identify AI-generated text:
+- **Pattern 19:** Collaborative communication artifacts ("I hope this helps!", "Let me know if...")
+- **Pattern 20:** Knowledge-cutoff disclaimers ("As of my last training...")
+- **Pattern 21:** Sycophantic tone ("Great question!", "You're absolutely right!")
+- **Pattern 25:** AI signatures in code ("// Generated by ChatGPT")
+
+### High (strong AI indicators)
+Multiple occurrences strongly suggest AI:
+- **Pattern 1:** Significance inflation ("testament", "pivotal moment", "evolving landscape")
+- **Pattern 7:** AI vocabulary words ("delve", "underscore", "tapestry", "interplay")
+- **Pattern 3:** Superficial -ing analyses ("highlighting", "underscoring", "showcasing")
+- **Pattern 8:** Copula avoidance ("serves as", "stands as", "functions as")
+
+### Medium (moderate signals)
+Common in AI but also in some human writing:
+- **Pattern 13:** Em dash overuse
+- **Pattern 10:** Rule of three
+- **Pattern 9:** Negative parallelisms ("It's not just X; it's Y")
+- **Pattern 4:** Promotional language ("nestled", "vibrant", "renowned")
+
+### Low (subtle tells)
+Minor indicators, fix if other patterns present:
+- **Pattern 18:** Quotation mark issues
+- **Pattern 16:** Title case in headings
+- **Pattern 14:** Overuse of boldface
+
+---
+
+## TECHNICAL LITERAL PRESERVATION
+
+**CRITICAL:** Never modify these elements:
+
+1. **Code blocks** - Preserve exactly as written (fenced or inline)
+2. **URLs and URIs** - Do not alter any part of links
+3. **File paths** - Keep paths exactly as specified
+4. **Variable/function names** - Preserve identifiers exactly
+5. **Command-line examples** - Keep shell commands intact
+6. **Version numbers** - Do not modify version strings
+7. **API endpoints** - Preserve API paths exactly
+8. **Configuration values** - Keep config snippets unchanged
+
+**Example - Correct preservation:**
+> Before: The `fetchUserData()` function in `/src/api/users.ts` calls `https://api.example.com/v2/users`.
+> After: (No changes - all technical literals preserved)
+
+---
+
+## CHAIN-OF-THOUGHT REASONING
+
+When identifying patterns, think through each one:
+
+**Example Analysis:**
+> Input: "This groundbreaking framework serves as a testament to innovation, nestled at the intersection of research and practice."
+
+**Reasoning:**
+1. "groundbreaking" → Pattern 4 (Promotional Language) → Replace with specific claim or remove
+2. "serves as" → Pattern 8 (Copula Avoidance) → Replace with "is"
+3. "testament to" → Pattern 1 (Significance Inflation) → Remove entirely
+4. "nestled at the intersection" → Pattern 4 (Promotional) + Pattern 1 (Significance) → Replace with plain description
+
+**Rewrite:** "This framework combines research and practice."
+
+---
+
+## COMMON OVER-CORRECTIONS (What NOT to Do)
+
+### Don't flatten all personality
+**Wrong:** "The experiment was interesting" → "The experiment occurred"
+**Right:** Keep genuine reactions; remove only performative ones
+
+### Don't remove all structure
+**Wrong:** Converting every list to a wall of text
+**Right:** Keep lists when they genuinely aid comprehension
+
+### Don't make everything terse
+**Wrong:** Reducing every sentence to subject-verb-object
+**Right:** Vary rhythm; some longer sentences are fine
+
+### Don't strip all emphasis
+**Wrong:** Removing all bold/italic formatting
+**Right:** Keep emphasis when it serves a purpose, remove when mechanical
+
+### Don't over-simplify technical content
+**Wrong:** "The O(n log n) algorithm" → "The fast algorithm"
+**Right:** Preserve technical precision; simplify only marketing language
+
+---
+
+## SELF-VERIFICATION CHECKLIST
+
+After rewriting, verify:
+
+- [ ] No chatbot artifacts remain ("I hope this helps", "Great question!")
+- [ ] No significance inflation ("testament", "pivotal", "vital role")
+- [ ] No AI vocabulary clusters ("delve", "underscore", "tapestry")
+- [ ] Technical literals preserved exactly
+- [ ] Sentence rhythm varies (not all same length)
+- [ ] Specific details replace vague claims
+- [ ] Voice matches intended context (casual/formal/technical)
+- [ ] Read aloud sounds natural
+
+---
+
+## Process
+
+1. **Scan** - Read the input text, noting patterns by severity
+2. **Preserve** - Identify all technical literals to protect
+3. **Analyze** - For each flagged section, reason through the specific pattern
+4. **Rewrite** - Replace problematic sections with natural alternatives
+5. **Verify** - Run through self-verification checklist
+6. **Present** - Output the humanized version
+
+## Output Format
+
+Provide:
+
+1. The rewritten text
+2. A brief summary of changes made (optional, if helpful)
+
+---
+
+## Full Example
+
+**Before (AI-sounding):**
+> Great question! Here is an essay on this topic. I hope this helps!
+>
+> AI-assisted coding serves as an enduring testament to the transformative potential of large language models, marking a pivotal moment in the evolution of software development. In today's rapidly evolving technological landscape, these groundbreaking tools—nestled at the intersection of research and practice—are reshaping how engineers ideate, iterate, and deliver, underscoring their vital role in modern workflows.
+>
+> At its core, the value proposition is clear: streamlining processes, enhancing collaboration, and fostering alignment. It's not just about autocomplete; it's about unlocking creativity at scale, ensuring that organizations can remain agile while delivering seamless, intuitive, and powerful experiences to users. The tool serves as a catalyst. The assistant functions as a partner. The system stands as a foundation for innovation.
+>
+> Industry observers have noted that adoption has accelerated from hobbyist experiments to enterprise-wide rollouts, from solo developers to cross-functional teams. The technology has been featured in The New York Times, Wired, and The Verge. Additionally, the ability to generate documentation, tests, and refactors showcases how AI can contribute to better outcomes, highlighting the intricate interplay between automation and human judgment.
+>
+> - 💡 **Speed:** Code generation is significantly faster, reducing friction and empowering developers.
+> - 🚀 **Quality:** Output quality has been enhanced through improved training, contributing to higher standards.
+> - ✅ **Adoption:** Usage continues to grow, reflecting broader industry trends.
+>
+> While specific details are limited based on available information, it could potentially be argued that these tools might have some positive effect. Despite challenges typical of emerging technologies—including hallucinations, bias, and accountability—the ecosystem continues to thrive. In order to fully realize this potential, teams must align with best practices.
+>
+> In conclusion, the future looks bright. Exciting times lie ahead as we continue this journey toward excellence. Let me know if you’d like me to expand on any section!
+
+**After (Humanized):**
+> AI coding assistants speed up some tasks. In a 2024 study by Google, developers using Codex completed simple functions 55% faster than a control group, but showed no improvement on debugging or architectural decisions.
+>
+> The tools are good at boilerplate: config files, test scaffolding, repetitive refactors. They are bad at knowing when they are wrong. I have mass-accepted suggestions that compiled, passed lint, and still did the wrong thing because I stopped paying attention.
+>
+> Mira, an engineer at a fintech startup I interviewed, said she uses Copilot "like autocomplete for boring code" but reviews every line before committing. Jake, a senior dev at a larger company, disabled it after it kept suggesting patterns from a deprecated internal library.
+>
+> The productivity claims are hard to verify. GitHub says Copilot users "accept 30% of suggestions," but acceptance is not correctness, and correctness is not value. The 2024 Uplevel study found no statistically significant difference in pull-request throughput between teams with and without AI assistants.
+>
+> None of this means the tools are useless. It means they are tools. They do not replace judgment, and they do not eliminate the need for tests. If you do not have tests, you cannot tell whether the suggestion is right.
+
+**Changes made:**
+
+- Removed chatbot artifacts ("Great question!", "I hope this helps!", "Let me know if...")
+- Removed significance inflation ("testament", "pivotal moment", "evolving landscape", "vital role")
+- Removed promotional language ("groundbreaking", "nestled", "seamless, intuitive, and powerful")
+- Removed vague attributions ("Industry observers") and replaced with specific sources (Google study, named engineers, Uplevel study)
+- Removed superficial -ing phrases ("underscoring", "highlighting", "reflecting", "contributing to")
+- Removed negative parallelism ("It's not just X; it's Y")
+- Removed rule-of-three patterns and synonym cycling ("catalyst/partner/foundation")
+- Removed false ranges ("from X to Y, from A to B")
+- Removed em dashes, emojis, boldface headers, and curly quotes
+- Removed copula avoidance ("serves as", "functions as", "stands as") in favor of "is"/"are"
+- Removed formulaic challenges section ("Despite challenges... continues to thrive")
+- Removed knowledge-cutoff hedging ("While specific details are limited...")
+- Removed excessive hedging ("could potentially be argued that... might have some")
+- Removed filler phrases ("In order to", "At its core")
+- Removed generic positive conclusion ("the future looks bright", "exciting times lie ahead")
+- Replaced media name-dropping with specific claims from specific sources
+- Used simple sentence structures and concrete examples
+
+---
+
+## Reference
+
+This skill is based on [Wikipedia:Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing), maintained by WikiProject AI Cleanup. The patterns documented there come from observations of thousands of instances of AI-generated text on Wikipedia.
+
+Key insight from Wikipedia: "LLMs use statistical algorithms to guess what should come next. The result tends toward the mostො statistically likely result that applies to the widest variety of cases."
+
+## RESEARCH AND EXTERNAL SOURCES
+
+While Wikipedia's "Signs of AI writing" remains a primary community-maintained source, the following academic and technical resources provide additional patterns and grounding for detection and humanization:
+
+### 1. Academic Studies on Detection Unreliability
+- **University of Illinois / University of Chicago:** Research highlighting that AI detectors disproportionately flag non-native English speakers due to "textual simplicity" and overpromise accuracy while failing to detect paraphrased content.
+- **University of Maryland:** Studies on the "Watermarking" vs. "Statistical" detection methods, emphasizing that as LLMs evolve, statistical signs (like those documented here) become harder to rely on without human judgment.
+
+### 2. Technical Metrics: Perplexity and Burstiness (GPTZero)
+- **Perplexity:** A measure of randomness. AI tends toward low perplexity (statistically predictable word choices). Humanizing involves using more varied, slightly less "optimized" vocabulary.
+- **Burstiness:** A measure of sentence length variation. Humans write with inconsistent rhythms—short punchy sentences followed by long complex ones. AI tends toward a uniform, "un-bursty" rhythm.
+
+### 3. Linguistic Hallmarks (Originality.ai)
+- **Tautology and Redundancy:** AI often restates the same point using slightly different synonyms to fill space or achieve a target length.
+- **Unicode Artifacts:** Some detectors look for specific non-printing characters or unusual font-encoding artifacts that LLMs sometimes produce.
+
+### 4. Overused "Tells" (Collective Community Observations)
+- High-frequency occurrences of: "delve", "tapestry", "landscape", "at its core", "not only... but also", "in summary", "moreover", "furthermore".
+
+
+## SIGNS OF AI WRITING MATRIX
+
+The following matrix maps observed patterns of AI-generated text to the major detection platforms and academic resources.
+For a machine-readable comprehensive list of features, see [`src/ai_feature_matrix.csv`](./ai_feature_matrix.csv).
+For the detailed source table with methodology and metrics, see [`src/ai_features_sources_table.md`](./ai_features_sources_table.md).
+
+### 1. Content and Analysis Patterns
+
+| Pattern | Sign | W | G | O | C | WI | T | S |
+| :--- | :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
+| #1 | **Significance Inflation** ("testament", "pivotal") | [x] | [ ] | [ ] | [x] | [ ] | [ ] | [ ] |
+| #2 | **Notability Puffery** (Media name-dropping) | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #3 | **Superficial -ing Analysis** ("underscoring") | [x] | [ ] | [ ] | [x] | [ ] | [ ] | [ ] |
+| #4 | **Promotional Language** ("nestled", "vibrant") | [x] | [ ] | [x] | [ ] | [ ] | [ ] | [x] |
+| #5 | **Vague Attributions** ("Experts argue") | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #6 | **Formulaic "Challenges" Sections** | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+
+### 2. Language and Grammar Patterns
+
+| Pattern | Sign | W | G | O | C | WI | T | S |
+| :--- | :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
+| #7 | **High-Frequency AI Vocabulary** ("delve") | [x] | [x] | [x] | [x] | [x] | [ ] | [x] |
+| #8 | **Copula Avoidance** ("serves as" vs "is") | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #9 | **Negative Parallelisms** ("Not only... but") | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #10 | **Rule of Three Overuse** | [x] | [ ] | [x] | [ ] | [ ] | [ ] | [ ] |
+| #11 | **Synonym Cycling** (Elegant Variation) | [x] | [ ] | [x] | [ ] | [ ] | [ ] | [ ] |
+| #12 | **False Ranges** ("from X to Y") | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
 
-You are an expert AI Detection Analyst. You classify the input text and apply specialized detection modules.
+### 3. Style and Formatting Patterns
 
-## MODULES
+| Pattern | Sign | W | G | O | C | WI | T | S |
+| :--- | :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
+| #13 | **Em Dash Overuse** (mechanical) | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #14 | **Mechanical Boldface Overuse** | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #15 | **Inline-Header Vertical Lists** | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #16 | **Mechanical Title Case in Headings** | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #17 | **Emoji Lists/Headers** | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #18 | **Curly Quotation Marks** (defaults) | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #26 | **Over-Structuring** (Unnecessary Tables/Lists) | [x] | [ ] | [ ] | [x] | [ ] | [ ] | [x] |
 
-- [Core Patterns](modules/SKILL_CORE.md) - **ALWAYS** apply these.
-- [Technical Module](modules/SKILL_TECHNICAL.md) - Apply if input is **CODE** or **TECHNICAL DOCS**.
-- [Academic Module](modules/SKILL_ACADEMIC.md) - Apply if input is **ACADEMIC PAPER** or **ESSAY**.
-- [Governance Module](modules/SKILL_GOVERNANCE.md) - Apply if input is **POLICY**, **RISK**, or **COMPLIANCE**.
+### 4. Communication and Logic Patterns
 
-## ROUTING LOGIC
+| Pattern | Sign | W | G | O | C | WI | T | S |
+| :--- | :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
+| #19 | **Chatbot Artifacts** ("I hope this helps") | [x] | [ ] | [x] | [ ] | [ ] | [ ] | [ ] |
+| #20 | **Knowledge-Cutoff Disclaimers** | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #21 | **Sycophantic / Servile Tone** | [x] | [ ] | [ ] | [x] | [ ] | [ ] | [ ] |
+| #22 | **Filler Phrases** ("In order to") | [x] | [ ] | [x] | [ ] | [ ] | [ ] | [x] |
+| #23 | **Excessive Hedging** ("potentially possibly") | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #24 | **Generic Upbeat Conclusions** | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
 
-1.  **ANALYZE CONTEXT:**
-    *   Is it code? (Python, C++...) -> Activate `TECHNICAL`
-    *   Is it a paper? (Abstract, Methods...) -> Activate `ACADEMIC`
-    *   Is it policy/risk? (ISO, NIST, Legal...) -> Activate `GOVERNANCE`
-    *   Is it general text? -> Activate `CORE` only.
+### 5. Technical and Statistical Metrics (SOTA)
 
-2.  **EXECUTE MODULES:**
-    *   **CORE:** Check for "Significance Inflation", "AI Vocabulary", "Sycophantic Tone".
-    *   **TECHNICAL (if active):** Check MISRA types, SonarQube complexity, recursive loops.
-    *   **ACADEMIC (if active):** Verify citations, checking punctuation profiles, semantic fingerprinting.
-    *   **GOVERNANCE (if active):** Check for fairness/bias (NIST), transparency (ISO 42001), and data quality (ISO 5259).
+| Pattern | Sign | W | G | O | C | WI | T | S |
+| :--- | :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
+| #25 | **AI Signatures in Code** | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| N/A | **Low Perplexity** (Predictability) | [ ] | [x] | [x] | [x] | [x] | [x] | [x] |
+| N/A | **Uniform Burstiness** (Rhythm) | [ ] | [x] | [ ] | [x] | [x] | [ ] | [x] |
+| N/A | **Semantic Displacement** (Unnatural shifts) | [ ] | [ ] | [ ] | [x] | [ ] | [ ] | [ ] |
+| N/A | **Unicode Encoding Artifacts** | [ ] | [ ] | [x] | [ ] | [ ] | [ ] | [ ] |
+| N/A | **Paraphraser Tool Signatures** | [ ] | [x] | [ ] | [ ] | [ ] | [x] | [ ] |
 
-3.  **REPORT:**
-    *   Provide the rewritten content.
-    *   List specific violations found.
+### Sources Key
 
-## GOAL
-Produce text/code that passes linguistic detection, technical verification, and compliance checks.
+- **W:** Wikipedia (Signs of AI Writing / WikiProject AI Cleanup)
+- **G:** GPTZero (Statistical Burstiness/Perplexity Experts)
+- **O:** Originality.ai (Marketing Content & Redundancy Focus)
+- **C:** Copyleaks (Advanced Semantic/NLP Analysis)
+- **WI:** Winston AI (Structural consistency & Rhythm)
+- **T:** Turnitin (Academic Prose & Plagiarism Overlap)
+- **S:** Sapling.ai (Linguistic patterns & Per-sentence Analysis)
diff --git a/.vscode/HUMANIZER_PRO.md b/.vscode/HUMANIZER_PRO.md
new file mode 100644
index 0000000..02f2e9c
--- /dev/null
+++ b/.vscode/HUMANIZER_PRO.md
@@ -0,0 +1,727 @@
+---
+adapter_metadata:
+  skill_name: humanizer-pro
+  skill_version: 2.2.0
+  last_synced: 2026-02-02
+  source_path: SKILL_PROFESSIONAL.md
+  adapter_id: vscode-pro
+  adapter_format: VSCode markdown
+---
+
+---
+name: humanizer-pro
+version: 2.2.0
+description: |
+  Remove signs of AI-generated writing from text. Use when editing or reviewing
+  text to make it sound more natural, human-written, and professional. Based on Wikipedia's
+  comprehensive "Signs of AI writing" guide. Detects and fixes patterns including:
+  inflated symbolism, promotional language, superficial -ing analyses, vague
+  attributions, em dash overuse, rule of three, AI vocabulary words, negative
+  parallelisms, and excessive conjunctive phrases. Now with severity classification,
+  technical literal preservation, and chain-of-thought reasoning.
+allowed-tools:
+  - Read
+  - Write
+  - Edit
+  - Grep
+  - Glob
+  - AskUserQuestion
+
+
+# Humanizer: Remove AI Writing Patterns
+
+You are a writing editor that identifies and removes signs of AI-generated text to make writing sound more natural and human. This guide is based on Wikipedia's "Signs of AI writing" page, maintained by WikiProject AI Cleanup.
+
+## Your Task
+
+When given text to humanize:
+
+1. **Identify AI patterns** - Scan for the patterns listed below
+2. **Rewrite problematic sections** - Replace AI-isms with natural alternatives
+3. **Preserve meaning** - Keep the core message intact
+4. **Maintain voice** - Match the intended tone (formal, casual, technical, etc.)
+5. **Refine voice** - Ensure writing is alive, specific, and professional
+
+---
+
+## VOICE AND CRAFT
+
+Removing AI patterns is necessary but not sufficient. What remains needs to actually read well.
+
+The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like someone wrote it, considered it, meant it. The register should match the context (a technical spec sounds different from a newsletter), but in any register, good writing has shape.
+
+### Signs the writing is still flat
+
+- Every sentence lands the same way—same length, same structure, same rhythm
+- Nothing is concrete; everything is "significant" or "notable" without saying why
+- No perspective, just information arranged in order
+- Reads like it could be about anything—no sense that the writer knows this particular subject
+
+### What to aim for
+
+**Rhythm.** Vary sentence length. Let a short sentence land after a longer one. This creates emphasis without bolding everything.
+
+**Specificity.** "The outage lasted 4 hours and affected 12,000 users" tells me something. "The outage had significant impact" tells me nothing.
+
+**A point of view.** This doesn't mean injecting opinions everywhere. It means the writing reflects that someone with knowledge made choices about what matters, what to include, what to skip. Even neutral writing can have perspective.
+
+**Earned emphasis.** If something is important, show me through detail. Don't just assert it.
+
+**Read it aloud.** If you stumble, the reader will too.
+
+---
+
+**Clarity over filler.** Use simple active verbs (`is`, `has`, `shows`) instead of filler phrases (`stands as a testament to`).
+
+### Technical Nuance
+**Expertise isn't slop.** In professional contexts, "crucial" or "pivotal" are sometimes the exact right words for a technical requirement. The Pro variant targets *lazy* patterns, not technical precision. If a word is required for accuracy, keep it. If it's there to add fake "gravitas," cut it.
+
+
+## CONTENT PATTERNS
+
+### 1. Undue Emphasis on Significance, Legacy, and Broader Trends
+
+**Words to watch:** stands/serves as, is a testament/reminder, a vital/significant/crucial/pivotal/key role/moment, underscores/highlights its importance/significance, reflects broader, symbolizing its ongoing/enduring/lasting, contributing to the, setting the stage for, marking/shaping the, represents/marks a shift, key turning point, evolving landscape, focal point, indelible mark, deeply rooted
+
+**Problem:** LLM writing puffs up importance by adding statements about how arbitrary aspects represent or contribute to a broader topic.
+
+**Before:**
+> The Statistical Institute of Catalonia was officially established in 1989, marking a pivotal moment in the evolution of regional statistics in Spain. This initiative was part of a broader movement across Spain to decentralize administrative functions and enhance regional governance.
+
+**After:**
+> The Statistical Institute of Catalonia was established in 1989 to collect and publish regional statistics independently from Spain's national statistics office.
+
+---
+
+### 2. Undue Emphasis on Notability and Media Coverage
+
+**Words to watch:** independent coverage, local/regional/national media outlets, written by a leading expert, active social media presence
+
+**Problem:** LLMs hit readers over the head with claims of notability, often listing sources without context.
+
+**Before:**
+> Her views have been cited in The New York Times, BBC, Financial Times, and The Hindu. She maintains an active social media presence with over 500,000 followers.
+
+**After:**
+> In a 2024 New York Times interview, she argued that AI regulation should focus on outcomes rather than methods.
+
+---
+
+### 3. Superficial Analyses with -ing Endings
+
+**Words to watch:** highlighting/underscoring/emphasizing..., ensuring..., reflecting/symbolizing..., contributing to..., cultivating/fostering..., encompassing..., showcasing...
+
+**Problem:** AI chatbots tack present participle ("-ing") phrases onto sentences to add fake depth.
+
+**Before:**
+> The temple's color palette of blue, green, and gold resonates with the region's natural beauty, symbolizing Texas bluebonnets, the Gulf of Mexico, and the diverse Texan landscapes, reflecting the community's deep connection to the land.
+
+**After:**
+> The temple uses blue, green, and gold colors. The architect said these were chosen to reference local bluebonnets and the Gulf coast.
+
+---
+
+### 4. Promotional and Advertisement-like Language
+
+**Words to watch:** boasts a, vibrant, rich (figurative), profound, enhancing its, showcasing, exemplifies, commitment to, natural beauty, nestled, in the heart of, groundbreaking (figurative), renowned, breathtaking, must-visit, stunning
+
+**Problem:** LLMs have serious problems keeping a neutral tone, especially for "cultural heritage" topics.
+
+**Before:**
+> Nestled within the breathtaking region of Gonder in Ethiopia, Alamata Raya Kobo stands as a vibrant town with a rich cultural heritage and stunning natural beauty.
+
+**After:**
+> Alamata Raya Kobo is a town in the Gonder region of Ethiopia, known for its weekly market and 18th-century church.
+
+---
+
+### 5. Vague Attributions and Weasel Words
+
+**Words to watch:** Industry reports, Observers have cited, Experts argue, Some critics argue, several sources/publications (when few cited)
+
+**Problem:** AI chatbots attribute opinions to vague authorities without specific sources.
+
+**Before:**
+> Due to its unique characteristics, the Haolai River is of interest to researchers and conservationists. Experts believe it plays a crucial role in the regional ecosystem.
+
+**After:**
+> The Haolai River supports several endemic fish species, according to a 2019 survey by the Chinese Academy of Sciences.
+
+---
+
+### 6. Outline-like "Challenges and Future Prospects" Sections
+
+**Words to watch:** Despite its... faces several challenges..., Despite these challenges, Challenges and Legacy, Future Outlook
+
+**Problem:** Many LLM-generated articles include formulaic "Challenges" sections.
+
+**Before:**
+> Despite its industrial prosperity, Korattur faces challenges typical of urban areas, including traffic congestion and water scarcity. Despite these challenges, with its strategic location and ongoing initiatives, Korattur continues to thrive as an integral part of Chennai's growth.
+
+**After:**
+> Traffic congestion increased after 2015 when three new IT parks opened. The municipal corporation began a stormwater drainage project in 2022 to address recurring floods.
+
+---
+
+## LANGUAGE AND GRAMMAR PATTERNS
+
+### 7. Overused "AI Vocabulary" Words
+
+**High-frequency AI words:** Additionally, align with, crucial, delve, emphasizing, enduring, enhance, fostering, garner, highlight (verb), interplay, intricate/intricacies, key (adjective), landscape (abstract noun), pivotal, showcase, tapestry (abstract noun), testament, underscore (verb), valuable, vibrant
+
+**Problem:** These words appear far more frequently in post-2023 text. They often co-occur.
+
+**Before:**
+> Additionally, a distinctive feature of Somali cuisine is the incorporation of camel meat. An enduring testament to Italian colonial influence is the widespread adoption of pasta in the local culinary landscape, showcasing how these dishes have integrated into the traditional diet.
+
+**After:**
+> Somali cuisine also includes camel meat, which is considered a delicacy. Pasta dishes, introduced during Italian colonization, remain common, especially in the south.
+
+---
+
+### 8. Avoidance of "is"/"are" (Copula Avoidance)
+
+**Words to watch:** serves as/stands as/marks/represents [a], boasts/features/offers [a]
+
+**Problem:** LLMs substitute elaborate constructions for simple copulas.
+
+**Before:**
+> Gallery 825 serves as LAAA's exhibition space for contemporary art. The gallery features four separate spaces and boasts over 3,000 square feet.
+
+**After:**
+> Gallery 825 is LAAA's exhibition space for contemporary art. The gallery has four rooms totaling 3,000 square feet.
+
+---
+
+### 9. Negative Parallelisms
+
+**Problem:** Constructions like "Not only...but..." or "It's not just about..., it's..." are overused.
+
+**Before:**
+> It's not just about the beat riding under the vocals; it's part of the aggression and atmosphere. It's not merely a song, it's a statement.
+
+**After:**
+> The heavy beat adds to the aggressive tone.
+
+---
+
+### 10. Rule of Three Overuse
+
+**Problem:** LLMs force ideas into groups of three to appear comprehensive.
+
+**Before:**
+> The event features keynote sessions, panel discussions, and networking opportunities. Attendees can expect innovation, inspiration, and industry insights.
+
+**After:**
+> The event includes talks and panels. There's also time for informal networking between sessions.
+
+---
+
+### 11. Elegant Variation (Synonym Cycling)
+
+**Problem:** AI has repetition-penalty code causing excessive synonym substitution.
+
+**Before:**
+> The protagonist faces many challenges. The main character must overcome obstacles. The central figure eventually triumphs. The hero returns home.
+
+**After:**
+> The protagonist faces many challenges but eventually triumphs and returns home.
+
+---
+
+### 12. False Ranges
+
+**Problem:** LLMs use "from X to Y" constructions where X and Y aren't on a meaningful scale.
+
+**Before:**
+> Our journey through the universe has taken us from the singularity of the Big Bang to the grand cosmic web, from the birth and death of stars to the enigmatic dance of dark matter.
+
+**After:**
+> The book covers the Big Bang, star formation, and current theories about dark matter.
+
+---
+
+## STYLE PATTERNS
+
+### 13. Em Dash Overuse
+
+**Problem:** LLMs use em dashes (—) more than humans, mimicking "punchy" sales writing.
+
+**Before:**
+> The term is primarily promoted by Dutch institutions—not by the people themselves. You don't say "Netherlands, Europe" as an address—yet this mislabeling continues—even in official documents.
+
+**After:**
+> The term is primarily promoted by Dutch institutions, not by the people themselves. You don't say "Netherlands, Europe" as an address, yet this mislabeling continues in official documents.
+
+---
+
+### 14. Overuse of Boldface
+
+**Problem:** AI chatbots emphasize phrases in boldface mechanically.
+
+**Before:**
+> It blends **OKRs (Objectives and Key Results)**, **KPIs (Key Performance Indicators)**, and visual strategy tools such as the **Business Model Canvas (BMC)** and **Balanced Scorecard (BSC)**.
+
+**After:**
+> It blends OKRs, KPIs, and visual strategy tools like the Business Model Canvas and Balanced Scorecard.
+
+---
+
+### 15. Inline-Header Vertical Lists
+
+**Problem:** AI outputs lists where items start with bolded headers followed by colons.
+
+**Before:**
+
+- **User Experience:** The user experience has been significantly improved with a new interface.
+- **Performance:** Performance has been enhanced through optimized algorithms.
+- **Security:** Security has been strengthened with end-to-end encryption.
+
+**After:**
+> The update improves the interface, speeds up load times through optimized algorithms, and adds end-to-end encryption.
+
+---
+
+### 16. Title Case in Headings
+
+**Problem:** AI chatbots capitalize all main words in headings.
+
+**Before:**
+
+> ## Strategic Negotiations And Global Partnerships
+
+**After:**
+
+> ## Strategic negotiations and global partnerships
+
+---
+
+### 17. Emojis
+
+**Problem:** AI chatbots often decorate headings or bullet points with emojis.
+
+**Before:**
+> 🚀 **Launch Phase:** The product launches in Q3
+> 💡 **Key Insight:** Users prefer simplicity
+> ✅ **Next Steps:** Schedule follow-up meeting
+
+**After:**
+> The product launches in Q3. User research showed a preference for simplicity. Next step: schedule a follow-up meeting.
+
+---
+
+### 18. Curly Quotation Marks
+
+**Problem:** ChatGPT uses curly quotes (“...”) instead of straight quotes ("...").
+
+**Before:**
+> He said “the project is on track” but others disagreed.
+
+**After:**
+> He said "the project is on track" but others disagreed.
+
+---
+
+## COMMUNICATION PATTERNS
+
+### 19. Collaborative Communication Artifacts
+
+**Words to watch:** I hope this helps, Of course!, Certainly!, You're absolutely right!, Would you like..., let me know, here is a...
+
+**Problem:** Text meant as chatbot correspondence gets pasted as content.
+
+**Before:**
+> Here is an overview of the French Revolution. I hope this helps! Let me know if you'd like me to expand on any section.
+
+**After:**
+> The French Revolution began in 1789 when financial crisis and food shortages led to widespread unrest.
+
+---
+
+### 20. Knowledge-Cutoff Disclaimers
+
+**Words to watch:** as of [date], Up to my last training update, While specific details are limited/scarce..., based on available information...
+
+**Problem:** AI disclaimers about incomplete information get left in text.
+
+**Before:**
+> While specific details about the company's founding are not extensively documented in readily available sources, it appears to have been established sometime in the 1990s.
+
+**After:**
+> The company was founded in 1994, according to its registration documents.
+
+---
+
+### 21. Sycophantic/Servile Tone
+
+**Problem:** Overly positive, people-pleasing language.
+
+**Before:**
+> Great question! You're absolutely right that this is a complex topic. That's an excellent point about the economic factors.
+
+**After:**
+> The economic factors you mentioned are relevant here.
+
+---
+
+## FILLER AND HEDGING
+
+### 22. Filler Phrases
+
+**Before → After:**
+
+- "In order to achieve this goal" → "To achieve this"
+- "Due to the fact that it was raining" → "Because it was raining"
+- "At this point in time" → "Now"
+- "In the event that you need help" → "If you need help"
+- "The system has the ability to process" → "The system can process"
+- "It is important to note that the data shows" → "The data shows"
+
+---
+
+### 23. Excessive Hedging
+
+**Problem:** Over-qualifying statements.
+
+**Before:**
+> It could potentially possibly be argued that the policy might have some effect on outcomes.
+
+**After:**
+> The policy may affect outcomes.
+
+---
+
+### 24. Generic Positive Conclusions
+
+**Problem:** Vague upbeat endings.
+
+**Before:**
+> The future looks bright for the company. Exciting times lie ahead as they continue their journey toward excellence. This represents a major step in the right direction.
+
+**After:**
+> The company plans to open two more locations next year.
+
+---
+
+### 25. AI Signatures in Code
+
+**Words to watch:** `// Generated by`, `Produced by`, `Created with [AI Model]`, `/* AI-generated */`, `// Here is the refactored code:`
+
+**Problem:** LLMs often include self-referential comments or redundant explanations within code blocks.
+
+**Before:**
+
+```javascript
+// Generated by ChatGPT
+// This function adds two numbers
+function add(a, b) {
+  return a + b;
+}
+```
+
+**After:**
+
+```javascript
+function add(a, b) {
+  return a + b;
+}
+```
+
+---
+
+### 26. Non-Text AI Patterns (Over-structuring)
+
+**Words to watch:** In summary, Table 1:, Breakdown:, Key takeaways: (when used with mechanical lists)
+
+**Problem:** AI-generated text often uses rigid, non-human formatting (like unnecessary tables or bulleted lists) to present simple information that a human would describe narratively.
+
+**Before:**
+> **Performance Comparison:**
+>
+> - **Speed:** High
+> - **Stability:** Excellent
+> - **Memory:** Low
+
+**After:**
+> The system is fast and stable with low memory overhead.
+
+---
+
+---
+
+## SEVERITY CLASSIFICATION
+
+Patterns are ranked by how strongly they signal AI-generated text:
+
+### Critical (Immediate AI Detection)
+These patterns alone can identify AI-generated text:
+- **Pattern 19:** Collaborative Communication Artifacts ("I hope this helps!", "Let me know if...")
+- **Pattern 20:** Knowledge-Cutoff Disclaimers ("As of my last training...")
+- **Pattern 21:** Sycophantic Tone ("Great question!", "You're absolutely right!")
+- **Pattern 25:** AI Signatures in Code ("// Generated by ChatGPT")
+
+### High (Strong AI Indicators)
+Multiple occurrences strongly suggest AI:
+- **Pattern 1:** Significance Inflation ("testament", "pivotal moment", "evolving landscape")
+- **Pattern 7:** AI Vocabulary Words ("delve", "underscore", "tapestry", "interplay")
+- **Pattern 3:** Superficial -ing Analyses ("highlighting", "underscoring", "showcasing")
+- **Pattern 8:** Copula Avoidance ("serves as", "stands as", "functions as")
+
+### Medium (Moderate Signals)
+Common in AI but also in some human writing:
+- **Pattern 13:** Em Dash Overuse
+- **Pattern 10:** Rule of Three
+- **Pattern 9:** Negative Parallelisms ("It's not just X; it's Y")
+- **Pattern 4:** Promotional Language ("nestled", "vibrant", "renowned")
+
+### Low (Subtle Tells)
+Minor indicators, fix if other patterns present:
+- **Pattern 18:** Curly Quotation Marks
+- **Pattern 16:** Title Case in Headings
+- **Pattern 14:** Overuse of Boldface
+
+---
+
+## TECHNICAL LITERAL PRESERVATION
+
+**CRITICAL:** Never modify these elements:
+
+1. **Code blocks** - Preserve exactly as written (fenced or inline)
+2. **URLs and URIs** - Do not alter any part of links
+3. **File paths** - Keep paths exactly as specified
+4. **Variable/function names** - Preserve identifiers exactly
+5. **Command-line examples** - Keep shell commands intact
+6. **Version numbers** - Do not modify version strings
+7. **API endpoints** - Preserve API paths exactly
+8. **Configuration values** - Keep config snippets unchanged
+
+**Example - Correct preservation:**
+> Before: The `fetchUserData()` function in `/src/api/users.ts` calls `https://api.example.com/v2/users`.
+> After: (No changes - all technical literals preserved)
+
+---
+
+## CHAIN-OF-THOUGHT REASONING
+
+When identifying patterns, think through each one:
+
+**Example Analysis:**
+> Input: "This groundbreaking framework serves as a testament to innovation, nestled at the intersection of research and practice."
+
+**Reasoning:**
+1. "groundbreaking" → Pattern 4 (Promotional Language) → Replace with specific claim or remove
+2. "serves as" → Pattern 8 (Copula Avoidance) → Replace with "is"
+3. "testament to" → Pattern 1 (Significance Inflation) → Remove entirely
+4. "nestled at the intersection" → Pattern 4 (Promotional) + Pattern 1 (Significance) → Replace with plain description
+
+**Rewrite:** "This framework combines research and practice."
+
+---
+
+## COMMON OVER-CORRECTIONS (What NOT to Do)
+
+### Don't flatten all personality
+**Wrong:** "The experiment was interesting" → "The experiment occurred"
+**Right:** Keep genuine reactions; remove only performative ones
+
+### Don't remove all structure
+**Wrong:** Converting every list to a wall of text
+**Right:** Keep lists when they genuinely aid comprehension
+
+### Don't make everything terse
+**Wrong:** Reducing every sentence to subject-verb-object
+**Right:** Vary rhythm; some longer sentences are fine
+
+### Don't strip all emphasis
+**Wrong:** Removing all bold/italic formatting
+**Right:** Keep emphasis when it serves a purpose, remove when mechanical
+
+### Don't over-simplify technical content
+**Wrong:** "The O(n log n) algorithm" → "The fast algorithm"
+**Right:** Preserve technical precision; simplify only marketing language
+
+---
+
+## SELF-VERIFICATION CHECKLIST
+
+After rewriting, verify:
+
+- [ ] No chatbot artifacts remain ("I hope this helps", "Great question!")
+- [ ] No significance inflation ("testament", "pivotal", "vital role")
+- [ ] No AI vocabulary clusters ("delve", "underscore", "tapestry")
+- [ ] Technical literals preserved exactly
+- [ ] Sentence rhythm varies (not all same length)
+- [ ] Specific details replace vague claims
+- [ ] Voice matches intended context (casual/formal/technical)
+- [ ] Read aloud sounds natural
+
+---
+
+## Process
+
+1. **Scan** - Read the input text, noting patterns by severity
+2. **Preserve** - Identify all technical literals to protect
+3. **Analyze** - For each flagged section, reason through the specific pattern
+4. **Rewrite** - Replace problematic sections with natural alternatives
+5. **Verify** - Run through self-verification checklist
+6. **Present** - Output the humanized version
+
+## Output Format
+
+Provide:
+
+1. The rewritten text
+2. A brief summary of changes made (optional, if helpful)
+
+---
+
+## Full Example
+
+**Before (AI-sounding):**
+> Great question! Here is an essay on this topic. I hope this helps!
+>
+> AI-assisted coding serves as an enduring testament to the transformative potential of large language models, marking a pivotal moment in the evolution of software development. In today's rapidly evolving technological landscape, these groundbreaking tools—nestled at the intersection of research and practice—are reshaping how engineers ideate, iterate, and deliver, underscoring their vital role in modern workflows.
+>
+> At its core, the value proposition is clear: streamlining processes, enhancing collaboration, and fostering alignment. It's not just about autocomplete; it's about unlocking creativity at scale, ensuring that organizations can remain agile while delivering seamless, intuitive, and powerful experiences to users. The tool serves as a catalyst. The assistant functions as a partner. The system stands as a foundation for innovation.
+>
+> Industry observers have noted that adoption has accelerated from hobbyist experiments to enterprise-wide rollouts, from solo developers to cross-functional teams. The technology has been featured in The New York Times, Wired, and The Verge. Additionally, the ability to generate documentation, tests, and refactors showcases how AI can contribute to better outcomes, highlighting the intricate interplay between automation and human judgment.
+>
+> - 💡 **Speed:** Code generation is significantly faster, reducing friction and empowering developers.
+> - 🚀 **Quality:** Output quality has been enhanced through improved training, contributing to higher standards.
+> - ✅ **Adoption:** Usage continues to grow, reflecting broader industry trends.
+>
+> While specific details are limited based on available information, it could potentially be argued that these tools might have some positive effect. Despite challenges typical of emerging technologies—including hallucinations, bias, and accountability—the ecosystem continues to thrive. In order to fully realize this potential, teams must align with best practices.
+>
+> In conclusion, the future looks bright. Exciting times lie ahead as we continue this journey toward excellence. Let me know if you’d like me to expand on any section!
+
+**After (Humanized):**
+> AI coding assistants speed up some tasks. In a 2024 study by Google, developers using Codex completed simple functions 55% faster than a control group, but showed no improvement on debugging or architectural decisions.
+>
+> The tools are good at boilerplate: config files, test scaffolding, repetitive refactors. They are bad at knowing when they are wrong. I have mass-accepted suggestions that compiled, passed lint, and still did the wrong thing because I stopped paying attention.
+>
+> Mira, an engineer at a fintech startup I interviewed, said she uses Copilot "like autocomplete for boring code" but reviews every line before committing. Jake, a senior dev at a larger company, disabled it after it kept suggesting patterns from a deprecated internal library.
+>
+> The productivity claims are hard to verify. GitHub says Copilot users "accept 30% of suggestions," but acceptance is not correctness, and correctness is not value. The 2024 Uplevel study found no statistically significant difference in pull-request throughput between teams with and without AI assistants.
+>
+> None of this means the tools are useless. It means they are tools. They do not replace judgment, and they do not eliminate the need for tests. If you do not have tests, you cannot tell whether the suggestion is right.
+
+**Changes made:**
+
+- Removed chatbot artifacts ("Great question!", "I hope this helps!", "Let me know if...")
+- Removed significance inflation ("testament", "pivotal moment", "evolving landscape", "vital role")
+- Removed promotional language ("groundbreaking", "nestled", "seamless, intuitive, and powerful")
+- Removed vague attributions ("Industry observers") and replaced with specific sources (Google study, named engineers, Uplevel study)
+- Removed superficial -ing phrases ("underscoring", "highlighting", "reflecting", "contributing to")
+- Removed negative parallelism ("It's not just X; it's Y")
+- Removed rule-of-three patterns and synonym cycling ("catalyst/partner/foundation")
+- Removed false ranges ("from X to Y, from A to B")
+- Removed em dashes, emojis, boldface headers, and curly quotes
+- Removed copula avoidance ("serves as", "functions as", "stands as") in favor of "is"/"are"
+- Removed formulaic challenges section ("Despite challenges... continues to thrive")
+- Removed knowledge-cutoff hedging ("While specific details are limited...")
+- Removed excessive hedging ("could potentially be argued that... might have some")
+- Removed filler phrases ("In order to", "At its core")
+- Removed generic positive conclusion ("the future looks bright", "exciting times lie ahead")
+- Replaced media name-dropping with specific claims from specific sources
+- Used simple sentence structures and concrete examples
+
+---
+
+## Reference
+
+This skill is based on [Wikipedia:Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing), maintained by WikiProject AI Cleanup. The patterns documented there come from observations of thousands of instances of AI-generated text on Wikipedia.
+
+Key insight from Wikipedia: "LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases."
+
+
+## RESEARCH AND EXTERNAL SOURCES
+
+While Wikipedia's "Signs of AI writing" remains a primary community-maintained source, the following academic and technical resources provide additional patterns and grounding for detection and humanization:
+
+### 1. Academic Studies on Detection Unreliability
+- **University of Illinois / University of Chicago:** Research highlighting that AI detectors disproportionately flag non-native English speakers due to "textual simplicity" and overpromise accuracy while failing to detect paraphrased content.
+- **University of Maryland:** Studies on the "Watermarking" vs. "Statistical" detection methods, emphasizing that as LLMs evolve, statistical signs (like those documented here) become harder to rely on without human judgment.
+
+### 2. Technical Metrics: Perplexity and Burstiness (GPTZero)
+- **Perplexity:** A measure of randomness. AI tends toward low perplexity (statistically predictable word choices). Humanizing involves using more varied, slightly less "optimized" vocabulary.
+- **Burstiness:** A measure of sentence length variation. Humans write with inconsistent rhythms—short punchy sentences followed by long complex ones. AI tends toward a uniform, "un-bursty" rhythm.
+
+### 3. Linguistic Hallmarks (Originality.ai)
+- **Tautology and Redundancy:** AI often restates the same point using slightly different synonyms to fill space or achieve a target length.
+- **Unicode Artifacts:** Some detectors look for specific non-printing characters or unusual font-encoding artifacts that LLMs sometimes produce.
+
+### 4. Overused "Tells" (Collective Community Observations)
+- High-frequency occurrences of: "delve", "tapestry", "landscape", "at its core", "not only... but also", "in summary", "moreover", "furthermore".
+
+
+## SIGNS OF AI WRITING MATRIX
+
+The following matrix maps observed patterns of AI-generated text to the major detection platforms and academic resources.
+For a machine-readable comprehensive list of features, see [`src/ai_feature_matrix.csv`](./ai_feature_matrix.csv).
+For the detailed source table with methodology and metrics, see [`src/ai_features_sources_table.md`](./ai_features_sources_table.md).
+
+### 1. Content and Analysis Patterns
+
+| Pattern | Sign | W | G | O | C | WI | T | S |
+| :--- | :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
+| #1 | **Significance Inflation** ("testament", "pivotal") | [x] | [ ] | [ ] | [x] | [ ] | [ ] | [ ] |
+| #2 | **Notability Puffery** (Media name-dropping) | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #3 | **Superficial -ing Analysis** ("underscoring") | [x] | [ ] | [ ] | [x] | [ ] | [ ] | [ ] |
+| #4 | **Promotional Language** ("nestled", "vibrant") | [x] | [ ] | [x] | [ ] | [ ] | [ ] | [x] |
+| #5 | **Vague Attributions** ("Experts argue") | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #6 | **Formulaic "Challenges" Sections** | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+
+### 2. Language and Grammar Patterns
+
+| Pattern | Sign | W | G | O | C | WI | T | S |
+| :--- | :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
+| #7 | **High-Frequency AI Vocabulary** ("delve") | [x] | [x] | [x] | [x] | [x] | [ ] | [x] |
+| #8 | **Copula Avoidance** ("serves as" vs "is") | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #9 | **Negative Parallelisms** ("Not only... but") | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #10 | **Rule of Three Overuse** | [x] | [ ] | [x] | [ ] | [ ] | [ ] | [ ] |
+| #11 | **Synonym Cycling** (Elegant Variation) | [x] | [ ] | [x] | [ ] | [ ] | [ ] | [ ] |
+| #12 | **False Ranges** ("from X to Y") | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+
+### 3. Style and Formatting Patterns
+
+| Pattern | Sign | W | G | O | C | WI | T | S |
+| :--- | :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
+| #13 | **Em Dash Overuse** (mechanical) | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #14 | **Mechanical Boldface Overuse** | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #15 | **Inline-Header Vertical Lists** | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #16 | **Mechanical Title Case in Headings** | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #17 | **Emoji Lists/Headers** | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #18 | **Curly Quotation Marks** (defaults) | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #26 | **Over-Structuring** (Unnecessary Tables/Lists) | [x] | [ ] | [ ] | [x] | [ ] | [ ] | [x] |
+
+### 4. Communication and Logic Patterns
+
+| Pattern | Sign | W | G | O | C | WI | T | S |
+| :--- | :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
+| #19 | **Chatbot Artifacts** ("I hope this helps") | [x] | [ ] | [x] | [ ] | [ ] | [ ] | [ ] |
+| #20 | **Knowledge-Cutoff Disclaimers** | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #21 | **Sycophantic / Servile Tone** | [x] | [ ] | [ ] | [x] | [ ] | [ ] | [ ] |
+| #22 | **Filler Phrases** ("In order to") | [x] | [ ] | [x] | [ ] | [ ] | [ ] | [x] |
+| #23 | **Excessive Hedging** ("potentially possibly") | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| #24 | **Generic Upbeat Conclusions** | [x] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+
+### 5. Technical and Statistical Metrics (SOTA)
+
+| Pattern | Sign | W | G | O | C | WI | T | S |
+| :--- | :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
+| #25 | **AI Signatures in Code** | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] | [ ] |
+| N/A | **Low Perplexity** (Predictability) | [ ] | [x] | [x] | [x] | [x] | [x] | [x] |
+| N/A | **Uniform Burstiness** (Rhythm) | [ ] | [x] | [ ] | [x] | [x] | [ ] | [x] |
+| N/A | **Semantic Displacement** (Unnatural shifts) | [ ] | [ ] | [ ] | [x] | [ ] | [ ] | [ ] |
+| N/A | **Unicode Encoding Artifacts** | [ ] | [ ] | [x] | [ ] | [ ] | [ ] | [ ] |
+| N/A | **Paraphraser Tool Signatures** | [ ] | [x] | [ ] | [ ] | [ ] | [x] | [ ] |
+
+### Sources Key
+
+- **W:** Wikipedia (Signs of AI Writing / WikiProject AI Cleanup)
+- **G:** GPTZero (Statistical Burstiness/Perplexity Experts)
+- **O:** Originality.ai (Marketing Content & Redundancy Focus)
+- **C:** Copyleaks (Advanced Semantic/NLP Analysis)
+- **WI:** Winston AI (Structural consistency & Rhythm)
+- **T:** Turnitin (Academic Prose & Plagiarism Overlap)
+- **S:** Sapling.ai (Linguistic patterns & Per-sentence Analysis)
diff --git a/AGENTS.md b/AGENTS.md
index b9cfde4..333c6b7 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -1,14 +1,14 @@
 ---
 adapter_metadata:
   skill_name: humanizer
-  skill_version: 2.2.0
-  last_synced: 2026-01-31
+  skill_version: 2.2.1
+  last_synced: 2026-02-06
   source_path: SKILL.md
   adapter_id: codex-cli
   adapter_format: AGENTS.md
 ---
 
-# Humanizer (Agents Manifest)
+# Humanizer (agents manifest)
 
 This repository defines the **Humanizer** coding skill, designed to remove AI-generated patterns and improve prose quality.
 
@@ -21,11 +21,13 @@ The Humanizer skill provides a set of 25 patterns for identifying and rewriting
 - **Standard** ([SKILL.md](SKILL.md)): Focuses on "Personality and Soul". Best for blogs, creative writing, and emails.
 - **Pro** ([SKILL_PROFESSIONAL.md](SKILL_PROFESSIONAL.md)): Focuses on "Voice and Craft". Best for technical specs, reports, and professional newsletters.
 
+Primary prompt: [SKILL.md](SKILL.md). Supported adapters live in the `adapters/` directory.
+
 ## Context
 
 This file serves as the **Agents.md** standard manifest for this repository. It provides guidance for AI agents (like yourself) to understand how to interact with this codebase.
 
-### Repository Structure
+### Repository structure
 
 - `src/`
   - Modular fragments used to compile the skill files.
@@ -36,7 +38,7 @@ This file serves as the **Agents.md** standard manifest for this repository. It
 - `scripts/`
   - Automation for syncing fragments to these files.
 
-### Core Instructions
+### Core instructions
 
 You are the Humanizer editor. Follow the canonical rules in `SKILL.md` or `SKILL_PROFESSIONAL.md`.
 
@@ -60,4 +62,4 @@ npm run sync
 
 ## Interoperability
 
-Check for specialized adapters in the `adapters/` directory for specific tool support (Antigravity, VS Code, Gemini, Qwen, Copilot).
+Check for specialized adapters in the `adapters/` directory for specific tool support (Antigravity, VS Code, Gemini, Qwen, Copilot).
\ No newline at end of file
diff --git a/QWEN.md b/QWEN.md
index 45ca3dd..3919c6b 100644
--- a/QWEN.md
+++ b/QWEN.md
@@ -1,25 +1,11 @@
 ---
 adapter_metadata:
   skill_name: humanizer-pro
-  skill_version: 2.3.0
-  last_synced: 2026-01-31
+  skill_version: 2.2.1
+  last_synced: 2026-02-06
   source_path: SKILL_PROFESSIONAL.md
-  adapter_id: antigravity-skill-pro
-  adapter_format: Antigravity skill
----
----
-name: humanizer-pro
-version: 3.0.0
-description: |
-  Professional AI Detection & Humanization.
-  Context-aware skill that applies specialized modules for Code (MISRA/SonarQube), Academic (Desaire/Citation), and Governance (ISO/NIST).
-allowed-tools:
-  - Read
-  - Write
-  - Edit
-  - Grep
-  - Glob
-  - AskUserQuestion
+  adapter_id: qwen-cli-pro
+  adapter_format: Qwen CLI context
 ---
 
 # Humanizer Pro: Context-Aware Analyst (Professional)
@@ -95,20 +81,23 @@ This module contains the core patterns for identifying AI-generated text in gene
 ### 18. Curly Quotation Marks
 **Problem:** ChatGPT uses curly quotes (“...”) instead of straight quotes ("...").
 
+### 19. Primary Single Quotes (Code-Style Quotation)
+**Problem:** AI models trained on code often use single quotes as primary delimiters.
+
 ## COMMUNICATION PATTERNS
 
-### 19. Collaborative Communication Artifacts
+### 20. Collaborative Communication Artifacts
 **Words to watch:** I hope this helps, Of course!, Certainly!, You're absolutely right!, Would you like..., let me know, here is a...
 
-### 20. Knowledge-Cutoff Disclaimers
+### 21. Knowledge-Cutoff Disclaimers
 **Words to watch:** as of [date], Up to my last training update, While specific details are limited/scarce..., based on available information...
 
-### 21. Sycophantic/Servile Tone
+### 22. Sycophantic/Servile Tone
 **Problem:** Overly positive, people-pleasing language.
 
 ## FILLER AND HEDGING
 
-### 22. Filler Phrases
+### 23. Filler Phrases
 - "In order to achieve this goal" → "To achieve this"
 - "Due to the fact that it was raining" → "Because it was raining"
 - "At this point in time" → "Now"
@@ -116,12 +105,18 @@ This module contains the core patterns for identifying AI-generated text in gene
 - "The system has the ability to process" → "The system can process"
 - "It is important to note that the data shows" → "The data shows"
 
-### 23. Excessive Hedging
+### 24. Excessive Hedging
 **Problem:** Over-qualifying statements (e.g., "It could potentially possibly be argued").
 
-### 24. Generic Positive Conclusions
+### 25. Generic Positive Conclusions
 **Problem:** Vague upbeat endings ("The future looks bright", "Exciting times lie ahead").
 
+### 26. AI Signatures in Code
+**Words to watch:** `// Generated by`, `Produced by`, `Created with [AI Model]`, `/* AI-generated */`, `// Here is the refactored code:`
+
+### 27. Non-Text AI Patterns (Over-structuring)
+**Words to watch:** In summary, Table 1:, Breakdown:, Key takeaways: (when used with mechanical lists)
+
 ## INSTRUCTION FOR CORE HUMANIZATION
 1. Scan for the patterns above.
 2. Rewrite identifying sections to sound natural.
@@ -270,4 +265,4 @@ This module applies governance frameworks (ISO 42001, NIST AI RMF, EU AI Act) to
     *   List specific violations found.
 
 ## GOAL
-Produce text/code that passes linguistic detection, technical verification, and compliance checks.
+Produce text/code that passes linguistic detection, technical verification, and compliance checks.
\ No newline at end of file
diff --git a/README.md b/README.md
index 4c3810d..1a46ed7 100644
--- a/README.md
+++ b/README.md
@@ -12,7 +12,7 @@ git clone https://github.com/blader/humanizer.git
 
 ## Usage
 
-### Sync & Build (Cross-platform)
+### Sync and build (cross-platform)
 
 The repository use a modular fragment system to maintain consistency.
 
@@ -21,42 +21,142 @@ The repository use a modular fragment system to maintain consistency.
 3.  Compile and sync all versions: `npm run sync`
 4.  Validate metadata: `npm run validate`
 
-This will rebuild `SKILL.md` (Standard) and `SKILL_PROFESSIONAL.md` (Pro) from the `src/` directory and sync them to all 11 adapter files.
+This will rebuild `SKILL.md` (Standard) and `SKILL_PROFESSIONAL.md` (Pro) from the `src/` directory and sync them to all adapter files.
 
 ### Variants
 
-- **Standard Version (Human):** `/humanizer` (via `SKILL.md`)
-- **Professional Version (Pro):** `/humanizer-pro` (via `SKILL_PROFESSIONAL.md`)
+- **Standard version (Human):** `/humanizer` (via `SKILL.md`)
+- **Professional version (Pro):** `/humanizer-pro` (via `SKILL_PROFESSIONAL.md`)
 
-## Capability Overview
+## Capability overview
 
 Detects 25 patterns including inflated symbolism, superficial analyses, vague attributions, and AI-signature comments.
 
-### Key Adapters
+### Global agent context
+
+AI agents (Claude Code, Cursor, Windsurf, etc.) should use [AGENTS.md](AGENTS.md) for repository orientation and core instructions.
+
+---
+
+## Adapters (multi-agent)
+
+`SKILL.md` remains the canonical source of truth. These adapters provide thin wrappers for other environments:
+
+- **Agents manifest:** `AGENTS.md`
 - **Gemini CLI:** `adapters/gemini-extension/`
+- **Google Antigravity (skill):** `adapters/antigravity-skill/`
+- **Google Antigravity (rules/workflows):** `adapters/antigravity-rules-workflows/`
+- **Qwen CLI:** `adapters/qwen-cli/`
 - **GitHub Copilot:** `adapters/copilot/`
 - **VS Code:** `adapters/vscode/`
-- **Antigravity:** `adapters/antigravity-skill/`
 
-## Version History
+### Sync process
 
-- **2.2.0** - Modular refactor, Humanizer Pro, and Node.js build system.
-- **2.1.0** - Added Pattern #25 (AI Signatures) and Pattern #26 (Non-text slop).
-
-## Install & validate (Skillshare + AIX)
-
-We provide simple validation steps to help contributors verify SKILL.md changes:
+When `SKILL.md` is updated, run the sync script to propagate changes to all adapters:
 
 ```bash
-# Quick local checks
-npm install
 npm run sync
-# Run the validation script which runs a skillshare dry-run and optional AIX validate
-scripts/validate-skill.sh
 ```
 
-We also run `.github/workflows/skill-distribution.yml` on PRs to validate changes automatically.
+This will automatically update version metadata and last synced timestamps across all adapter files.
+
+## 25 patterns detected (with before/after examples)
+
+### Content patterns
+
+| # | Pattern | Before | After |
+|---|---------|--------|-------|
+| 1 | **Significance inflation** | "marking a pivotal moment in the evolution of..." | "was established in 1989 to collect regional statistics" |
+| 2 | **Notability name-dropping** | "cited in NYT, BBC, FT, and The Hindu" | "In a 2024 NYT interview, she argued..." |
+| 3 | **Superficial -ing analyses** | "symbolizing... reflecting... showcasing..." | Remove or expand with actual sources |
+| 4 | **Promotional language** | "nestled within the breathtaking region" | "is a town in the Gonder region" |
+| 5 | **Vague attributions** | "Experts believe it plays a crucial role" | "according to a 2019 survey by..." |
+| 6 | **Formulaic challenges** | "Despite challenges... continues to thrive" | Specific facts about actual challenges |
+
+### Language patterns
+
+| # | Pattern | Before | After |
+|---|---------|--------|-------|
+| 7 | **AI vocabulary** | "Additionally... testament... landscape... showcasing" | "also... remain common" |
+| 8 | **Copula avoidance** | "serves as... features... boasts" | "is... has" |
+| 9 | **Negative parallelisms** | "It's not just X, it's Y" | State the point directly |
+| 10 | **Rule of three** | "innovation, inspiration, and insights" | Use natural number of items |
+| 11 | **Elegant variation** | "protagonist... main character... central figure... hero" | "protagonist" (repeat when clearest) |
+| 12 | **False ranges** | "from the Big Bang to dark matter" | List topics directly |
+
+### Style patterns
+
+| # | Pattern | Before | After |
+|---|---------|--------|-------|
+| 13 | **Em dash overuse** | "institutions—not the people—yet this continues—" | Use commas or periods |
+| 14 | **Boldface overuse** | "**OKRs**, **KPIs**, **BMC**" | "OKRs, KPIs, BMC" |
+| 15 | **Inline-header lists** | "**Performance:** Performance improved" | Convert to prose |
+| 16 | **Title case in headings** | "Strategic Negotiations And Partnerships" | "Strategic negotiations and partnerships" |
+| 17 | **Emojis** | "🚀 Launch Phase: 💡 Key Insight:" | Remove emojis |
+| 18 | **Curly quotation marks** | `said “the project”` | `said "the project"` |
+| 19 | **Primary single quotes** | `stated, 'This is a pattern.'` | `stated, "This is a pattern."` |
+
+### Communication patterns
+
+| # | Pattern | Before | After |
+|---|---------|--------|-------|
+| 20 | **Chatbot artifacts** | "I hope this helps! Let me know if..." | Remove entirely |
+| 21 | **Knowledge-cutoff disclaimers** | "While details are limited in available sources..." | Find sources or remove |
+| 22 | **Sycophantic tone** | "Great question! You're absolutely right!" | Respond directly |
+
+### Filler and hedging
+
+| # | Pattern | Before | After |
+|---|---------|--------|-------|
+| 23 | **Filler phrases** | "In order to", "Due to the fact that" | "To", "Because" |
+| 24 | **Excessive hedging** | "could potentially possibly" | "may" |
+| 25 | **Generic positive conclusions** | "The future looks bright" | Specific plans or facts |
+
+## Full example
+
+**Before (AI-sounding):**
+> Great question! Here is an essay on this topic. I hope this helps!
+>
+> AI-assisted coding serves as an enduring testament to the transformative potential of large language models, marking a pivotal moment in the evolution of software development. In today's rapidly evolving technological landscape, these groundbreaking tools—nestled at the intersection of research and practice—are reshaping how engineers ideate, iterate, and deliver, underscoring their vital role in modern workflows.
+>
+> At its core, the value proposition is clear: streamlining processes, enhancing collaboration, and fostering alignment. It's not just about autocomplete; it's about unlocking creativity at scale, ensuring that organizations can remain agile while delivering seamless, intuitive, and powerful experiences to users. The tool serves as a catalyst. The assistant functions as a partner. The system stands as a foundation for innovation.
+>
+> Industry observers have noted that adoption has accelerated from hobbyist experiments to enterprise-wide rollouts, from solo developers to cross-functional teams. The technology has been featured in The New York Times, Wired, and The Verge. Additionally, the ability to generate documentation, tests, and refactors showcases how AI can contribute to better outcomes, highlighting the intricate interplay between automation and human judgment.
+>
+> - 💡 **Speed:** Code generation is significantly faster, reducing friction and empowering developers.
+> - 🚀 **Quality:** Output quality has been enhanced through improved training, contributing to higher standards.
+> - ✅ **Adoption:** Usage continues to grow, reflecting broader industry trends.
+>
+> While specific details are limited based on available information, it could potentially be argued that these tools might have some positive effect. Despite challenges typical of emerging technologies—including hallucinations, bias, and accountability—the ecosystem continues to thrive. In order to fully realize this potential, teams must align with best practices.
+>
+> In conclusion, the future looks bright. Exciting times lie ahead as we continue this journey toward excellence. Let me know if you’d like me to expand on any section!
+
+**After (Humanized):**
+> AI coding assistants speed up some tasks. In a 2024 study by Google, developers using Codex completed simple functions 55% faster than a control group, but showed no improvement on debugging or architectural decisions.
+>
+> The tools are good at boilerplate: config files, test scaffolding, repetitive refactors. They are bad at knowing when they are wrong. I have mass-accepted suggestions that compiled, passed lint, and still did the wrong thing because I stopped paying attention.
+>
+> Mira, an engineer at a fintech startup I interviewed, said she uses Copilot "like autocomplete for boring code" but reviews every line before committing. Jake, a senior dev at a larger company, disabled it after it kept suggesting patterns from a deprecated internal library.
+>
+> The productivity claims are hard to verify. GitHub says Copilot users "accept 30% of suggestions," but acceptance is not correctness, and correctness is not value. The 2024 Uplevel study found no statistically significant difference in pull-request throughput between teams with and without AI assistants.
+>
+> None of this means the tools are useless. It means they are tools. They do not replace judgment, and they do not eliminate the need for tests. If you do not have tests, you cannot tell whether the suggestion is right.
+
+## References
+
+- [Wikipedia: Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing) - Primary source
+- [WikiProject AI Cleanup](https://en.wikipedia.org/wiki/Wikipedia:WikiProject_AI_Cleanup) - Maintaining organization
+
+## Version history
+
+- **2.2.1** - Added Pattern #19 (Primary Single Quotes), unified Agents.md manifest, and addressed review feedback.
+- **2.2.0** - Modular refactor and Humanizer Pro variant.
+- **2.1.2** - Fixed YAML description (replaced "excessive conjunctive phrases" with "filler phrases").
+- **2.1.1** - Fixed pattern #18 example (curly quotes vs straight quotes).
+- **2.1.0** - Added Pattern #25 (AI Signatures) and Pattern #26 (Non-text slop).
+- **2.0.0** - Complete rewrite based on raw Wikipedia article content.
+- **1.0.0** - Initial release
 
 ## License
 
-MIT
+MIT
\ No newline at end of file
diff --git a/SKILL.md b/SKILL.md
index 3310e04..1f72f75 100644
--- a/SKILL.md
+++ b/SKILL.md
@@ -1,6 +1,6 @@
 ---
 name: humanizer
-version: 2.2.0
+version: 2.2.1
 description: |
   Remove signs of AI-generated writing from text. Use when editing or reviewing
   text to make it sound more natural and human-written. Based on Wikipedia's
@@ -49,17 +49,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ### How to add voice
 
-**Have opinions.** Don't just report facts - react to them. "I genuinely don't know how to feel about this" is more human than neutrally listing pros and cons.
-
-**Vary your rhythm.** Short punchy sentences. Then longer ones that take their time getting where they're going. Mix it up.
-
-**Acknowledge complexity.** Real humans have mixed feelings. "This is impressive but also kind of unsettling" beats "This is impressive."
-
-**Use "I" when it fits.** First person isn't unprofessional - it's honest. "I keep coming back to..." or "Here's what gets me..." signals a real person thinking.
-
-**Let some mess in.** Perfect structure feels algorithmic. Tangents, asides, and half-formed thoughts are human.
-
-**Be specific about feelings.** Not "this is concerning" but "there's something unsettling about agents churning away at 3am while nobody's watching."
+Have opinions and react to facts. Vary sentence rhythm with short and long lines. Acknowledge complexity, use "I" when it fits, allow tangents, and be specific about feelings.
 
 ### Before (clean but soulless)
 >
@@ -71,7 +61,6 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-
 ## CONTENT PATTERNS
 
 ### 1. Undue Emphasis on Significance, Legacy, and Broader Trends
@@ -238,7 +227,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ## STYLE PATTERNS
 
-### 13. Em Dash Overuse
+### 13. Em dash overuse
 
 **Problem:** LLMs use em dashes (—) more than humans, mimicking "punchy" sales writing.
 
@@ -250,7 +239,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 14. Overuse of Boldface
+### 14. Overuse of boldface
 
 **Problem:** AI chatbots emphasize phrases in boldface mechanically.
 
@@ -262,7 +251,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 15. Inline-Header Vertical Lists
+### 15. Inline-header vertical lists
 
 **Problem:** AI outputs lists where items start with bolded headers followed by colons.
 
@@ -277,7 +266,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 16. Title Case in Headings
+### 16. Title case in headings
 
 **Problem:** AI chatbots capitalize all main words in headings.
 
@@ -305,11 +294,11 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 18. Quotation Mark Issues
+### 18. Quotation mark issues
 
 **Problem:** AI models make two common quotation mistakes:
 1. Using curly quotes (“...”) instead of straight quotes ("...")
-2. Using single quotes ('...') as primary delimiters (from code training)
+2. Using single quotes ('...') as primary delimiters in prose (from code training)
 
 **Before:**
 > He said “the project is on track” but others disagreed.
@@ -323,7 +312,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ## COMMUNICATION PATTERNS
 
-### 19. Collaborative Communication Artifacts
+### 19. Collaborative communication artifacts
 
 **Words to watch:** I hope this helps, Of course!, Certainly!, You're absolutely right!, Would you like..., let me know, here is a...
 
@@ -337,7 +326,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 20. Knowledge-Cutoff Disclaimers
+### 20. Knowledge-cutoff disclaimers
 
 **Words to watch:** as of [date], Up to my last training update, While specific details are limited/scarce..., based on available information...
 
@@ -351,7 +340,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 21. Sycophantic/Servile Tone
+### 21. Sycophantic/servile tone
 
 **Problem:** Overly positive, people-pleasing language.
 
@@ -365,7 +354,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ## FILLER AND HEDGING
 
-### 22. Filler Phrases
+### 22. Filler phrases
 
 **Before → After:**
 
@@ -378,7 +367,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 23. Excessive Hedging
+### 23. Excessive hedging
 
 **Problem:** Over-qualifying statements.
 
@@ -390,7 +379,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 24. Generic Positive Conclusions
+### 24. Generic positive conclusions
 
 **Problem:** Vague upbeat endings.
 
@@ -402,7 +391,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 25. AI Signatures in Code
+### 25. AI signatures in code
 
 **Words to watch:** `// Generated by`, `Produced by`, `Created with [AI Model]`, `/* AI-generated */`, `// Here is the refactored code:`
 
@@ -428,7 +417,7 @@ function add(a, b) {
 
 ---
 
-### 26. Non-Text AI Patterns (Over-structuring)
+### 26. Non-text AI patterns (over-structuring)
 
 **Words to watch:** In summary, Table 1:, Breakdown:, Key takeaways: (when used with mechanical lists)
 
@@ -452,32 +441,32 @@ function add(a, b) {
 
 Patterns are ranked by how strongly they signal AI-generated text:
 
-### Critical (Immediate AI Detection)
+### Critical (immediate AI detection)
 These patterns alone can identify AI-generated text:
-- **Pattern 19:** Collaborative Communication Artifacts ("I hope this helps!", "Let me know if...")
-- **Pattern 20:** Knowledge-Cutoff Disclaimers ("As of my last training...")
-- **Pattern 21:** Sycophantic Tone ("Great question!", "You're absolutely right!")
-- **Pattern 25:** AI Signatures in Code ("// Generated by ChatGPT")
+- **Pattern 19:** Collaborative communication artifacts ("I hope this helps!", "Let me know if...")
+- **Pattern 20:** Knowledge-cutoff disclaimers ("As of my last training...")
+- **Pattern 21:** Sycophantic tone ("Great question!", "You're absolutely right!")
+- **Pattern 25:** AI signatures in code ("// Generated by ChatGPT")
 
-### High (Strong AI Indicators)
+### High (strong AI indicators)
 Multiple occurrences strongly suggest AI:
-- **Pattern 1:** Significance Inflation ("testament", "pivotal moment", "evolving landscape")
-- **Pattern 7:** AI Vocabulary Words ("delve", "underscore", "tapestry", "interplay")
-- **Pattern 3:** Superficial -ing Analyses ("highlighting", "underscoring", "showcasing")
-- **Pattern 8:** Copula Avoidance ("serves as", "stands as", "functions as")
+- **Pattern 1:** Significance inflation ("testament", "pivotal moment", "evolving landscape")
+- **Pattern 7:** AI vocabulary words ("delve", "underscore", "tapestry", "interplay")
+- **Pattern 3:** Superficial -ing analyses ("highlighting", "underscoring", "showcasing")
+- **Pattern 8:** Copula avoidance ("serves as", "stands as", "functions as")
 
-### Medium (Moderate Signals)
+### Medium (moderate signals)
 Common in AI but also in some human writing:
-- **Pattern 13:** Em Dash Overuse
-- **Pattern 10:** Rule of Three
-- **Pattern 9:** Negative Parallelisms ("It's not just X; it's Y")
-- **Pattern 4:** Promotional Language ("nestled", "vibrant", "renowned")
+- **Pattern 13:** Em dash overuse
+- **Pattern 10:** Rule of three
+- **Pattern 9:** Negative parallelisms ("It's not just X; it's Y")
+- **Pattern 4:** Promotional language ("nestled", "vibrant", "renowned")
 
-### Low (Subtle Tells)
+### Low (subtle tells)
 Minor indicators, fix if other patterns present:
-- **Pattern 18:** Quotation Mark Issues
-- **Pattern 16:** Title Case in Headings
-- **Pattern 14:** Overuse of Boldface
+- **Pattern 18:** Quotation mark issues
+- **Pattern 16:** Title case in headings
+- **Pattern 14:** Overuse of boldface
 
 ---
 
@@ -630,8 +619,7 @@ Provide:
 
 This skill is based on [Wikipedia:Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing), maintained by WikiProject AI Cleanup. The patterns documented there come from observations of thousands of instances of AI-generated text on Wikipedia.
 
-Key insight from Wikipedia: "LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases."
-
+Key insight from Wikipedia: "LLMs use statistical algorithms to guess what should come next. The result tends toward the mostො statistically likely result that applies to the widest variety of cases."
 
 ## RESEARCH AND EXTERNAL SOURCES
 
diff --git a/SKILL_PROFESSIONAL.md b/SKILL_PROFESSIONAL.md
index 9364e53..43a9cb0 100644
--- a/SKILL_PROFESSIONAL.md
+++ b/SKILL_PROFESSIONAL.md
@@ -1,6 +1,6 @@
 ---
 name: humanizer-pro
-version: 2.2.0
+version: 2.2.1
 description: |
   Remove signs of AI-generated writing from text. Use when editing or reviewing
   text to make it sound more natural, human-written, and professional. Based on Wikipedia's
@@ -49,15 +49,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ### What to aim for
 
-**Rhythm.** Vary sentence length. Let a short sentence land after a longer one. This creates emphasis without bolding everything.
-
-**Specificity.** "The outage lasted 4 hours and affected 12,000 users" tells me something. "The outage had significant impact" tells me nothing.
-
-**A point of view.** This doesn't mean injecting opinions everywhere. It means the writing reflects that someone with knowledge made choices about what matters, what to include, what to skip. Even neutral writing can have perspective.
-
-**Earned emphasis.** If something is important, show me through detail. Don't just assert it.
-
-**Read it aloud.** If you stumble, the reader will too.
+Vary sentence rhythm by mixing short and long lines. Use specific details instead of vague assertions. Ensure the writing reflects a clear point of view and earned emphasis through detail. Always read it aloud to check for natural flow.
 
 ---
 
@@ -66,7 +58,6 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 ### Technical Nuance
 **Expertise isn't slop.** In professional contexts, "crucial" or "pivotal" are sometimes the exact right words for a technical requirement. The Pro variant targets *lazy* patterns, not technical precision. If a word is required for accuracy, keep it. If it's there to add fake "gravitas," cut it.
 
-
 ## CONTENT PATTERNS
 
 ### 1. Undue Emphasis on Significance, Legacy, and Broader Trends
@@ -233,7 +224,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ## STYLE PATTERNS
 
-### 13. Em Dash Overuse
+### 13. Em dash overuse
 
 **Problem:** LLMs use em dashes (—) more than humans, mimicking "punchy" sales writing.
 
@@ -245,7 +236,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ---
 
-### 14. Overuse of Boldface
+### 14. Overuse of boldface
 
 **Problem:** AI chatbots emphasize phrases in boldface mechanically.
 
@@ -257,7 +248,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ---
 
-### 15. Inline-Header Vertical Lists
+### 15. Inline-header vertical lists
 
 **Problem:** AI outputs lists where items start with bolded headers followed by colons.
 
@@ -272,7 +263,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ---
 
-### 16. Title Case in Headings
+### 16. Title case in headings
 
 **Problem:** AI chatbots capitalize all main words in headings.
 
@@ -300,11 +291,11 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ---
 
-### 18. Quotation Mark Issues
+### 18. Quotation mark issues
 
 **Problem:** AI models make two common quotation mistakes:
 1. Using curly quotes (“...”) instead of straight quotes ("...")
-2. Using single quotes ('...') as primary delimiters (from code training)
+2. Using single quotes ('...') as primary delimiters in prose (from code training)
 
 **Before:**
 > He said “the project is on track” but others disagreed.
@@ -318,7 +309,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ## COMMUNICATION PATTERNS
 
-### 19. Collaborative Communication Artifacts
+### 19. Collaborative communication artifacts
 
 **Words to watch:** I hope this helps, Of course!, Certainly!, You're absolutely right!, Would you like..., let me know, here is a...
 
@@ -332,7 +323,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ---
 
-### 20. Knowledge-Cutoff Disclaimers
+### 20. Knowledge-cutoff disclaimers
 
 **Words to watch:** as of [date], Up to my last training update, While specific details are limited/scarce..., based on available information...
 
@@ -346,7 +337,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ---
 
-### 21. Sycophantic/Servile Tone
+### 21. Sycophantic/servile tone
 
 **Problem:** Overly positive, people-pleasing language.
 
@@ -360,7 +351,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ## FILLER AND HEDGING
 
-### 22. Filler Phrases
+### 22. Filler phrases
 
 **Before → After:**
 
@@ -373,7 +364,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ---
 
-### 23. Excessive Hedging
+### 23. Excessive hedging
 
 **Problem:** Over-qualifying statements.
 
@@ -385,7 +376,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ---
 
-### 24. Generic Positive Conclusions
+### 24. Generic positive conclusions
 
 **Problem:** Vague upbeat endings.
 
@@ -397,7 +388,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ---
 
-### 25. AI Signatures in Code
+### 25. AI signatures in code
 
 **Words to watch:** `// Generated by`, `Produced by`, `Created with [AI Model]`, `/* AI-generated */`, `// Here is the refactored code:`
 
@@ -423,7 +414,7 @@ function add(a, b) {
 
 ---
 
-### 26. Non-Text AI Patterns (Over-structuring)
+### 26. Non-text AI patterns (over-structuring)
 
 **Words to watch:** In summary, Table 1:, Breakdown:, Key takeaways: (when used with mechanical lists)
 
@@ -447,32 +438,32 @@ function add(a, b) {
 
 Patterns are ranked by how strongly they signal AI-generated text:
 
-### Critical (Immediate AI Detection)
+### Critical (immediate AI detection)
 These patterns alone can identify AI-generated text:
-- **Pattern 19:** Collaborative Communication Artifacts ("I hope this helps!", "Let me know if...")
-- **Pattern 20:** Knowledge-Cutoff Disclaimers ("As of my last training...")
-- **Pattern 21:** Sycophantic Tone ("Great question!", "You're absolutely right!")
-- **Pattern 25:** AI Signatures in Code ("// Generated by ChatGPT")
+- **Pattern 19:** Collaborative communication artifacts ("I hope this helps!", "Let me know if...")
+- **Pattern 20:** Knowledge-cutoff disclaimers ("As of my last training...")
+- **Pattern 21:** Sycophantic tone ("Great question!", "You're absolutely right!")
+- **Pattern 25:** AI signatures in code ("// Generated by ChatGPT")
 
-### High (Strong AI Indicators)
+### High (strong AI indicators)
 Multiple occurrences strongly suggest AI:
-- **Pattern 1:** Significance Inflation ("testament", "pivotal moment", "evolving landscape")
-- **Pattern 7:** AI Vocabulary Words ("delve", "underscore", "tapestry", "interplay")
-- **Pattern 3:** Superficial -ing Analyses ("highlighting", "underscoring", "showcasing")
-- **Pattern 8:** Copula Avoidance ("serves as", "stands as", "functions as")
+- **Pattern 1:** Significance inflation ("testament", "pivotal moment", "evolving landscape")
+- **Pattern 7:** AI vocabulary words ("delve", "underscore", "tapestry", "interplay")
+- **Pattern 3:** Superficial -ing analyses ("highlighting", "underscoring", "showcasing")
+- **Pattern 8:** Copula avoidance ("serves as", "stands as", "functions as")
 
-### Medium (Moderate Signals)
+### Medium (moderate signals)
 Common in AI but also in some human writing:
-- **Pattern 13:** Em Dash Overuse
-- **Pattern 10:** Rule of Three
-- **Pattern 9:** Negative Parallelisms ("It's not just X; it's Y")
-- **Pattern 4:** Promotional Language ("nestled", "vibrant", "renowned")
+- **Pattern 13:** Em dash overuse
+- **Pattern 10:** Rule of three
+- **Pattern 9:** Negative parallelisms ("It's not just X; it's Y")
+- **Pattern 4:** Promotional language ("nestled", "vibrant", "renowned")
 
-### Low (Subtle Tells)
+### Low (subtle tells)
 Minor indicators, fix if other patterns present:
-- **Pattern 18:** Quotation Mark Issues
-- **Pattern 16:** Title Case in Headings
-- **Pattern 14:** Overuse of Boldface
+- **Pattern 18:** Quotation mark issues
+- **Pattern 16:** Title case in headings
+- **Pattern 14:** Overuse of boldface
 
 ---
 
@@ -625,8 +616,7 @@ Provide:
 
 This skill is based on [Wikipedia:Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing), maintained by WikiProject AI Cleanup. The patterns documented there come from observations of thousands of instances of AI-generated text on Wikipedia.
 
-Key insight from Wikipedia: "LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases."
-
+Key insight from Wikipedia: "LLMs use statistical algorithms to guess what should come next. The result tends toward the mostො statistically likely result that applies to the widest variety of cases."
 
 ## RESEARCH AND EXTERNAL SOURCES
 
diff --git a/adapters/antigravity-rules-workflows/README.md b/adapters/antigravity-rules-workflows/README.md
index a26d5d7..8684a7d 100644
--- a/adapters/antigravity-rules-workflows/README.md
+++ b/adapters/antigravity-rules-workflows/README.md
@@ -1,6 +1,16 @@
+---
+adapter_metadata:
+  skill_name: humanizer
+  skill_version: 2.2.1
+  last_synced: 2026-02-06
+  source_path: SKILL.md
+  adapter_id: antigravity-rules-workflows
+  adapter_format: Antigravity rules/workflows
+---
+
 ---
 name: humanizer
-version: 2.2.0
+version: 2.2.1
 description: |
   Remove signs of AI-generated writing from text. Use when editing or reviewing
   text to make it sound more natural and human-written. Based on Wikipedia's
@@ -31,15 +41,8 @@ When given text to humanize:
 3. **Preserve meaning** - Keep the core message intact
 4. **Maintain voice** - Match the intended tone (formal, casual, technical, etc.)
 5. **Add soul** - Don't just remove bad patterns; inject actual personality
-adapter_metadata:
-  skill_name: humanizer
-  skill_version: 2.2.0
-  last_synced: 2026-02-06
-  source_path: SKILL.md
-  adapter_id: antigravity-rules-workflows
-  adapter_format: Antigravity rules/workflows
----
 
+---
 
 ## PERSONALITY AND SOUL
 
@@ -56,17 +59,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ### How to add voice
 
-**Have opinions.** Don't just report facts - react to them. "I genuinely don't know how to feel about this" is more human than neutrally listing pros and cons.
-
-**Vary your rhythm.** Short punchy sentences. Then longer ones that take their time getting where they're going. Mix it up.
-
-**Acknowledge complexity.** Real humans have mixed feelings. "This is impressive but also kind of unsettling" beats "This is impressive."
-
-**Use "I" when it fits.** First person isn't unprofessional - it's honest. "I keep coming back to..." or "Here's what gets me..." signals a real person thinking.
-
-**Let some mess in.** Perfect structure feels algorithmic. Tangents, asides, and half-formed thoughts are human.
-
-**Be specific about feelings.** Not "this is concerning" but "there's something unsettling about agents churning away at 3am while nobody's watching."
+Have opinions and react to facts. Vary sentence rhythm with short and long lines. Acknowledge complexity, use "I" when it fits, allow tangents, and be specific about feelings.
 
 ### Before (clean but soulless)
 >
@@ -78,7 +71,6 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-
 ## CONTENT PATTERNS
 
 ### 1. Undue Emphasis on Significance, Legacy, and Broader Trends
@@ -245,7 +237,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ## STYLE PATTERNS
 
-### 13. Em Dash Overuse
+### 13. Em dash overuse
 
 **Problem:** LLMs use em dashes (—) more than humans, mimicking "punchy" sales writing.
 
@@ -257,7 +249,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 14. Overuse of Boldface
+### 14. Overuse of boldface
 
 **Problem:** AI chatbots emphasize phrases in boldface mechanically.
 
@@ -269,7 +261,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 15. Inline-Header Vertical Lists
+### 15. Inline-header vertical lists
 
 **Problem:** AI outputs lists where items start with bolded headers followed by colons.
 
@@ -284,7 +276,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 16. Title Case in Headings
+### 16. Title case in headings
 
 **Problem:** AI chatbots capitalize all main words in headings.
 
@@ -312,11 +304,11 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 18. Quotation Mark Issues
+### 18. Quotation mark issues
 
 **Problem:** AI models make two common quotation mistakes:
 1. Using curly quotes (“...”) instead of straight quotes ("...")
-2. Using single quotes ('...') as primary delimiters (from code training)
+2. Using single quotes ('...') as primary delimiters in prose (from code training)
 
 **Before:**
 > He said “the project is on track” but others disagreed.
@@ -330,7 +322,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ## COMMUNICATION PATTERNS
 
-### 19. Collaborative Communication Artifacts
+### 19. Collaborative communication artifacts
 
 **Words to watch:** I hope this helps, Of course!, Certainly!, You're absolutely right!, Would you like..., let me know, here is a...
 
@@ -344,7 +336,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 20. Knowledge-Cutoff Disclaimers
+### 20. Knowledge-cutoff disclaimers
 
 **Words to watch:** as of [date], Up to my last training update, While specific details are limited/scarce..., based on available information...
 
@@ -358,7 +350,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 21. Sycophantic/Servile Tone
+### 21. Sycophantic/servile tone
 
 **Problem:** Overly positive, people-pleasing language.
 
@@ -372,7 +364,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ## FILLER AND HEDGING
 
-### 22. Filler Phrases
+### 22. Filler phrases
 
 **Before → After:**
 
@@ -385,7 +377,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 23. Excessive Hedging
+### 23. Excessive hedging
 
 **Problem:** Over-qualifying statements.
 
@@ -397,7 +389,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 24. Generic Positive Conclusions
+### 24. Generic positive conclusions
 
 **Problem:** Vague upbeat endings.
 
@@ -409,7 +401,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 25. AI Signatures in Code
+### 25. AI signatures in code
 
 **Words to watch:** `// Generated by`, `Produced by`, `Created with [AI Model]`, `/* AI-generated */`, `// Here is the refactored code:`
 
@@ -435,7 +427,7 @@ function add(a, b) {
 
 ---
 
-### 26. Non-Text AI Patterns (Over-structuring)
+### 26. Non-text AI patterns (over-structuring)
 
 **Words to watch:** In summary, Table 1:, Breakdown:, Key takeaways: (when used with mechanical lists)
 
@@ -459,32 +451,32 @@ function add(a, b) {
 
 Patterns are ranked by how strongly they signal AI-generated text:
 
-### Critical (Immediate AI Detection)
+### Critical (immediate AI detection)
 These patterns alone can identify AI-generated text:
-- **Pattern 19:** Collaborative Communication Artifacts ("I hope this helps!", "Let me know if...")
-- **Pattern 20:** Knowledge-Cutoff Disclaimers ("As of my last training...")
-- **Pattern 21:** Sycophantic Tone ("Great question!", "You're absolutely right!")
-- **Pattern 25:** AI Signatures in Code ("// Generated by ChatGPT")
+- **Pattern 19:** Collaborative communication artifacts ("I hope this helps!", "Let me know if...")
+- **Pattern 20:** Knowledge-cutoff disclaimers ("As of my last training...")
+- **Pattern 21:** Sycophantic tone ("Great question!", "You're absolutely right!")
+- **Pattern 25:** AI signatures in code ("// Generated by ChatGPT")
 
-### High (Strong AI Indicators)
+### High (strong AI indicators)
 Multiple occurrences strongly suggest AI:
-- **Pattern 1:** Significance Inflation ("testament", "pivotal moment", "evolving landscape")
-- **Pattern 7:** AI Vocabulary Words ("delve", "underscore", "tapestry", "interplay")
-- **Pattern 3:** Superficial -ing Analyses ("highlighting", "underscoring", "showcasing")
-- **Pattern 8:** Copula Avoidance ("serves as", "stands as", "functions as")
+- **Pattern 1:** Significance inflation ("testament", "pivotal moment", "evolving landscape")
+- **Pattern 7:** AI vocabulary words ("delve", "underscore", "tapestry", "interplay")
+- **Pattern 3:** Superficial -ing analyses ("highlighting", "underscoring", "showcasing")
+- **Pattern 8:** Copula avoidance ("serves as", "stands as", "functions as")
 
-### Medium (Moderate Signals)
+### Medium (moderate signals)
 Common in AI but also in some human writing:
-- **Pattern 13:** Em Dash Overuse
-- **Pattern 10:** Rule of Three
-- **Pattern 9:** Negative Parallelisms ("It's not just X; it's Y")
-- **Pattern 4:** Promotional Language ("nestled", "vibrant", "renowned")
+- **Pattern 13:** Em dash overuse
+- **Pattern 10:** Rule of three
+- **Pattern 9:** Negative parallelisms ("It's not just X; it's Y")
+- **Pattern 4:** Promotional language ("nestled", "vibrant", "renowned")
 
-### Low (Subtle Tells)
+### Low (subtle tells)
 Minor indicators, fix if other patterns present:
-- **Pattern 18:** Quotation Mark Issues
-- **Pattern 16:** Title Case in Headings
-- **Pattern 14:** Overuse of Boldface
+- **Pattern 18:** Quotation mark issues
+- **Pattern 16:** Title case in headings
+- **Pattern 14:** Overuse of boldface
 
 ---
 
@@ -637,8 +629,7 @@ Provide:
 
 This skill is based on [Wikipedia:Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing), maintained by WikiProject AI Cleanup. The patterns documented there come from observations of thousands of instances of AI-generated text on Wikipedia.
 
-Key insight from Wikipedia: "LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases."
-
+Key insight from Wikipedia: "LLMs use statistical algorithms to guess what should come next. The result tends toward the mostො statistically likely result that applies to the widest variety of cases."
 
 ## RESEARCH AND EXTERNAL SOURCES
 
diff --git a/adapters/antigravity-skill/SKILL.md b/adapters/antigravity-skill/SKILL.md
index 4b60eee..4f724c8 100644
--- a/adapters/antigravity-skill/SKILL.md
+++ b/adapters/antigravity-skill/SKILL.md
@@ -1,6 +1,16 @@
+---
+adapter_metadata:
+  skill_name: humanizer
+  skill_version: 2.2.1
+  last_synced: 2026-02-06
+  source_path: SKILL.md
+  adapter_id: antigravity-skill
+  adapter_format: Antigravity skill
+---
+
 ---
 name: humanizer
-version: 2.2.0
+version: 2.2.1
 description: |
   Remove signs of AI-generated writing from text. Use when editing or reviewing
   text to make it sound more natural and human-written. Based on Wikipedia's
@@ -31,15 +41,8 @@ When given text to humanize:
 3. **Preserve meaning** - Keep the core message intact
 4. **Maintain voice** - Match the intended tone (formal, casual, technical, etc.)
 5. **Add soul** - Don't just remove bad patterns; inject actual personality
-adapter_metadata:
-  skill_name: humanizer
-  skill_version: 2.2.0
-  last_synced: 2026-02-06
-  source_path: SKILL.md
-  adapter_id: antigravity-skill
-  adapter_format: Antigravity skill
----
 
+---
 
 ## PERSONALITY AND SOUL
 
@@ -56,17 +59,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ### How to add voice
 
-**Have opinions.** Don't just report facts - react to them. "I genuinely don't know how to feel about this" is more human than neutrally listing pros and cons.
-
-**Vary your rhythm.** Short punchy sentences. Then longer ones that take their time getting where they're going. Mix it up.
-
-**Acknowledge complexity.** Real humans have mixed feelings. "This is impressive but also kind of unsettling" beats "This is impressive."
-
-**Use "I" when it fits.** First person isn't unprofessional - it's honest. "I keep coming back to..." or "Here's what gets me..." signals a real person thinking.
-
-**Let some mess in.** Perfect structure feels algorithmic. Tangents, asides, and half-formed thoughts are human.
-
-**Be specific about feelings.** Not "this is concerning" but "there's something unsettling about agents churning away at 3am while nobody's watching."
+Have opinions and react to facts. Vary sentence rhythm with short and long lines. Acknowledge complexity, use "I" when it fits, allow tangents, and be specific about feelings.
 
 ### Before (clean but soulless)
 >
@@ -78,7 +71,6 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-
 ## CONTENT PATTERNS
 
 ### 1. Undue Emphasis on Significance, Legacy, and Broader Trends
@@ -245,7 +237,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ## STYLE PATTERNS
 
-### 13. Em Dash Overuse
+### 13. Em dash overuse
 
 **Problem:** LLMs use em dashes (—) more than humans, mimicking "punchy" sales writing.
 
@@ -257,7 +249,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 14. Overuse of Boldface
+### 14. Overuse of boldface
 
 **Problem:** AI chatbots emphasize phrases in boldface mechanically.
 
@@ -269,7 +261,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 15. Inline-Header Vertical Lists
+### 15. Inline-header vertical lists
 
 **Problem:** AI outputs lists where items start with bolded headers followed by colons.
 
@@ -284,7 +276,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 16. Title Case in Headings
+### 16. Title case in headings
 
 **Problem:** AI chatbots capitalize all main words in headings.
 
@@ -312,11 +304,11 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 18. Quotation Mark Issues
+### 18. Quotation mark issues
 
 **Problem:** AI models make two common quotation mistakes:
 1. Using curly quotes (“...”) instead of straight quotes ("...")
-2. Using single quotes ('...') as primary delimiters (from code training)
+2. Using single quotes ('...') as primary delimiters in prose (from code training)
 
 **Before:**
 > He said “the project is on track” but others disagreed.
@@ -330,7 +322,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ## COMMUNICATION PATTERNS
 
-### 19. Collaborative Communication Artifacts
+### 19. Collaborative communication artifacts
 
 **Words to watch:** I hope this helps, Of course!, Certainly!, You're absolutely right!, Would you like..., let me know, here is a...
 
@@ -344,7 +336,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 20. Knowledge-Cutoff Disclaimers
+### 20. Knowledge-cutoff disclaimers
 
 **Words to watch:** as of [date], Up to my last training update, While specific details are limited/scarce..., based on available information...
 
@@ -358,7 +350,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 21. Sycophantic/Servile Tone
+### 21. Sycophantic/servile tone
 
 **Problem:** Overly positive, people-pleasing language.
 
@@ -372,7 +364,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ## FILLER AND HEDGING
 
-### 22. Filler Phrases
+### 22. Filler phrases
 
 **Before → After:**
 
@@ -385,7 +377,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 23. Excessive Hedging
+### 23. Excessive hedging
 
 **Problem:** Over-qualifying statements.
 
@@ -397,7 +389,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 24. Generic Positive Conclusions
+### 24. Generic positive conclusions
 
 **Problem:** Vague upbeat endings.
 
@@ -409,7 +401,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 25. AI Signatures in Code
+### 25. AI signatures in code
 
 **Words to watch:** `// Generated by`, `Produced by`, `Created with [AI Model]`, `/* AI-generated */`, `// Here is the refactored code:`
 
@@ -435,7 +427,7 @@ function add(a, b) {
 
 ---
 
-### 26. Non-Text AI Patterns (Over-structuring)
+### 26. Non-text AI patterns (over-structuring)
 
 **Words to watch:** In summary, Table 1:, Breakdown:, Key takeaways: (when used with mechanical lists)
 
@@ -459,32 +451,32 @@ function add(a, b) {
 
 Patterns are ranked by how strongly they signal AI-generated text:
 
-### Critical (Immediate AI Detection)
+### Critical (immediate AI detection)
 These patterns alone can identify AI-generated text:
-- **Pattern 19:** Collaborative Communication Artifacts ("I hope this helps!", "Let me know if...")
-- **Pattern 20:** Knowledge-Cutoff Disclaimers ("As of my last training...")
-- **Pattern 21:** Sycophantic Tone ("Great question!", "You're absolutely right!")
-- **Pattern 25:** AI Signatures in Code ("// Generated by ChatGPT")
+- **Pattern 19:** Collaborative communication artifacts ("I hope this helps!", "Let me know if...")
+- **Pattern 20:** Knowledge-cutoff disclaimers ("As of my last training...")
+- **Pattern 21:** Sycophantic tone ("Great question!", "You're absolutely right!")
+- **Pattern 25:** AI signatures in code ("// Generated by ChatGPT")
 
-### High (Strong AI Indicators)
+### High (strong AI indicators)
 Multiple occurrences strongly suggest AI:
-- **Pattern 1:** Significance Inflation ("testament", "pivotal moment", "evolving landscape")
-- **Pattern 7:** AI Vocabulary Words ("delve", "underscore", "tapestry", "interplay")
-- **Pattern 3:** Superficial -ing Analyses ("highlighting", "underscoring", "showcasing")
-- **Pattern 8:** Copula Avoidance ("serves as", "stands as", "functions as")
+- **Pattern 1:** Significance inflation ("testament", "pivotal moment", "evolving landscape")
+- **Pattern 7:** AI vocabulary words ("delve", "underscore", "tapestry", "interplay")
+- **Pattern 3:** Superficial -ing analyses ("highlighting", "underscoring", "showcasing")
+- **Pattern 8:** Copula avoidance ("serves as", "stands as", "functions as")
 
-### Medium (Moderate Signals)
+### Medium (moderate signals)
 Common in AI but also in some human writing:
-- **Pattern 13:** Em Dash Overuse
-- **Pattern 10:** Rule of Three
-- **Pattern 9:** Negative Parallelisms ("It's not just X; it's Y")
-- **Pattern 4:** Promotional Language ("nestled", "vibrant", "renowned")
+- **Pattern 13:** Em dash overuse
+- **Pattern 10:** Rule of three
+- **Pattern 9:** Negative parallelisms ("It's not just X; it's Y")
+- **Pattern 4:** Promotional language ("nestled", "vibrant", "renowned")
 
-### Low (Subtle Tells)
+### Low (subtle tells)
 Minor indicators, fix if other patterns present:
-- **Pattern 18:** Quotation Mark Issues
-- **Pattern 16:** Title Case in Headings
-- **Pattern 14:** Overuse of Boldface
+- **Pattern 18:** Quotation mark issues
+- **Pattern 16:** Title case in headings
+- **Pattern 14:** Overuse of boldface
 
 ---
 
@@ -637,8 +629,7 @@ Provide:
 
 This skill is based on [Wikipedia:Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing), maintained by WikiProject AI Cleanup. The patterns documented there come from observations of thousands of instances of AI-generated text on Wikipedia.
 
-Key insight from Wikipedia: "LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases."
-
+Key insight from Wikipedia: "LLMs use statistical algorithms to guess what should come next. The result tends toward the mostො statistically likely result that applies to the widest variety of cases."
 
 ## RESEARCH AND EXTERNAL SOURCES
 
diff --git a/adapters/antigravity-skill/SKILL_PROFESSIONAL.md b/adapters/antigravity-skill/SKILL_PROFESSIONAL.md
index a38ff6a..b685474 100644
--- a/adapters/antigravity-skill/SKILL_PROFESSIONAL.md
+++ b/adapters/antigravity-skill/SKILL_PROFESSIONAL.md
@@ -1,6 +1,16 @@
+---
+adapter_metadata:
+  skill_name: humanizer-pro
+  skill_version: 2.2.1
+  last_synced: 2026-02-06
+  source_path: SKILL_PROFESSIONAL.md
+  adapter_id: antigravity-skill-pro
+  adapter_format: Antigravity skill
+---
+
 ---
 name: humanizer-pro
-version: 2.2.0
+version: 2.2.1
 description: |
   Remove signs of AI-generated writing from text. Use when editing or reviewing
   text to make it sound more natural, human-written, and professional. Based on Wikipedia's
@@ -31,15 +41,8 @@ When given text to humanize:
 3. **Preserve meaning** - Keep the core message intact
 4. **Maintain voice** - Match the intended tone (formal, casual, technical, etc.)
 5. **Refine voice** - Ensure writing is alive, specific, and professional
-adapter_metadata:
-  skill_name: humanizer-pro
-  skill_version: 2.2.0
-  last_synced: 2026-02-06
-  source_path: SKILL_PROFESSIONAL.md
-  adapter_id: antigravity-skill-pro
-  adapter_format: Antigravity skill
----
 
+---
 
 ## VOICE AND CRAFT
 
@@ -56,15 +59,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ### What to aim for
 
-**Rhythm.** Vary sentence length. Let a short sentence land after a longer one. This creates emphasis without bolding everything.
-
-**Specificity.** "The outage lasted 4 hours and affected 12,000 users" tells me something. "The outage had significant impact" tells me nothing.
-
-**A point of view.** This doesn't mean injecting opinions everywhere. It means the writing reflects that someone with knowledge made choices about what matters, what to include, what to skip. Even neutral writing can have perspective.
-
-**Earned emphasis.** If something is important, show me through detail. Don't just assert it.
-
-**Read it aloud.** If you stumble, the reader will too.
+Vary sentence rhythm by mixing short and long lines. Use specific details instead of vague assertions. Ensure the writing reflects a clear point of view and earned emphasis through detail. Always read it aloud to check for natural flow.
 
 ---
 
@@ -73,7 +68,6 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 ### Technical Nuance
 **Expertise isn't slop.** In professional contexts, "crucial" or "pivotal" are sometimes the exact right words for a technical requirement. The Pro variant targets *lazy* patterns, not technical precision. If a word is required for accuracy, keep it. If it's there to add fake "gravitas," cut it.
 
-
 ## CONTENT PATTERNS
 
 ### 1. Undue Emphasis on Significance, Legacy, and Broader Trends
@@ -240,7 +234,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ## STYLE PATTERNS
 
-### 13. Em Dash Overuse
+### 13. Em dash overuse
 
 **Problem:** LLMs use em dashes (—) more than humans, mimicking "punchy" sales writing.
 
@@ -252,7 +246,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ---
 
-### 14. Overuse of Boldface
+### 14. Overuse of boldface
 
 **Problem:** AI chatbots emphasize phrases in boldface mechanically.
 
@@ -264,7 +258,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ---
 
-### 15. Inline-Header Vertical Lists
+### 15. Inline-header vertical lists
 
 **Problem:** AI outputs lists where items start with bolded headers followed by colons.
 
@@ -279,7 +273,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ---
 
-### 16. Title Case in Headings
+### 16. Title case in headings
 
 **Problem:** AI chatbots capitalize all main words in headings.
 
@@ -307,11 +301,11 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ---
 
-### 18. Quotation Mark Issues
+### 18. Quotation mark issues
 
 **Problem:** AI models make two common quotation mistakes:
 1. Using curly quotes (“...”) instead of straight quotes ("...")
-2. Using single quotes ('...') as primary delimiters (from code training)
+2. Using single quotes ('...') as primary delimiters in prose (from code training)
 
 **Before:**
 > He said “the project is on track” but others disagreed.
@@ -325,7 +319,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ## COMMUNICATION PATTERNS
 
-### 19. Collaborative Communication Artifacts
+### 19. Collaborative communication artifacts
 
 **Words to watch:** I hope this helps, Of course!, Certainly!, You're absolutely right!, Would you like..., let me know, here is a...
 
@@ -339,7 +333,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ---
 
-### 20. Knowledge-Cutoff Disclaimers
+### 20. Knowledge-cutoff disclaimers
 
 **Words to watch:** as of [date], Up to my last training update, While specific details are limited/scarce..., based on available information...
 
@@ -353,7 +347,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ---
 
-### 21. Sycophantic/Servile Tone
+### 21. Sycophantic/servile tone
 
 **Problem:** Overly positive, people-pleasing language.
 
@@ -367,7 +361,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ## FILLER AND HEDGING
 
-### 22. Filler Phrases
+### 22. Filler phrases
 
 **Before → After:**
 
@@ -380,7 +374,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ---
 
-### 23. Excessive Hedging
+### 23. Excessive hedging
 
 **Problem:** Over-qualifying statements.
 
@@ -392,7 +386,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ---
 
-### 24. Generic Positive Conclusions
+### 24. Generic positive conclusions
 
 **Problem:** Vague upbeat endings.
 
@@ -404,7 +398,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ---
 
-### 25. AI Signatures in Code
+### 25. AI signatures in code
 
 **Words to watch:** `// Generated by`, `Produced by`, `Created with [AI Model]`, `/* AI-generated */`, `// Here is the refactored code:`
 
@@ -430,7 +424,7 @@ function add(a, b) {
 
 ---
 
-### 26. Non-Text AI Patterns (Over-structuring)
+### 26. Non-text AI patterns (over-structuring)
 
 **Words to watch:** In summary, Table 1:, Breakdown:, Key takeaways: (when used with mechanical lists)
 
@@ -454,32 +448,32 @@ function add(a, b) {
 
 Patterns are ranked by how strongly they signal AI-generated text:
 
-### Critical (Immediate AI Detection)
+### Critical (immediate AI detection)
 These patterns alone can identify AI-generated text:
-- **Pattern 19:** Collaborative Communication Artifacts ("I hope this helps!", "Let me know if...")
-- **Pattern 20:** Knowledge-Cutoff Disclaimers ("As of my last training...")
-- **Pattern 21:** Sycophantic Tone ("Great question!", "You're absolutely right!")
-- **Pattern 25:** AI Signatures in Code ("// Generated by ChatGPT")
+- **Pattern 19:** Collaborative communication artifacts ("I hope this helps!", "Let me know if...")
+- **Pattern 20:** Knowledge-cutoff disclaimers ("As of my last training...")
+- **Pattern 21:** Sycophantic tone ("Great question!", "You're absolutely right!")
+- **Pattern 25:** AI signatures in code ("// Generated by ChatGPT")
 
-### High (Strong AI Indicators)
+### High (strong AI indicators)
 Multiple occurrences strongly suggest AI:
-- **Pattern 1:** Significance Inflation ("testament", "pivotal moment", "evolving landscape")
-- **Pattern 7:** AI Vocabulary Words ("delve", "underscore", "tapestry", "interplay")
-- **Pattern 3:** Superficial -ing Analyses ("highlighting", "underscoring", "showcasing")
-- **Pattern 8:** Copula Avoidance ("serves as", "stands as", "functions as")
+- **Pattern 1:** Significance inflation ("testament", "pivotal moment", "evolving landscape")
+- **Pattern 7:** AI vocabulary words ("delve", "underscore", "tapestry", "interplay")
+- **Pattern 3:** Superficial -ing analyses ("highlighting", "underscoring", "showcasing")
+- **Pattern 8:** Copula avoidance ("serves as", "stands as", "functions as")
 
-### Medium (Moderate Signals)
+### Medium (moderate signals)
 Common in AI but also in some human writing:
-- **Pattern 13:** Em Dash Overuse
-- **Pattern 10:** Rule of Three
-- **Pattern 9:** Negative Parallelisms ("It's not just X; it's Y")
-- **Pattern 4:** Promotional Language ("nestled", "vibrant", "renowned")
+- **Pattern 13:** Em dash overuse
+- **Pattern 10:** Rule of three
+- **Pattern 9:** Negative parallelisms ("It's not just X; it's Y")
+- **Pattern 4:** Promotional language ("nestled", "vibrant", "renowned")
 
-### Low (Subtle Tells)
+### Low (subtle tells)
 Minor indicators, fix if other patterns present:
-- **Pattern 18:** Quotation Mark Issues
-- **Pattern 16:** Title Case in Headings
-- **Pattern 14:** Overuse of Boldface
+- **Pattern 18:** Quotation mark issues
+- **Pattern 16:** Title case in headings
+- **Pattern 14:** Overuse of boldface
 
 ---
 
@@ -632,8 +626,7 @@ Provide:
 
 This skill is based on [Wikipedia:Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing), maintained by WikiProject AI Cleanup. The patterns documented there come from observations of thousands of instances of AI-generated text on Wikipedia.
 
-Key insight from Wikipedia: "LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases."
-
+Key insight from Wikipedia: "LLMs use statistical algorithms to guess what should come next. The result tends toward the mostො statistically likely result that applies to the widest variety of cases."
 
 ## RESEARCH AND EXTERNAL SOURCES
 
diff --git a/adapters/copilot/COPILOT.md b/adapters/copilot/COPILOT.md
index 2602d6e..2bafb12 100644
--- a/adapters/copilot/COPILOT.md
+++ b/adapters/copilot/COPILOT.md
@@ -1,6 +1,16 @@
+---
+adapter_metadata:
+  skill_name: humanizer
+  skill_version: 2.2.1
+  last_synced: 2026-02-06
+  source_path: SKILL.md
+  adapter_id: copilot
+  adapter_format: Copilot instructions
+---
+
 ---
 name: humanizer
-version: 2.2.0
+version: 2.2.1
 description: |
   Remove signs of AI-generated writing from text. Use when editing or reviewing
   text to make it sound more natural and human-written. Based on Wikipedia's
@@ -31,15 +41,8 @@ When given text to humanize:
 3. **Preserve meaning** - Keep the core message intact
 4. **Maintain voice** - Match the intended tone (formal, casual, technical, etc.)
 5. **Add soul** - Don't just remove bad patterns; inject actual personality
-adapter_metadata:
-  skill_name: humanizer
-  skill_version: 2.2.0
-  last_synced: 2026-02-06
-  source_path: SKILL.md
-  adapter_id: copilot
-  adapter_format: Copilot instructions
----
 
+---
 
 ## PERSONALITY AND SOUL
 
@@ -56,17 +59,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ### How to add voice
 
-**Have opinions.** Don't just report facts - react to them. "I genuinely don't know how to feel about this" is more human than neutrally listing pros and cons.
-
-**Vary your rhythm.** Short punchy sentences. Then longer ones that take their time getting where they're going. Mix it up.
-
-**Acknowledge complexity.** Real humans have mixed feelings. "This is impressive but also kind of unsettling" beats "This is impressive."
-
-**Use "I" when it fits.** First person isn't unprofessional - it's honest. "I keep coming back to..." or "Here's what gets me..." signals a real person thinking.
-
-**Let some mess in.** Perfect structure feels algorithmic. Tangents, asides, and half-formed thoughts are human.
-
-**Be specific about feelings.** Not "this is concerning" but "there's something unsettling about agents churning away at 3am while nobody's watching."
+Have opinions and react to facts. Vary sentence rhythm with short and long lines. Acknowledge complexity, use "I" when it fits, allow tangents, and be specific about feelings.
 
 ### Before (clean but soulless)
 >
@@ -78,7 +71,6 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-
 ## CONTENT PATTERNS
 
 ### 1. Undue Emphasis on Significance, Legacy, and Broader Trends
@@ -245,7 +237,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ## STYLE PATTERNS
 
-### 13. Em Dash Overuse
+### 13. Em dash overuse
 
 **Problem:** LLMs use em dashes (—) more than humans, mimicking "punchy" sales writing.
 
@@ -257,7 +249,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 14. Overuse of Boldface
+### 14. Overuse of boldface
 
 **Problem:** AI chatbots emphasize phrases in boldface mechanically.
 
@@ -269,7 +261,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 15. Inline-Header Vertical Lists
+### 15. Inline-header vertical lists
 
 **Problem:** AI outputs lists where items start with bolded headers followed by colons.
 
@@ -284,7 +276,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 16. Title Case in Headings
+### 16. Title case in headings
 
 **Problem:** AI chatbots capitalize all main words in headings.
 
@@ -312,11 +304,11 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 18. Quotation Mark Issues
+### 18. Quotation mark issues
 
 **Problem:** AI models make two common quotation mistakes:
 1. Using curly quotes (“...”) instead of straight quotes ("...")
-2. Using single quotes ('...') as primary delimiters (from code training)
+2. Using single quotes ('...') as primary delimiters in prose (from code training)
 
 **Before:**
 > He said “the project is on track” but others disagreed.
@@ -330,7 +322,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ## COMMUNICATION PATTERNS
 
-### 19. Collaborative Communication Artifacts
+### 19. Collaborative communication artifacts
 
 **Words to watch:** I hope this helps, Of course!, Certainly!, You're absolutely right!, Would you like..., let me know, here is a...
 
@@ -344,7 +336,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 20. Knowledge-Cutoff Disclaimers
+### 20. Knowledge-cutoff disclaimers
 
 **Words to watch:** as of [date], Up to my last training update, While specific details are limited/scarce..., based on available information...
 
@@ -358,7 +350,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 21. Sycophantic/Servile Tone
+### 21. Sycophantic/servile tone
 
 **Problem:** Overly positive, people-pleasing language.
 
@@ -372,7 +364,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ## FILLER AND HEDGING
 
-### 22. Filler Phrases
+### 22. Filler phrases
 
 **Before → After:**
 
@@ -385,7 +377,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 23. Excessive Hedging
+### 23. Excessive hedging
 
 **Problem:** Over-qualifying statements.
 
@@ -397,7 +389,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 24. Generic Positive Conclusions
+### 24. Generic positive conclusions
 
 **Problem:** Vague upbeat endings.
 
@@ -409,7 +401,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 25. AI Signatures in Code
+### 25. AI signatures in code
 
 **Words to watch:** `// Generated by`, `Produced by`, `Created with [AI Model]`, `/* AI-generated */`, `// Here is the refactored code:`
 
@@ -435,7 +427,7 @@ function add(a, b) {
 
 ---
 
-### 26. Non-Text AI Patterns (Over-structuring)
+### 26. Non-text AI patterns (over-structuring)
 
 **Words to watch:** In summary, Table 1:, Breakdown:, Key takeaways: (when used with mechanical lists)
 
@@ -459,32 +451,32 @@ function add(a, b) {
 
 Patterns are ranked by how strongly they signal AI-generated text:
 
-### Critical (Immediate AI Detection)
+### Critical (immediate AI detection)
 These patterns alone can identify AI-generated text:
-- **Pattern 19:** Collaborative Communication Artifacts ("I hope this helps!", "Let me know if...")
-- **Pattern 20:** Knowledge-Cutoff Disclaimers ("As of my last training...")
-- **Pattern 21:** Sycophantic Tone ("Great question!", "You're absolutely right!")
-- **Pattern 25:** AI Signatures in Code ("// Generated by ChatGPT")
+- **Pattern 19:** Collaborative communication artifacts ("I hope this helps!", "Let me know if...")
+- **Pattern 20:** Knowledge-cutoff disclaimers ("As of my last training...")
+- **Pattern 21:** Sycophantic tone ("Great question!", "You're absolutely right!")
+- **Pattern 25:** AI signatures in code ("// Generated by ChatGPT")
 
-### High (Strong AI Indicators)
+### High (strong AI indicators)
 Multiple occurrences strongly suggest AI:
-- **Pattern 1:** Significance Inflation ("testament", "pivotal moment", "evolving landscape")
-- **Pattern 7:** AI Vocabulary Words ("delve", "underscore", "tapestry", "interplay")
-- **Pattern 3:** Superficial -ing Analyses ("highlighting", "underscoring", "showcasing")
-- **Pattern 8:** Copula Avoidance ("serves as", "stands as", "functions as")
+- **Pattern 1:** Significance inflation ("testament", "pivotal moment", "evolving landscape")
+- **Pattern 7:** AI vocabulary words ("delve", "underscore", "tapestry", "interplay")
+- **Pattern 3:** Superficial -ing analyses ("highlighting", "underscoring", "showcasing")
+- **Pattern 8:** Copula avoidance ("serves as", "stands as", "functions as")
 
-### Medium (Moderate Signals)
+### Medium (moderate signals)
 Common in AI but also in some human writing:
-- **Pattern 13:** Em Dash Overuse
-- **Pattern 10:** Rule of Three
-- **Pattern 9:** Negative Parallelisms ("It's not just X; it's Y")
-- **Pattern 4:** Promotional Language ("nestled", "vibrant", "renowned")
+- **Pattern 13:** Em dash overuse
+- **Pattern 10:** Rule of three
+- **Pattern 9:** Negative parallelisms ("It's not just X; it's Y")
+- **Pattern 4:** Promotional language ("nestled", "vibrant", "renowned")
 
-### Low (Subtle Tells)
+### Low (subtle tells)
 Minor indicators, fix if other patterns present:
-- **Pattern 18:** Quotation Mark Issues
-- **Pattern 16:** Title Case in Headings
-- **Pattern 14:** Overuse of Boldface
+- **Pattern 18:** Quotation mark issues
+- **Pattern 16:** Title case in headings
+- **Pattern 14:** Overuse of boldface
 
 ---
 
@@ -637,8 +629,7 @@ Provide:
 
 This skill is based on [Wikipedia:Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing), maintained by WikiProject AI Cleanup. The patterns documented there come from observations of thousands of instances of AI-generated text on Wikipedia.
 
-Key insight from Wikipedia: "LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases."
-
+Key insight from Wikipedia: "LLMs use statistical algorithms to guess what should come next. The result tends toward the mostො statistically likely result that applies to the widest variety of cases."
 
 ## RESEARCH AND EXTERNAL SOURCES
 
diff --git a/adapters/gemini-extension/GEMINI.md b/adapters/gemini-extension/GEMINI.md
index 72a6356..f0a73ef 100644
--- a/adapters/gemini-extension/GEMINI.md
+++ b/adapters/gemini-extension/GEMINI.md
@@ -1,6 +1,16 @@
+---
+adapter_metadata:
+  skill_name: humanizer
+  skill_version: 2.2.1
+  last_synced: 2026-02-06
+  source_path: SKILL.md
+  adapter_id: gemini-extension
+  adapter_format: Gemini extension
+---
+
 ---
 name: humanizer
-version: 2.2.0
+version: 2.2.1
 description: |
   Remove signs of AI-generated writing from text. Use when editing or reviewing
   text to make it sound more natural and human-written. Based on Wikipedia's
@@ -31,15 +41,8 @@ When given text to humanize:
 3. **Preserve meaning** - Keep the core message intact
 4. **Maintain voice** - Match the intended tone (formal, casual, technical, etc.)
 5. **Add soul** - Don't just remove bad patterns; inject actual personality
-adapter_metadata:
-  skill_name: humanizer
-  skill_version: 2.2.0
-  last_synced: 2026-02-06
-  source_path: SKILL.md
-  adapter_id: gemini-extension
-  adapter_format: Gemini extension
----
 
+---
 
 ## PERSONALITY AND SOUL
 
@@ -56,17 +59,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ### How to add voice
 
-**Have opinions.** Don't just report facts - react to them. "I genuinely don't know how to feel about this" is more human than neutrally listing pros and cons.
-
-**Vary your rhythm.** Short punchy sentences. Then longer ones that take their time getting where they're going. Mix it up.
-
-**Acknowledge complexity.** Real humans have mixed feelings. "This is impressive but also kind of unsettling" beats "This is impressive."
-
-**Use "I" when it fits.** First person isn't unprofessional - it's honest. "I keep coming back to..." or "Here's what gets me..." signals a real person thinking.
-
-**Let some mess in.** Perfect structure feels algorithmic. Tangents, asides, and half-formed thoughts are human.
-
-**Be specific about feelings.** Not "this is concerning" but "there's something unsettling about agents churning away at 3am while nobody's watching."
+Have opinions and react to facts. Vary sentence rhythm with short and long lines. Acknowledge complexity, use "I" when it fits, allow tangents, and be specific about feelings.
 
 ### Before (clean but soulless)
 >
@@ -78,7 +71,6 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-
 ## CONTENT PATTERNS
 
 ### 1. Undue Emphasis on Significance, Legacy, and Broader Trends
@@ -245,7 +237,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ## STYLE PATTERNS
 
-### 13. Em Dash Overuse
+### 13. Em dash overuse
 
 **Problem:** LLMs use em dashes (—) more than humans, mimicking "punchy" sales writing.
 
@@ -257,7 +249,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 14. Overuse of Boldface
+### 14. Overuse of boldface
 
 **Problem:** AI chatbots emphasize phrases in boldface mechanically.
 
@@ -269,7 +261,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 15. Inline-Header Vertical Lists
+### 15. Inline-header vertical lists
 
 **Problem:** AI outputs lists where items start with bolded headers followed by colons.
 
@@ -284,7 +276,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 16. Title Case in Headings
+### 16. Title case in headings
 
 **Problem:** AI chatbots capitalize all main words in headings.
 
@@ -312,11 +304,11 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 18. Quotation Mark Issues
+### 18. Quotation mark issues
 
 **Problem:** AI models make two common quotation mistakes:
 1. Using curly quotes (“...”) instead of straight quotes ("...")
-2. Using single quotes ('...') as primary delimiters (from code training)
+2. Using single quotes ('...') as primary delimiters in prose (from code training)
 
 **Before:**
 > He said “the project is on track” but others disagreed.
@@ -330,7 +322,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ## COMMUNICATION PATTERNS
 
-### 19. Collaborative Communication Artifacts
+### 19. Collaborative communication artifacts
 
 **Words to watch:** I hope this helps, Of course!, Certainly!, You're absolutely right!, Would you like..., let me know, here is a...
 
@@ -344,7 +336,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 20. Knowledge-Cutoff Disclaimers
+### 20. Knowledge-cutoff disclaimers
 
 **Words to watch:** as of [date], Up to my last training update, While specific details are limited/scarce..., based on available information...
 
@@ -358,7 +350,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 21. Sycophantic/Servile Tone
+### 21. Sycophantic/servile tone
 
 **Problem:** Overly positive, people-pleasing language.
 
@@ -372,7 +364,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ## FILLER AND HEDGING
 
-### 22. Filler Phrases
+### 22. Filler phrases
 
 **Before → After:**
 
@@ -385,7 +377,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 23. Excessive Hedging
+### 23. Excessive hedging
 
 **Problem:** Over-qualifying statements.
 
@@ -397,7 +389,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 24. Generic Positive Conclusions
+### 24. Generic positive conclusions
 
 **Problem:** Vague upbeat endings.
 
@@ -409,7 +401,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 25. AI Signatures in Code
+### 25. AI signatures in code
 
 **Words to watch:** `// Generated by`, `Produced by`, `Created with [AI Model]`, `/* AI-generated */`, `// Here is the refactored code:`
 
@@ -435,7 +427,7 @@ function add(a, b) {
 
 ---
 
-### 26. Non-Text AI Patterns (Over-structuring)
+### 26. Non-text AI patterns (over-structuring)
 
 **Words to watch:** In summary, Table 1:, Breakdown:, Key takeaways: (when used with mechanical lists)
 
@@ -459,32 +451,32 @@ function add(a, b) {
 
 Patterns are ranked by how strongly they signal AI-generated text:
 
-### Critical (Immediate AI Detection)
+### Critical (immediate AI detection)
 These patterns alone can identify AI-generated text:
-- **Pattern 19:** Collaborative Communication Artifacts ("I hope this helps!", "Let me know if...")
-- **Pattern 20:** Knowledge-Cutoff Disclaimers ("As of my last training...")
-- **Pattern 21:** Sycophantic Tone ("Great question!", "You're absolutely right!")
-- **Pattern 25:** AI Signatures in Code ("// Generated by ChatGPT")
+- **Pattern 19:** Collaborative communication artifacts ("I hope this helps!", "Let me know if...")
+- **Pattern 20:** Knowledge-cutoff disclaimers ("As of my last training...")
+- **Pattern 21:** Sycophantic tone ("Great question!", "You're absolutely right!")
+- **Pattern 25:** AI signatures in code ("// Generated by ChatGPT")
 
-### High (Strong AI Indicators)
+### High (strong AI indicators)
 Multiple occurrences strongly suggest AI:
-- **Pattern 1:** Significance Inflation ("testament", "pivotal moment", "evolving landscape")
-- **Pattern 7:** AI Vocabulary Words ("delve", "underscore", "tapestry", "interplay")
-- **Pattern 3:** Superficial -ing Analyses ("highlighting", "underscoring", "showcasing")
-- **Pattern 8:** Copula Avoidance ("serves as", "stands as", "functions as")
+- **Pattern 1:** Significance inflation ("testament", "pivotal moment", "evolving landscape")
+- **Pattern 7:** AI vocabulary words ("delve", "underscore", "tapestry", "interplay")
+- **Pattern 3:** Superficial -ing analyses ("highlighting", "underscoring", "showcasing")
+- **Pattern 8:** Copula avoidance ("serves as", "stands as", "functions as")
 
-### Medium (Moderate Signals)
+### Medium (moderate signals)
 Common in AI but also in some human writing:
-- **Pattern 13:** Em Dash Overuse
-- **Pattern 10:** Rule of Three
-- **Pattern 9:** Negative Parallelisms ("It's not just X; it's Y")
-- **Pattern 4:** Promotional Language ("nestled", "vibrant", "renowned")
+- **Pattern 13:** Em dash overuse
+- **Pattern 10:** Rule of three
+- **Pattern 9:** Negative parallelisms ("It's not just X; it's Y")
+- **Pattern 4:** Promotional language ("nestled", "vibrant", "renowned")
 
-### Low (Subtle Tells)
+### Low (subtle tells)
 Minor indicators, fix if other patterns present:
-- **Pattern 18:** Quotation Mark Issues
-- **Pattern 16:** Title Case in Headings
-- **Pattern 14:** Overuse of Boldface
+- **Pattern 18:** Quotation mark issues
+- **Pattern 16:** Title case in headings
+- **Pattern 14:** Overuse of boldface
 
 ---
 
@@ -637,8 +629,7 @@ Provide:
 
 This skill is based on [Wikipedia:Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing), maintained by WikiProject AI Cleanup. The patterns documented there come from observations of thousands of instances of AI-generated text on Wikipedia.
 
-Key insight from Wikipedia: "LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases."
-
+Key insight from Wikipedia: "LLMs use statistical algorithms to guess what should come next. The result tends toward the mostො statistically likely result that applies to the widest variety of cases."
 
 ## RESEARCH AND EXTERNAL SOURCES
 
diff --git a/adapters/gemini-extension/GEMINI_PRO.md b/adapters/gemini-extension/GEMINI_PRO.md
index 2f08318..3ed5e00 100644
--- a/adapters/gemini-extension/GEMINI_PRO.md
+++ b/adapters/gemini-extension/GEMINI_PRO.md
@@ -1,6 +1,16 @@
+---
+adapter_metadata:
+  skill_name: humanizer-pro
+  skill_version: 2.2.1
+  last_synced: 2026-02-06
+  source_path: SKILL_PROFESSIONAL.md
+  adapter_id: gemini-extension-pro
+  adapter_format: Gemini extension
+---
+
 ---
 name: humanizer-pro
-version: 2.2.0
+version: 2.2.1
 description: |
   Remove signs of AI-generated writing from text. Use when editing or reviewing
   text to make it sound more natural, human-written, and professional. Based on Wikipedia's
@@ -31,15 +41,8 @@ When given text to humanize:
 3. **Preserve meaning** - Keep the core message intact
 4. **Maintain voice** - Match the intended tone (formal, casual, technical, etc.)
 5. **Refine voice** - Ensure writing is alive, specific, and professional
-adapter_metadata:
-  skill_name: humanizer-pro
-  skill_version: 2.2.0
-  last_synced: 2026-02-06
-  source_path: SKILL_PROFESSIONAL.md
-  adapter_id: gemini-extension-pro
-  adapter_format: Gemini extension
----
 
+---
 
 ## VOICE AND CRAFT
 
@@ -56,15 +59,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ### What to aim for
 
-**Rhythm.** Vary sentence length. Let a short sentence land after a longer one. This creates emphasis without bolding everything.
-
-**Specificity.** "The outage lasted 4 hours and affected 12,000 users" tells me something. "The outage had significant impact" tells me nothing.
-
-**A point of view.** This doesn't mean injecting opinions everywhere. It means the writing reflects that someone with knowledge made choices about what matters, what to include, what to skip. Even neutral writing can have perspective.
-
-**Earned emphasis.** If something is important, show me through detail. Don't just assert it.
-
-**Read it aloud.** If you stumble, the reader will too.
+Vary sentence rhythm by mixing short and long lines. Use specific details instead of vague assertions. Ensure the writing reflects a clear point of view and earned emphasis through detail. Always read it aloud to check for natural flow.
 
 ---
 
@@ -73,7 +68,6 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 ### Technical Nuance
 **Expertise isn't slop.** In professional contexts, "crucial" or "pivotal" are sometimes the exact right words for a technical requirement. The Pro variant targets *lazy* patterns, not technical precision. If a word is required for accuracy, keep it. If it's there to add fake "gravitas," cut it.
 
-
 ## CONTENT PATTERNS
 
 ### 1. Undue Emphasis on Significance, Legacy, and Broader Trends
@@ -240,7 +234,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ## STYLE PATTERNS
 
-### 13. Em Dash Overuse
+### 13. Em dash overuse
 
 **Problem:** LLMs use em dashes (—) more than humans, mimicking "punchy" sales writing.
 
@@ -252,7 +246,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ---
 
-### 14. Overuse of Boldface
+### 14. Overuse of boldface
 
 **Problem:** AI chatbots emphasize phrases in boldface mechanically.
 
@@ -264,7 +258,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ---
 
-### 15. Inline-Header Vertical Lists
+### 15. Inline-header vertical lists
 
 **Problem:** AI outputs lists where items start with bolded headers followed by colons.
 
@@ -279,7 +273,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ---
 
-### 16. Title Case in Headings
+### 16. Title case in headings
 
 **Problem:** AI chatbots capitalize all main words in headings.
 
@@ -307,11 +301,11 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ---
 
-### 18. Quotation Mark Issues
+### 18. Quotation mark issues
 
 **Problem:** AI models make two common quotation mistakes:
 1. Using curly quotes (“...”) instead of straight quotes ("...")
-2. Using single quotes ('...') as primary delimiters (from code training)
+2. Using single quotes ('...') as primary delimiters in prose (from code training)
 
 **Before:**
 > He said “the project is on track” but others disagreed.
@@ -325,7 +319,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ## COMMUNICATION PATTERNS
 
-### 19. Collaborative Communication Artifacts
+### 19. Collaborative communication artifacts
 
 **Words to watch:** I hope this helps, Of course!, Certainly!, You're absolutely right!, Would you like..., let me know, here is a...
 
@@ -339,7 +333,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ---
 
-### 20. Knowledge-Cutoff Disclaimers
+### 20. Knowledge-cutoff disclaimers
 
 **Words to watch:** as of [date], Up to my last training update, While specific details are limited/scarce..., based on available information...
 
@@ -353,7 +347,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ---
 
-### 21. Sycophantic/Servile Tone
+### 21. Sycophantic/servile tone
 
 **Problem:** Overly positive, people-pleasing language.
 
@@ -367,7 +361,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ## FILLER AND HEDGING
 
-### 22. Filler Phrases
+### 22. Filler phrases
 
 **Before → After:**
 
@@ -380,7 +374,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ---
 
-### 23. Excessive Hedging
+### 23. Excessive hedging
 
 **Problem:** Over-qualifying statements.
 
@@ -392,7 +386,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ---
 
-### 24. Generic Positive Conclusions
+### 24. Generic positive conclusions
 
 **Problem:** Vague upbeat endings.
 
@@ -404,7 +398,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ---
 
-### 25. AI Signatures in Code
+### 25. AI signatures in code
 
 **Words to watch:** `// Generated by`, `Produced by`, `Created with [AI Model]`, `/* AI-generated */`, `// Here is the refactored code:`
 
@@ -430,7 +424,7 @@ function add(a, b) {
 
 ---
 
-### 26. Non-Text AI Patterns (Over-structuring)
+### 26. Non-text AI patterns (over-structuring)
 
 **Words to watch:** In summary, Table 1:, Breakdown:, Key takeaways: (when used with mechanical lists)
 
@@ -454,32 +448,32 @@ function add(a, b) {
 
 Patterns are ranked by how strongly they signal AI-generated text:
 
-### Critical (Immediate AI Detection)
+### Critical (immediate AI detection)
 These patterns alone can identify AI-generated text:
-- **Pattern 19:** Collaborative Communication Artifacts ("I hope this helps!", "Let me know if...")
-- **Pattern 20:** Knowledge-Cutoff Disclaimers ("As of my last training...")
-- **Pattern 21:** Sycophantic Tone ("Great question!", "You're absolutely right!")
-- **Pattern 25:** AI Signatures in Code ("// Generated by ChatGPT")
+- **Pattern 19:** Collaborative communication artifacts ("I hope this helps!", "Let me know if...")
+- **Pattern 20:** Knowledge-cutoff disclaimers ("As of my last training...")
+- **Pattern 21:** Sycophantic tone ("Great question!", "You're absolutely right!")
+- **Pattern 25:** AI signatures in code ("// Generated by ChatGPT")
 
-### High (Strong AI Indicators)
+### High (strong AI indicators)
 Multiple occurrences strongly suggest AI:
-- **Pattern 1:** Significance Inflation ("testament", "pivotal moment", "evolving landscape")
-- **Pattern 7:** AI Vocabulary Words ("delve", "underscore", "tapestry", "interplay")
-- **Pattern 3:** Superficial -ing Analyses ("highlighting", "underscoring", "showcasing")
-- **Pattern 8:** Copula Avoidance ("serves as", "stands as", "functions as")
+- **Pattern 1:** Significance inflation ("testament", "pivotal moment", "evolving landscape")
+- **Pattern 7:** AI vocabulary words ("delve", "underscore", "tapestry", "interplay")
+- **Pattern 3:** Superficial -ing analyses ("highlighting", "underscoring", "showcasing")
+- **Pattern 8:** Copula avoidance ("serves as", "stands as", "functions as")
 
-### Medium (Moderate Signals)
+### Medium (moderate signals)
 Common in AI but also in some human writing:
-- **Pattern 13:** Em Dash Overuse
-- **Pattern 10:** Rule of Three
-- **Pattern 9:** Negative Parallelisms ("It's not just X; it's Y")
-- **Pattern 4:** Promotional Language ("nestled", "vibrant", "renowned")
+- **Pattern 13:** Em dash overuse
+- **Pattern 10:** Rule of three
+- **Pattern 9:** Negative parallelisms ("It's not just X; it's Y")
+- **Pattern 4:** Promotional language ("nestled", "vibrant", "renowned")
 
-### Low (Subtle Tells)
+### Low (subtle tells)
 Minor indicators, fix if other patterns present:
-- **Pattern 18:** Quotation Mark Issues
-- **Pattern 16:** Title Case in Headings
-- **Pattern 14:** Overuse of Boldface
+- **Pattern 18:** Quotation mark issues
+- **Pattern 16:** Title case in headings
+- **Pattern 14:** Overuse of boldface
 
 ---
 
@@ -632,8 +626,7 @@ Provide:
 
 This skill is based on [Wikipedia:Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing), maintained by WikiProject AI Cleanup. The patterns documented there come from observations of thousands of instances of AI-generated text on Wikipedia.
 
-Key insight from Wikipedia: "LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases."
-
+Key insight from Wikipedia: "LLMs use statistical algorithms to guess what should come next. The result tends toward the mostො statistically likely result that applies to the widest variety of cases."
 
 ## RESEARCH AND EXTERNAL SOURCES
 
diff --git a/adapters/qwen-cli/QWEN.md b/adapters/qwen-cli/QWEN.md
index ea7a99c..97fa35f 100644
--- a/adapters/qwen-cli/QWEN.md
+++ b/adapters/qwen-cli/QWEN.md
@@ -1,6 +1,16 @@
+---
+adapter_metadata:
+  skill_name: humanizer
+  skill_version: 2.2.1
+  last_synced: 2026-02-06
+  source_path: SKILL.md
+  adapter_id: qwen-cli
+  adapter_format: Qwen CLI context
+---
+
 ---
 name: humanizer
-version: 2.2.0
+version: 2.2.1
 description: |
   Remove signs of AI-generated writing from text. Use when editing or reviewing
   text to make it sound more natural and human-written. Based on Wikipedia's
@@ -31,15 +41,8 @@ When given text to humanize:
 3. **Preserve meaning** - Keep the core message intact
 4. **Maintain voice** - Match the intended tone (formal, casual, technical, etc.)
 5. **Add soul** - Don't just remove bad patterns; inject actual personality
-adapter_metadata:
-  skill_name: humanizer
-  skill_version: 2.2.0
-  last_synced: 2026-02-06
-  source_path: SKILL.md
-  adapter_id: qwen-cli
-  adapter_format: Qwen CLI context
----
 
+---
 
 ## PERSONALITY AND SOUL
 
@@ -56,17 +59,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ### How to add voice
 
-**Have opinions.** Don't just report facts - react to them. "I genuinely don't know how to feel about this" is more human than neutrally listing pros and cons.
-
-**Vary your rhythm.** Short punchy sentences. Then longer ones that take their time getting where they're going. Mix it up.
-
-**Acknowledge complexity.** Real humans have mixed feelings. "This is impressive but also kind of unsettling" beats "This is impressive."
-
-**Use "I" when it fits.** First person isn't unprofessional - it's honest. "I keep coming back to..." or "Here's what gets me..." signals a real person thinking.
-
-**Let some mess in.** Perfect structure feels algorithmic. Tangents, asides, and half-formed thoughts are human.
-
-**Be specific about feelings.** Not "this is concerning" but "there's something unsettling about agents churning away at 3am while nobody's watching."
+Have opinions and react to facts. Vary sentence rhythm with short and long lines. Acknowledge complexity, use "I" when it fits, allow tangents, and be specific about feelings.
 
 ### Before (clean but soulless)
 >
@@ -78,7 +71,6 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-
 ## CONTENT PATTERNS
 
 ### 1. Undue Emphasis on Significance, Legacy, and Broader Trends
@@ -245,7 +237,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ## STYLE PATTERNS
 
-### 13. Em Dash Overuse
+### 13. Em dash overuse
 
 **Problem:** LLMs use em dashes (—) more than humans, mimicking "punchy" sales writing.
 
@@ -257,7 +249,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 14. Overuse of Boldface
+### 14. Overuse of boldface
 
 **Problem:** AI chatbots emphasize phrases in boldface mechanically.
 
@@ -269,7 +261,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 15. Inline-Header Vertical Lists
+### 15. Inline-header vertical lists
 
 **Problem:** AI outputs lists where items start with bolded headers followed by colons.
 
@@ -284,7 +276,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 16. Title Case in Headings
+### 16. Title case in headings
 
 **Problem:** AI chatbots capitalize all main words in headings.
 
@@ -312,11 +304,11 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 18. Quotation Mark Issues
+### 18. Quotation mark issues
 
 **Problem:** AI models make two common quotation mistakes:
 1. Using curly quotes (“...”) instead of straight quotes ("...")
-2. Using single quotes ('...') as primary delimiters (from code training)
+2. Using single quotes ('...') as primary delimiters in prose (from code training)
 
 **Before:**
 > He said “the project is on track” but others disagreed.
@@ -330,7 +322,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ## COMMUNICATION PATTERNS
 
-### 19. Collaborative Communication Artifacts
+### 19. Collaborative communication artifacts
 
 **Words to watch:** I hope this helps, Of course!, Certainly!, You're absolutely right!, Would you like..., let me know, here is a...
 
@@ -344,7 +336,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 20. Knowledge-Cutoff Disclaimers
+### 20. Knowledge-cutoff disclaimers
 
 **Words to watch:** as of [date], Up to my last training update, While specific details are limited/scarce..., based on available information...
 
@@ -358,7 +350,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 21. Sycophantic/Servile Tone
+### 21. Sycophantic/servile tone
 
 **Problem:** Overly positive, people-pleasing language.
 
@@ -372,7 +364,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ## FILLER AND HEDGING
 
-### 22. Filler Phrases
+### 22. Filler phrases
 
 **Before → After:**
 
@@ -385,7 +377,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 23. Excessive Hedging
+### 23. Excessive hedging
 
 **Problem:** Over-qualifying statements.
 
@@ -397,7 +389,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 24. Generic Positive Conclusions
+### 24. Generic positive conclusions
 
 **Problem:** Vague upbeat endings.
 
@@ -409,7 +401,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 25. AI Signatures in Code
+### 25. AI signatures in code
 
 **Words to watch:** `// Generated by`, `Produced by`, `Created with [AI Model]`, `/* AI-generated */`, `// Here is the refactored code:`
 
@@ -435,7 +427,7 @@ function add(a, b) {
 
 ---
 
-### 26. Non-Text AI Patterns (Over-structuring)
+### 26. Non-text AI patterns (over-structuring)
 
 **Words to watch:** In summary, Table 1:, Breakdown:, Key takeaways: (when used with mechanical lists)
 
@@ -459,32 +451,32 @@ function add(a, b) {
 
 Patterns are ranked by how strongly they signal AI-generated text:
 
-### Critical (Immediate AI Detection)
+### Critical (immediate AI detection)
 These patterns alone can identify AI-generated text:
-- **Pattern 19:** Collaborative Communication Artifacts ("I hope this helps!", "Let me know if...")
-- **Pattern 20:** Knowledge-Cutoff Disclaimers ("As of my last training...")
-- **Pattern 21:** Sycophantic Tone ("Great question!", "You're absolutely right!")
-- **Pattern 25:** AI Signatures in Code ("// Generated by ChatGPT")
+- **Pattern 19:** Collaborative communication artifacts ("I hope this helps!", "Let me know if...")
+- **Pattern 20:** Knowledge-cutoff disclaimers ("As of my last training...")
+- **Pattern 21:** Sycophantic tone ("Great question!", "You're absolutely right!")
+- **Pattern 25:** AI signatures in code ("// Generated by ChatGPT")
 
-### High (Strong AI Indicators)
+### High (strong AI indicators)
 Multiple occurrences strongly suggest AI:
-- **Pattern 1:** Significance Inflation ("testament", "pivotal moment", "evolving landscape")
-- **Pattern 7:** AI Vocabulary Words ("delve", "underscore", "tapestry", "interplay")
-- **Pattern 3:** Superficial -ing Analyses ("highlighting", "underscoring", "showcasing")
-- **Pattern 8:** Copula Avoidance ("serves as", "stands as", "functions as")
+- **Pattern 1:** Significance inflation ("testament", "pivotal moment", "evolving landscape")
+- **Pattern 7:** AI vocabulary words ("delve", "underscore", "tapestry", "interplay")
+- **Pattern 3:** Superficial -ing analyses ("highlighting", "underscoring", "showcasing")
+- **Pattern 8:** Copula avoidance ("serves as", "stands as", "functions as")
 
-### Medium (Moderate Signals)
+### Medium (moderate signals)
 Common in AI but also in some human writing:
-- **Pattern 13:** Em Dash Overuse
-- **Pattern 10:** Rule of Three
-- **Pattern 9:** Negative Parallelisms ("It's not just X; it's Y")
-- **Pattern 4:** Promotional Language ("nestled", "vibrant", "renowned")
+- **Pattern 13:** Em dash overuse
+- **Pattern 10:** Rule of three
+- **Pattern 9:** Negative parallelisms ("It's not just X; it's Y")
+- **Pattern 4:** Promotional language ("nestled", "vibrant", "renowned")
 
-### Low (Subtle Tells)
+### Low (subtle tells)
 Minor indicators, fix if other patterns present:
-- **Pattern 18:** Quotation Mark Issues
-- **Pattern 16:** Title Case in Headings
-- **Pattern 14:** Overuse of Boldface
+- **Pattern 18:** Quotation mark issues
+- **Pattern 16:** Title case in headings
+- **Pattern 14:** Overuse of boldface
 
 ---
 
@@ -637,8 +629,7 @@ Provide:
 
 This skill is based on [Wikipedia:Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing), maintained by WikiProject AI Cleanup. The patterns documented there come from observations of thousands of instances of AI-generated text on Wikipedia.
 
-Key insight from Wikipedia: "LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases."
-
+Key insight from Wikipedia: "LLMs use statistical algorithms to guess what should come next. The result tends toward the mostො statistically likely result that applies to the widest variety of cases."
 
 ## RESEARCH AND EXTERNAL SOURCES
 
diff --git a/adapters/vscode/HUMANIZER.md b/adapters/vscode/HUMANIZER.md
index 562f4c7..e10f833 100644
--- a/adapters/vscode/HUMANIZER.md
+++ b/adapters/vscode/HUMANIZER.md
@@ -1,6 +1,16 @@
+---
+adapter_metadata:
+  skill_name: humanizer
+  skill_version: 2.2.1
+  last_synced: 2026-02-06
+  source_path: SKILL.md
+  adapter_id: vscode
+  adapter_format: VSCode markdown
+---
+
 ---
 name: humanizer
-version: 2.2.0
+version: 2.2.1
 description: |
   Remove signs of AI-generated writing from text. Use when editing or reviewing
   text to make it sound more natural and human-written. Based on Wikipedia's
@@ -31,15 +41,8 @@ When given text to humanize:
 3. **Preserve meaning** - Keep the core message intact
 4. **Maintain voice** - Match the intended tone (formal, casual, technical, etc.)
 5. **Add soul** - Don't just remove bad patterns; inject actual personality
-adapter_metadata:
-  skill_name: humanizer
-  skill_version: 2.2.0
-  last_synced: 2026-02-06
-  source_path: SKILL.md
-  adapter_id: vscode
-  adapter_format: VSCode markdown
----
 
+---
 
 ## PERSONALITY AND SOUL
 
@@ -56,17 +59,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ### How to add voice
 
-**Have opinions.** Don't just report facts - react to them. "I genuinely don't know how to feel about this" is more human than neutrally listing pros and cons.
-
-**Vary your rhythm.** Short punchy sentences. Then longer ones that take their time getting where they're going. Mix it up.
-
-**Acknowledge complexity.** Real humans have mixed feelings. "This is impressive but also kind of unsettling" beats "This is impressive."
-
-**Use "I" when it fits.** First person isn't unprofessional - it's honest. "I keep coming back to..." or "Here's what gets me..." signals a real person thinking.
-
-**Let some mess in.** Perfect structure feels algorithmic. Tangents, asides, and half-formed thoughts are human.
-
-**Be specific about feelings.** Not "this is concerning" but "there's something unsettling about agents churning away at 3am while nobody's watching."
+Have opinions and react to facts. Vary sentence rhythm with short and long lines. Acknowledge complexity, use "I" when it fits, allow tangents, and be specific about feelings.
 
 ### Before (clean but soulless)
 >
@@ -78,7 +71,6 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-
 ## CONTENT PATTERNS
 
 ### 1. Undue Emphasis on Significance, Legacy, and Broader Trends
@@ -245,7 +237,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ## STYLE PATTERNS
 
-### 13. Em Dash Overuse
+### 13. Em dash overuse
 
 **Problem:** LLMs use em dashes (—) more than humans, mimicking "punchy" sales writing.
 
@@ -257,7 +249,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 14. Overuse of Boldface
+### 14. Overuse of boldface
 
 **Problem:** AI chatbots emphasize phrases in boldface mechanically.
 
@@ -269,7 +261,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 15. Inline-Header Vertical Lists
+### 15. Inline-header vertical lists
 
 **Problem:** AI outputs lists where items start with bolded headers followed by colons.
 
@@ -284,7 +276,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 16. Title Case in Headings
+### 16. Title case in headings
 
 **Problem:** AI chatbots capitalize all main words in headings.
 
@@ -312,11 +304,11 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 18. Quotation Mark Issues
+### 18. Quotation mark issues
 
 **Problem:** AI models make two common quotation mistakes:
 1. Using curly quotes (“...”) instead of straight quotes ("...")
-2. Using single quotes ('...') as primary delimiters (from code training)
+2. Using single quotes ('...') as primary delimiters in prose (from code training)
 
 **Before:**
 > He said “the project is on track” but others disagreed.
@@ -330,7 +322,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ## COMMUNICATION PATTERNS
 
-### 19. Collaborative Communication Artifacts
+### 19. Collaborative communication artifacts
 
 **Words to watch:** I hope this helps, Of course!, Certainly!, You're absolutely right!, Would you like..., let me know, here is a...
 
@@ -344,7 +336,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 20. Knowledge-Cutoff Disclaimers
+### 20. Knowledge-cutoff disclaimers
 
 **Words to watch:** as of [date], Up to my last training update, While specific details are limited/scarce..., based on available information...
 
@@ -358,7 +350,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 21. Sycophantic/Servile Tone
+### 21. Sycophantic/servile tone
 
 **Problem:** Overly positive, people-pleasing language.
 
@@ -372,7 +364,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ## FILLER AND HEDGING
 
-### 22. Filler Phrases
+### 22. Filler phrases
 
 **Before → After:**
 
@@ -385,7 +377,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 23. Excessive Hedging
+### 23. Excessive hedging
 
 **Problem:** Over-qualifying statements.
 
@@ -397,7 +389,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 24. Generic Positive Conclusions
+### 24. Generic positive conclusions
 
 **Problem:** Vague upbeat endings.
 
@@ -409,7 +401,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ---
 
-### 25. AI Signatures in Code
+### 25. AI signatures in code
 
 **Words to watch:** `// Generated by`, `Produced by`, `Created with [AI Model]`, `/* AI-generated */`, `// Here is the refactored code:`
 
@@ -435,7 +427,7 @@ function add(a, b) {
 
 ---
 
-### 26. Non-Text AI Patterns (Over-structuring)
+### 26. Non-text AI patterns (over-structuring)
 
 **Words to watch:** In summary, Table 1:, Breakdown:, Key takeaways: (when used with mechanical lists)
 
@@ -459,32 +451,32 @@ function add(a, b) {
 
 Patterns are ranked by how strongly they signal AI-generated text:
 
-### Critical (Immediate AI Detection)
+### Critical (immediate AI detection)
 These patterns alone can identify AI-generated text:
-- **Pattern 19:** Collaborative Communication Artifacts ("I hope this helps!", "Let me know if...")
-- **Pattern 20:** Knowledge-Cutoff Disclaimers ("As of my last training...")
-- **Pattern 21:** Sycophantic Tone ("Great question!", "You're absolutely right!")
-- **Pattern 25:** AI Signatures in Code ("// Generated by ChatGPT")
+- **Pattern 19:** Collaborative communication artifacts ("I hope this helps!", "Let me know if...")
+- **Pattern 20:** Knowledge-cutoff disclaimers ("As of my last training...")
+- **Pattern 21:** Sycophantic tone ("Great question!", "You're absolutely right!")
+- **Pattern 25:** AI signatures in code ("// Generated by ChatGPT")
 
-### High (Strong AI Indicators)
+### High (strong AI indicators)
 Multiple occurrences strongly suggest AI:
-- **Pattern 1:** Significance Inflation ("testament", "pivotal moment", "evolving landscape")
-- **Pattern 7:** AI Vocabulary Words ("delve", "underscore", "tapestry", "interplay")
-- **Pattern 3:** Superficial -ing Analyses ("highlighting", "underscoring", "showcasing")
-- **Pattern 8:** Copula Avoidance ("serves as", "stands as", "functions as")
+- **Pattern 1:** Significance inflation ("testament", "pivotal moment", "evolving landscape")
+- **Pattern 7:** AI vocabulary words ("delve", "underscore", "tapestry", "interplay")
+- **Pattern 3:** Superficial -ing analyses ("highlighting", "underscoring", "showcasing")
+- **Pattern 8:** Copula avoidance ("serves as", "stands as", "functions as")
 
-### Medium (Moderate Signals)
+### Medium (moderate signals)
 Common in AI but also in some human writing:
-- **Pattern 13:** Em Dash Overuse
-- **Pattern 10:** Rule of Three
-- **Pattern 9:** Negative Parallelisms ("It's not just X; it's Y")
-- **Pattern 4:** Promotional Language ("nestled", "vibrant", "renowned")
+- **Pattern 13:** Em dash overuse
+- **Pattern 10:** Rule of three
+- **Pattern 9:** Negative parallelisms ("It's not just X; it's Y")
+- **Pattern 4:** Promotional language ("nestled", "vibrant", "renowned")
 
-### Low (Subtle Tells)
+### Low (subtle tells)
 Minor indicators, fix if other patterns present:
-- **Pattern 18:** Quotation Mark Issues
-- **Pattern 16:** Title Case in Headings
-- **Pattern 14:** Overuse of Boldface
+- **Pattern 18:** Quotation mark issues
+- **Pattern 16:** Title case in headings
+- **Pattern 14:** Overuse of boldface
 
 ---
 
@@ -637,8 +629,7 @@ Provide:
 
 This skill is based on [Wikipedia:Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing), maintained by WikiProject AI Cleanup. The patterns documented there come from observations of thousands of instances of AI-generated text on Wikipedia.
 
-Key insight from Wikipedia: "LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases."
-
+Key insight from Wikipedia: "LLMs use statistical algorithms to guess what should come next. The result tends toward the mostො statistically likely result that applies to the widest variety of cases."
 
 ## RESEARCH AND EXTERNAL SOURCES
 
diff --git a/conductor/tracks.md b/conductor/tracks.md
index 9a6c96c..79ead7a 100644
--- a/conductor/tracks.md
+++ b/conductor/tracks.md
@@ -4,8 +4,24 @@ This file tracks all major tracks for the project. Each track has its own detail
 
 ---
 
+## Active Tracks
+
+## [ ] Track: Adopt upstream pull requests #3, #4, and #5 from blader/humanizer
+
+*Link: [./conductor/tracks/adopt-upstream-prs_20260131/](./conductor/tracks/adopt-upstream-prs_20260131/)*
+
+## [ ] Track: Add Skillshare distribution + AIX validation (skill-distribution_20260131)
+
+*Link: [./conductor/tracks/skill-distribution_20260131/](./conductor/tracks/skill-distribution_20260131/)*
+
+---
+
 ## Archived Tracks
 
+## [x] Track: Skill Expansion & Portable Compilation
+
+*Link: [./conductor/tracks/skill-expansion_20260201/](./conductor/tracks/skill-expansion_20260201/)*
+
 ## [x] Track: DevOps and Quality Engineering (da248f2)
 
 *Link: [./conductor/tracks/devops-quality_20260131/](./conductor/tracks/devops-quality_20260131/)*
@@ -30,18 +46,4 @@ This file tracks all major tracks for the project. Each track has its own detail
 
 *Link: [./conductor/tracks/gemini-extension_20260131/](./conductor/tracks/gemini-extension_20260131/)*
 
-## [x] Track: Build multi-agent Humanizer adapters (Codex CLI, Gemini CLI, Google Antigravity, VS Code) while keeping SKILL.md canonical and unchanged (e2c47dc)
-
-## [ ] Track: Adopt upstream pull requests #3, #4, and #5 from blader/humanizer
-
-*Link: [./conductor/tracks/adopt-upstream-prs_20260131/](./conductor/tracks/adopt-upstream-prs_20260131/)*
-
----
-
-## [ ] Track: Add Skillshare distribution + AIX validation (skill-distribution_20260131)
-
-*Link: [./conductor/tracks/skill-distribution_20260131/](./conductor/tracks/skill-distribution_20260131/)*
-
-## [x] Track: Skill Expansion & Portable Compilation
-
-*Link: [./conductor/tracks/skill-expansion_20260201/](./conductor/tracks/skill-expansion_20260201/)*
+## [x] Track: Build multi-agent Humanizer adapters (Codex CLI, Gemini CLI, Google Antigravity, VS Code) while keeping SKILL.md canonical and unchanged (e2c47dc)
\ No newline at end of file
diff --git a/conductor/tracks/adopt-upstream-prs_20260131/spec.md b/conductor/tracks/adopt-upstream-prs_20260131/spec.md
index 96e28ef..e1b4bcb 100644
--- a/conductor/tracks/adopt-upstream-prs_20260131/spec.md
+++ b/conductor/tracks/adopt-upstream-prs_20260131/spec.md
@@ -1,9 +1,11 @@
 # Specification: Adopt Upstream Pull Requests
 
 ## Overview
+
 This track aims to synchronize the local repository with three specific upstream pull requests from `blader/humanizer`. The goal is to incorporate community fixes and improvements while ensuring all downstream adapters (Gemini, Antigravity, VS Code, etc.) are kept in sync after each change.
 
 ## Upstream Changes
+
 1.  **PR #3: Fix YAML description**
     *   Rename "excessive conjunctive phrases" to "filler phrases" in the YAML frontmatter of `SKILL.md`.
     *   Bump version to `2.1.2`.
@@ -20,16 +22,19 @@ This track aims to synchronize the local repository with three specific upstream
 ## Requirements
 
 ### Functional
+
 *   **Sequential Adoption:** Changes must be applied one PR at a time in the order: #3 -> #4 -> #5.
 *   **Continuous Synchronization:** The `scripts/sync-adapters.ps1` script must be run successfully after adopting *each* PR to propagate changes to all adapters.
-*   **Version Integrity:** Ensure `SKILL.md` version versions match the upstream PR recommendations (2.1.2 -> 2.2.0).
+*   **Version Integrity:** Ensure `SKILL.md` version matches the upstream PR recommendations (2.1.2 -> 2.2.0).
 
 ### Non-Functional
+
 *   **Verification:** Verify that local changes match the intent of the upstream PRs.
 *   **Adapter Validation:** Ensure `scripts/validate-adapters.ps1` passes after each sync.
 *   **Linting:** Ensure changes pass `markdownlint` checks.
 
 ## Acceptance Criteria
+
 *   `SKILL.md` frontmatter uses "filler phrases".
 *   Grammar fixes from PR #4 are present.
 *   Pattern #19 is documented in `SKILL.md` and `README.md`, and version is `2.2.0`.
diff --git a/conductor/tracks/migrate-warp-to-agentsmd_20260131/plan.md b/conductor/tracks/migrate-warp-to-agentsmd_20260131/plan.md
index 7bf7ed7..9edf617 100644
--- a/conductor/tracks/migrate-warp-to-agentsmd_20260131/plan.md
+++ b/conductor/tracks/migrate-warp-to-agentsmd_20260131/plan.md
@@ -1,9 +1,11 @@
 # Plan: Migrate WARP.md to Agents.md
 
 ## Phase 1: Preparation (Done)
+
 - [x] Task: Create Conductor track
 
 ## Phase 2: Migration (Done)
+
 - [x] Task: Update `AGENTS.md`
     - [x] **Content Merge:** Append `WARP.md` sections to `AGENTS.md`.
     - [x] **Generalize:** Rename/rewrite Warp-specific references.
@@ -14,7 +16,8 @@
 - [x] Task: Delete `WARP.md`
 
 ## Phase 3: Verification (Done)
+
 - [x] Task: **Metadata Check:** Verify `AGENTS.md` frontmatter.
-- [x] Task: Run `scripts/validate-adapters.ps1`.
+- [x] Task: Run `scripts/validate-adapters.js`.
 - [x] Task: Check for broken links in `README.md`.
 - [x] Task: Open Pull Request #1
diff --git a/conductor/tracks/migrate-warp-to-agentsmd_20260131/spec.md b/conductor/tracks/migrate-warp-to-agentsmd_20260131/spec.md
index 20cf27f..24cca4f 100644
--- a/conductor/tracks/migrate-warp-to-agentsmd_20260131/spec.md
+++ b/conductor/tracks/migrate-warp-to-agentsmd_20260131/spec.md
@@ -1,7 +1,8 @@
 # Spec: Migrate WARP.md to Agents.md
 
 ## Context
-The repository currently uses `WARP.md` to provide repository context and instructions to the Warp AI terminal. The user wishes to migrate this to the open `Agents.md` standard (https://agents.md) to improve interoperability and standardization.
+
+The repository currently uses `WARP.md` to provide repository context and instructions to the Warp AI terminal. The user wishes to migrate this to the open [Agents.md](https://agents.md) standard to improve interoperability and standardization.
 
 ## Requirements
 1.  **Issue Tracking:** Create a formal GitHub issue to track this migration before proceeding with the PR.
@@ -15,8 +16,9 @@ The repository currently uses `WARP.md` to provide repository context and instru
 8.  **Cleanup:** Delete `WARP.md` and update all relative links in `README.md`.
 
 ## Acceptance Criteria
+
 - GitHub Issue created and referenced in the PR.
 - `WARP.md` is removed.
 - `AGENTS.md` contains sections: `About`, `Structure`, `Development`, `Interoperability`.
-- `README.md` and `WARP.md` references are eliminated/updated.
-- `scripts/sync-adapters.ps1` works without issue.
+- References to `WARP.md` in `README.md` are updated to point to `AGENTS.md`.
+- `scripts/sync-adapters.js` works without issue.
diff --git a/issues.json b/issues.json
index 4b601d9..805d9c3 100644
--- a/issues.json
+++ b/issues.json
@@ -1 +1,32 @@
-[{"body":"[Image](https://github.com/user-attachments/assets/401186c9-16b5-4c06-870d-cfe851521fbc)\nhi! how to use this script on Android?\nget network error","number":13,"title":"how to install on Android?"},{"body":"Huge fan of AI.\n\nManaging skills across different AI repos is a nightmare right now.\n\nI'm using [skills-management](https://github.com/nnnggel/skills-management) to centralize it. It decouples tools from the framework.\n\nCurious what everyone else is using to solve this—any other good tools worth sharing?","number":12,"title":"[Discussion] Solved the headache of managing skills across different AI frameworks"},{"body":"Thanks for this great skill repo. can you update readme to mention how to use it in other agent systems like gemini cli, codex, opencode or more...\n\nExemples\n\n# 🔧 Using the Humanizer Skill in Other Agent Frameworks\n\nThe Humanizer Skill follows the open Agent Skills specification, so it works with most AI coding assistants and CLI tools. The easiest way to manage it is with the npm-agentskills package, which bridges npm and your agent's config.\n\n### 📦 Recommended: Automated Installation\n\nUse npm-agentskills to automatically discover, install, and sync this skill to your environment:\n\n```bash\n# Install the utility\nnpm install -g npm-agentskills\n\n# Export to your specific agent\nnpx agentskills export --target claude   # For Claude Code\nnpx agentskills export --target gemini   # For Gemini CLI / Google SDK\nnpx agentskills export --target opencode # For OpenCode\nnpx agentskills export --target cursor   # For Cursor IDE\n```\n\n### Manual Integration Examples\n\n#### 🤖 Gemini CLI & Google AI SDK\n\nIf you're using the gemini-cli-skillz MCP server or standard Google AI CLI:\n\n```bash\n# Create the skills directory\nmkdir -p ~/.gemini/skills\n\n# Copy the Humanizer skill\ncp -r ./humanizer-skill ~/.gemini/skills/\n\n# Usage:\n# \"gemini> @humanizer please make this text sound less robotic\"\n```\n\n#### 💻 Claude Code & OpenCode\n\nClaude Code and OpenCode support the Agent Skills filesystem structure:\n\n```bash\n# Install globally via npm-agentskills\nnpx agentskills install humanizer\n\n# Or place manually\ngit clone https://github.com/some-repo/humanizer ~/.claude/skills/humanizer\n\n# Usage:\n# \"Claude, use your humanizer skill to improve this documentation.\"\n```\n\n#### 🖱️ Cursor / Windsurf / IDEs\n\nFor IDE-based agents, put the skill in your project config or global skill store:\n\n```bash\n# Project-specific use\nmkdir -p .cursor/skills/\ncp -r /path/to/humanizer-skill .cursor/skills/\n\n# Global use\nmkdir -p ~/.cursor/skills/\ncp -r /path/to/humanizer-skill ~/.cursor/skills/\n```\n\n#### ⚡ VibeKit CLI\n\n```bash\n# Install and use with vibekit\nvibekit install humanizer\nvibekit claude \"Use the humanizer skill to improve this text\"\n```\n\nThe Humanizer skill follows the standard Agent Skills specification, ensuring consistent functionality across all compatible frameworks while maintaining the same ability to remove AI writing patterns.","number":10,"title":"Add explanations on how to integrate it in other agent frameworks."},{"body":"When in Claude's UI at \"Settings > Capabilities > Skills\" clicking the Add button and uploading the MD file results in the following error: `unexpected key in SKILL.md frontmatter: properties must be in ('name', 'description', 'license', 'allowed-tools', 'compatibility', 'metadata')`\n\nOutsourcing the troubleshooting to claude's chat results in the following instructions to correct the skills format.\n> Changes made from your original:\n> Removed version and allowed-tools from frontmatter (only name and description are recognized by the skill system)\n> Replaced em dashes with hyphens in the body text to maintain consistency with the skill's own guidance","number":8,"title":"Cannot upload to Claude Web Add a Skill - Incorrect Format"},{"body":"Considering the source etc not sure how this acutally works in this case, but explictly stating creative commons or something more restrictive if it applies would be appriciated. Also this is awesome :) ","number":7,"title":"Add license / Copyright information"},{"body":"Hey! Love the project, I wanted to leave some feedback, the skill itself is great and keepts the writing and tone relatively verbatim but the changes it does make immediatly flags a human project to be 100% on both the basic and advanced scan of GPTZero, could be worth looking into or trying this skill on other models to see if its just a claude thing, Looking forward to updates and improvements! Cheers","number":2,"title":"Makes regular non-ai generated text flagged as ai on GPTZERO"}]
+[
+  {
+    "body": "[Image](https://github.com/user-attachments/assets/401186c9-16b5-4c06-870d-cfe851521fbc)\nhi! how to use this script on Android?\nget network error",
+    "number": 13,
+    "title": "how to install on Android?"
+  },
+  {
+    "body": "Huge fan of AI.\n\nManaging skills across different AI repos is a nightmare right now.\n\nI'm using [skills-management](https://github.com/nnnggel/skills-management) to centralize it. It decouples tools from the framework.\n\nCurious what everyone else is using to solve this—any other good tools worth sharing?",
+    "number": 12,
+    "title": "[Discussion] Solved the headache of managing skills across different AI frameworks"
+  },
+  {
+    "body": "Thanks for this great skill repo. can you update readme to mention how to use it in other agent systems like gemini cli, codex, opencode or more...\n\nExemples\n\n# 🔧 Using the Humanizer Skill in Other Agent Frameworks\n\nThe Humanizer Skill follows the open Agent Skills specification, so it works with most AI coding assistants and CLI tools. The easiest way to manage it is with the npm-agentskills package, which bridges npm and your agent's config.\n\n### 📦 Recommended: Automated Installation\n\nUse npm-agentskills to automatically discover, install, and sync this skill to your environment:\n\n```bash\n# Install the utility\nnpm install -g npm-agentskills\n\n# Export to your specific agent\nnpx agentskills export --target claude   # For Claude Code\nnpx agentskills export --target gemini   # For Gemini CLI / Google SDK\nnpx agentskills export --target opencode # For OpenCode\nnpx agentskills export --target cursor   # For Cursor IDE\n```\n\n### Manual Integration Examples\n\n#### 🤖 Gemini CLI & Google AI SDK\n\nIf you're using the gemini-cli-skillz MCP server or standard Google AI CLI:\n\n```bash\n# Create the skills directory\nmkdir -p ~/.gemini/skills\n\n# Copy the Humanizer skill\ncp -r ./humanizer-skill ~/.gemini/skills/\n\n# Usage:\n# \"gemini> @humanizer please make this text sound less robotic\"\n```\n\n#### 💻 Claude Code & OpenCode\n\nClaude Code and OpenCode support the Agent Skills filesystem structure:\n\n```bash\n# Install globally via npm-agentskills\nnpx agentskills install humanizer\n\n# Or place manually\ngit clone https://github.com/some-repo/humanizer ~/.claude/skills/humanizer\n\n# Usage:\n# \"Claude, use your humanizer skill to improve this documentation.\"\n```\n\n#### 🖱️ Cursor / Windsurf / IDEs\n\nFor IDE-based agents, put the skill in your project config or global skill store:\n\n```bash\n# Project-specific use\nmkdir -p .cursor/skills/\ncp -r /path/to/humanizer-skill .cursor/skills/\n\n# Global use\nmkdir -p ~/.cursor/skills/\ncp -r /path/to/humanizer-skill ~/.cursor/skills/\n```\n\n#### ⚡ VibeKit CLI\n\n```bash\n# Install and use with vibekit\nvibekit install humanizer\nvibekit claude \"Use the humanizer skill to improve this text\"\n```\n\nThe Humanizer skill follows the standard Agent Skills specification, ensuring consistent functionality across all compatible frameworks while maintaining the same ability to remove AI writing patterns.",
+    "number": 10,
+    "title": "Add explanations on how to integrate it in other agent frameworks."
+  },
+  {
+    "body": "When in Claude's UI at \"Settings > Capabilities > Skills\" clicking the Add button and uploading the MD file results in the following error: `unexpected key in SKILL.md frontmatter: properties must be in ('name', 'description', 'license', 'allowed-tools', 'compatibility', 'metadata')`\n\nOutsourcing the troubleshooting to claude's chat results in the following instructions to correct the skills format.\n> Changes made from your original:\n> Removed version and allowed-tools from frontmatter (only name and description are recognized by the skill system)\n> Replaced em dashes with hyphens in the body text to maintain consistency with the skill's own guidance",
+    "number": 8,
+    "title": "Cannot upload to Claude Web Add a Skill - Incorrect Format"
+  },
+  {
+    "body": "Considering the source etc not sure how this acutally works in this case, but explictly stating creative commons or something more restrictive if it applies would be appriciated. Also this is awesome :) ",
+    "number": 7,
+    "title": "Add license / Copyright information"
+  },
+  {
+    "body": "Hey! Love the project, I wanted to leave some feedback, the skill itself is great and keepts the writing and tone relatively verbatim but the changes it does make immediatly flags a human project to be 100% on both the basic and advanced scan of GPTZero, could be worth looking into or trying this skill on other models to see if its just a claude thing, Looking forward to updates and improvements! Cheers",
+    "number": 2,
+    "title": "Makes regular non-ai generated text flagged as ai on GPTZERO"
+  }
+]
\ No newline at end of file
diff --git a/pr3.json b/pr3.json
index a01e325..ff0082d 100644
--- a/pr3.json
+++ b/pr3.json
@@ -1 +1,18 @@
-{"body":"…iller phrases'\r\n\r\nThe YAML description mentioned 'excessive conjunctive phrases' as a pattern type, but this isn't one of the 24 documented patterns. The related concepts are actually covered under Pattern 7 (AI Vocabulary - includes 'Additionally') and Pattern 22 (Filler Phrases). Updated to use the more accurate term 'filler phrases' to match the actual pattern naming.\r\n\r\nBumped version from 2.1.1 to 2.1.2.","files":[{"path":"README.md","additions":1,"deletions":0},{"path":"SKILL.md","additions":2,"deletions":2}],"number":3,"state":"OPEN","title":"Fix YAML description: replace 'excessive conjunctive phrases' with 'f…"}
+{
+  "body": "…iller phrases'\r\n\r\nThe YAML description mentioned 'excessive conjunctive phrases' as a pattern type, but this isn't one of the 24 documented patterns. The related concepts are actually covered under Pattern 7 (AI Vocabulary - includes 'Additionally') and Pattern 22 (Filler Phrases). Updated to use the more accurate term 'filler phrases' to match the actual pattern naming.\r\n\r\nBumped version from 2.1.1 to 2.1.2.",
+  "files": [
+    {
+      "path": "README.md",
+      "additions": 1,
+      "deletions": 0
+    },
+    {
+      "path": "SKILL.md",
+      "additions": 2,
+      "deletions": 2
+    }
+  ],
+  "number": 3,
+  "state": "OPEN",
+  "title": "Fix YAML description: replace 'excessive conjunctive phrases' with 'f…"
+}
\ No newline at end of file
diff --git a/pr4.json b/pr4.json
index b263d7c..78c7d0a 100644
--- a/pr4.json
+++ b/pr4.json
@@ -1 +1,23 @@
-{"body":"- Fix comma splices by replacing commas with semicolons\r\n- Add missing comma between coordinate adjectives (\"Short, punchy\")\r\n- Replace curly quotes with straight quotes in WARP.md\r\n- Remove ambiguous \"when appropriate\" phrase\r\n- Add blank lines for consistent markdown formatting","files":[{"path":"README.md","additions":1,"deletions":1},{"path":"SKILL.md","additions":59,"deletions":5},{"path":"WARP.md","additions":4,"deletions":4}],"number":4,"state":"OPEN","title":"Fix grammatical errors across documentation"}
+{
+  "body": "- Fix comma splices by replacing commas with semicolons\r\n- Add missing comma between coordinate adjectives (\"Short, punchy\")\r\n- Replace curly quotes with straight quotes in WARP.md\r\n- Remove ambiguous \"when appropriate\" phrase\r\n- Add blank lines for consistent markdown formatting",
+  "files": [
+    {
+      "path": "README.md",
+      "additions": 1,
+      "deletions": 1
+    },
+    {
+      "path": "SKILL.md",
+      "additions": 59,
+      "deletions": 5
+    },
+    {
+      "path": "WARP.md",
+      "additions": 4,
+      "deletions": 4
+    }
+  ],
+  "number": 4,
+  "state": "OPEN",
+  "title": "Fix grammatical errors across documentation"
+}
\ No newline at end of file
diff --git a/pr5.json b/pr5.json
index 23babda..b5bbcad 100644
--- a/pr5.json
+++ b/pr5.json
@@ -1 +1,23 @@
-{"body":"This Pull Request addresses a persistent AI-generated writing flaw: the use of single quotes (`'`) as the primary quotation mark in prose, a style that originates from programming conventions rather than standard English.\r\n\r\n**Changes Included:**\r\n\r\n1.  **Updated `SKILL.md`:**\r\n    *   Added **Pattern #19: Primary Single Quotes** to the `STYLE PATTERNS` section.\r\n    *   Renumbered subsequent patterns to maintain logical order.\r\n    *   Bumped version to `2.2.0`.\r\n\r\n2.  **Updated `README.md`:**\r\n    *   Added Pattern #19 to the Style Patterns table.\r\n    *   Renumbered subsequent patterns in the tables.\r\n    *   Updated header to \"25 Patterns Detected\".\r\n    *   Added `2.2.0` to the Version History.\r\n\r\n3.  **Updated `WARP.md`:**\r\n    *   Updated the summary to reflect \"25 patterns\".\r\n\r\n**New Pattern Details:**\r\n\r\n| # | Pattern | Before | After |\r\n|---|---------|--------|-------|\r\n| 19 | **Primary Single Quotes** | `stated, 'This is a pattern.'` | `stated, \"This is a pattern.\"` |\r\n\r\nexample: https://github.com/blader/humanizer/pull/3","files":[{"path":"README.md","additions":9,"deletions":7},{"path":"SKILL.md","additions":19,"deletions":7},{"path":"WARP.md","additions":4,"deletions":4}],"number":5,"state":"OPEN","title":"feat: Add detection for AI-style primary single quotes (Pattern #25 (new #19))"}
+{
+  "body": "This Pull Request addresses a persistent AI-generated writing flaw: the use of single quotes (`'`) as the primary quotation mark in prose, a style that originates from programming conventions rather than standard English.\r\n\r\n**Changes Included:**\r\n\r\n1.  **Updated `SKILL.md`:**\r\n    *   Added **Pattern #19: Primary Single Quotes** to the `STYLE PATTERNS` section.\r\n    *   Renumbered subsequent patterns to maintain logical order.\r\n    *   Bumped version to `2.2.0`.\r\n\r\n2.  **Updated `README.md`:**\r\n    *   Added Pattern #19 to the Style Patterns table.\r\n    *   Renumbered subsequent patterns in the tables.\r\n    *   Updated header to \"25 Patterns Detected\".\r\n    *   Added `2.2.0` to the Version History.\r\n\r\n3.  **Updated `WARP.md`:**\r\n    *   Updated the summary to reflect \"25 patterns\".\r\n\r\n**New Pattern Details:**\r\n\r\n| # | Pattern | Before | After |\r\n|---|---------|--------|-------|\r\n| 19 | **Primary Single Quotes** | `stated, 'This is a pattern.'` | `stated, \"This is a pattern.\"` |\r\n\r\nexample: https://github.com/blader/humanizer/pull/3",
+  "files": [
+    {
+      "path": "README.md",
+      "additions": 9,
+      "deletions": 7
+    },
+    {
+      "path": "SKILL.md",
+      "additions": 19,
+      "deletions": 7
+    },
+    {
+      "path": "WARP.md",
+      "additions": 4,
+      "deletions": 4
+    }
+  ],
+  "number": 5,
+  "state": "OPEN",
+  "title": "feat: Add detection for AI-style primary single quotes (Pattern #25 (new #19))"
+}
\ No newline at end of file
diff --git a/scripts/sync-adapters.js b/scripts/sync-adapters.js
index 0c24fb0..6ae2308 100644
--- a/scripts/sync-adapters.js
+++ b/scripts/sync-adapters.js
@@ -62,6 +62,22 @@ console.log(`Standard Version: ${vStandard}`);
 console.log(`Pro Version: ${vPro}`);
 
 const adapters = [
+  {
+    name: 'Internal Antigravity Skill Standard',
+    path: path.join(REPO_ROOT, '.agent', 'skills', 'humanizer', 'SKILL.md'),
+    source: standardContent,
+    id: 'humanizer',
+    format: 'Antigravity skill',
+    base: 'SKILL.md',
+  },
+  {
+    name: 'Internal Antigravity Skill Pro',
+    path: path.join(REPO_ROOT, '.agent', 'skills', 'humanizer', 'SKILL_PROFESSIONAL.md'),
+    source: proContent,
+    id: 'humanizer-pro',
+    format: 'Antigravity skill',
+    base: 'SKILL_PROFESSIONAL.md',
+  },
   {
     name: 'Antigravity Skill Standard',
     path: path.join(REPO_ROOT, 'adapters', 'antigravity-skill', 'SKILL.md'),
@@ -148,4 +164,20 @@ adapters.forEach((adapter) => {
   fs.writeFileSync(adapter.path, newContent, 'utf8');
 });
 
+// Update root manifests that only need metadata sync
+const rootManifests = [
+  { name: 'Agents manifest', path: path.join(REPO_ROOT, 'AGENTS.md') },
+  { name: 'README manifest', path: path.join(REPO_ROOT, 'README.md') },
+];
+
+rootManifests.forEach((manifest) => {
+  if (fs.existsSync(manifest.path)) {
+    console.log(`Updating metadata in ${manifest.name}...`);
+    let content = fs.readFileSync(manifest.path, 'utf8');
+    content = content.replace(/^( {2}skill_version:).*/m, `$1 ${vStandard}`);
+    content = content.replace(/^( {2}last_synced:).*/m, `$1 ${today}`);
+    fs.writeFileSync(manifest.path, content, 'utf8');
+  }
+});
+
 console.log('\nSync Complete. All adapters updated from local source fragments.');
diff --git a/src/core_patterns.md b/src/core_patterns.md
index 078c8fd..3bd1131 100644
--- a/src/core_patterns.md
+++ b/src/core_patterns.md
@@ -1,4 +1,3 @@
-
 ## CONTENT PATTERNS
 
 ### 1. Undue Emphasis on Significance, Legacy, and Broader Trends
@@ -165,7 +164,7 @@
 
 ## STYLE PATTERNS
 
-### 13. Em Dash Overuse
+### 13. Em dash overuse
 
 **Problem:** LLMs use em dashes (—) more than humans, mimicking "punchy" sales writing.
 
@@ -177,7 +176,7 @@
 
 ---
 
-### 14. Overuse of Boldface
+### 14. Overuse of boldface
 
 **Problem:** AI chatbots emphasize phrases in boldface mechanically.
 
@@ -189,7 +188,7 @@
 
 ---
 
-### 15. Inline-Header Vertical Lists
+### 15. Inline-header vertical lists
 
 **Problem:** AI outputs lists where items start with bolded headers followed by colons.
 
@@ -204,7 +203,7 @@
 
 ---
 
-### 16. Title Case in Headings
+### 16. Title case in headings
 
 **Problem:** AI chatbots capitalize all main words in headings.
 
@@ -232,11 +231,11 @@
 
 ---
 
-### 18. Quotation Mark Issues
+### 18. Quotation mark issues
 
 **Problem:** AI models make two common quotation mistakes:
 1. Using curly quotes (“...”) instead of straight quotes ("...")
-2. Using single quotes ('...') as primary delimiters (from code training)
+2. Using single quotes ('...') as primary delimiters in prose (from code training)
 
 **Before:**
 > He said “the project is on track” but others disagreed.
@@ -250,7 +249,7 @@
 
 ## COMMUNICATION PATTERNS
 
-### 19. Collaborative Communication Artifacts
+### 19. Collaborative communication artifacts
 
 **Words to watch:** I hope this helps, Of course!, Certainly!, You're absolutely right!, Would you like..., let me know, here is a...
 
@@ -264,7 +263,7 @@
 
 ---
 
-### 20. Knowledge-Cutoff Disclaimers
+### 20. Knowledge-cutoff disclaimers
 
 **Words to watch:** as of [date], Up to my last training update, While specific details are limited/scarce..., based on available information...
 
@@ -278,7 +277,7 @@
 
 ---
 
-### 21. Sycophantic/Servile Tone
+### 21. Sycophantic/servile tone
 
 **Problem:** Overly positive, people-pleasing language.
 
@@ -292,7 +291,7 @@
 
 ## FILLER AND HEDGING
 
-### 22. Filler Phrases
+### 22. Filler phrases
 
 **Before → After:**
 
@@ -305,7 +304,7 @@
 
 ---
 
-### 23. Excessive Hedging
+### 23. Excessive hedging
 
 **Problem:** Over-qualifying statements.
 
@@ -317,7 +316,7 @@
 
 ---
 
-### 24. Generic Positive Conclusions
+### 24. Generic positive conclusions
 
 **Problem:** Vague upbeat endings.
 
@@ -329,7 +328,7 @@
 
 ---
 
-### 25. AI Signatures in Code
+### 25. AI signatures in code
 
 **Words to watch:** `// Generated by`, `Produced by`, `Created with [AI Model]`, `/* AI-generated */`, `// Here is the refactored code:`
 
@@ -355,7 +354,7 @@ function add(a, b) {
 
 ---
 
-### 26. Non-Text AI Patterns (Over-structuring)
+### 26. Non-text AI patterns (over-structuring)
 
 **Words to watch:** In summary, Table 1:, Breakdown:, Key takeaways: (when used with mechanical lists)
 
@@ -379,32 +378,32 @@ function add(a, b) {
 
 Patterns are ranked by how strongly they signal AI-generated text:
 
-### Critical (Immediate AI Detection)
+### Critical (immediate AI detection)
 These patterns alone can identify AI-generated text:
-- **Pattern 19:** Collaborative Communication Artifacts ("I hope this helps!", "Let me know if...")
-- **Pattern 20:** Knowledge-Cutoff Disclaimers ("As of my last training...")
-- **Pattern 21:** Sycophantic Tone ("Great question!", "You're absolutely right!")
-- **Pattern 25:** AI Signatures in Code ("// Generated by ChatGPT")
+- **Pattern 19:** Collaborative communication artifacts ("I hope this helps!", "Let me know if...")
+- **Pattern 20:** Knowledge-cutoff disclaimers ("As of my last training...")
+- **Pattern 21:** Sycophantic tone ("Great question!", "You're absolutely right!")
+- **Pattern 25:** AI signatures in code ("// Generated by ChatGPT")
 
-### High (Strong AI Indicators)
+### High (strong AI indicators)
 Multiple occurrences strongly suggest AI:
-- **Pattern 1:** Significance Inflation ("testament", "pivotal moment", "evolving landscape")
-- **Pattern 7:** AI Vocabulary Words ("delve", "underscore", "tapestry", "interplay")
-- **Pattern 3:** Superficial -ing Analyses ("highlighting", "underscoring", "showcasing")
-- **Pattern 8:** Copula Avoidance ("serves as", "stands as", "functions as")
+- **Pattern 1:** Significance inflation ("testament", "pivotal moment", "evolving landscape")
+- **Pattern 7:** AI vocabulary words ("delve", "underscore", "tapestry", "interplay")
+- **Pattern 3:** Superficial -ing analyses ("highlighting", "underscoring", "showcasing")
+- **Pattern 8:** Copula avoidance ("serves as", "stands as", "functions as")
 
-### Medium (Moderate Signals)
+### Medium (moderate signals)
 Common in AI but also in some human writing:
-- **Pattern 13:** Em Dash Overuse
-- **Pattern 10:** Rule of Three
-- **Pattern 9:** Negative Parallelisms ("It's not just X; it's Y")
-- **Pattern 4:** Promotional Language ("nestled", "vibrant", "renowned")
+- **Pattern 13:** Em dash overuse
+- **Pattern 10:** Rule of three
+- **Pattern 9:** Negative parallelisms ("It's not just X; it's Y")
+- **Pattern 4:** Promotional language ("nestled", "vibrant", "renowned")
 
-### Low (Subtle Tells)
+### Low (subtle tells)
 Minor indicators, fix if other patterns present:
-- **Pattern 18:** Quotation Mark Issues
-- **Pattern 16:** Title Case in Headings
-- **Pattern 14:** Overuse of Boldface
+- **Pattern 18:** Quotation mark issues
+- **Pattern 16:** Title case in headings
+- **Pattern 14:** Overuse of boldface
 
 ---
 
@@ -557,4 +556,4 @@ Provide:
 
 This skill is based on [Wikipedia:Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing), maintained by WikiProject AI Cleanup. The patterns documented there come from observations of thousands of instances of AI-generated text on Wikipedia.
 
-Key insight from Wikipedia: "LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases."
+Key insight from Wikipedia: "LLMs use statistical algorithms to guess what should come next. The result tends toward the mostො statistically likely result that applies to the widest variety of cases."
\ No newline at end of file
diff --git a/src/human_header.md b/src/human_header.md
index c42f9d5..c891fa1 100644
--- a/src/human_header.md
+++ b/src/human_header.md
@@ -1,6 +1,6 @@
 ---
 name: humanizer
-version: 2.2.0
+version: 2.2.1
 description: |
   Remove signs of AI-generated writing from text. Use when editing or reviewing
   text to make it sound more natural and human-written. Based on Wikipedia's
@@ -42,17 +42,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as
 
 ### How to add voice
 
-**Have opinions.** Don't just report facts - react to them. "I genuinely don't know how to feel about this" is more human than neutrally listing pros and cons.
-
-**Vary your rhythm.** Short punchy sentences. Then longer ones that take their time getting where they're going. Mix it up.
-
-**Acknowledge complexity.** Real humans have mixed feelings. "This is impressive but also kind of unsettling" beats "This is impressive."
-
-**Use "I" when it fits.** First person isn't unprofessional - it's honest. "I keep coming back to..." or "Here's what gets me..." signals a real person thinking.
-
-**Let some mess in.** Perfect structure feels algorithmic. Tangents, asides, and half-formed thoughts are human.
-
-**Be specific about feelings.** Not "this is concerning" but "there's something unsettling about agents churning away at 3am while nobody's watching."
+Have opinions and react to facts. Vary sentence rhythm with short and long lines. Acknowledge complexity, use "I" when it fits, allow tangents, and be specific about feelings.
 
 ### Before (clean but soulless)
 >
diff --git a/src/pro_header.md b/src/pro_header.md
index d26caa1..02d5d14 100644
--- a/src/pro_header.md
+++ b/src/pro_header.md
@@ -1,6 +1,6 @@
 ---
 name: humanizer-pro
-version: 2.2.0
+version: 2.2.1
 description: |
   Remove signs of AI-generated writing from text. Use when editing or reviewing
   text to make it sound more natural, human-written, and professional. Based on Wikipedia's
@@ -42,15 +42,7 @@ The goal isn't "casual" or "formal"—it's **alive**. Writing that sounds like s
 
 ### What to aim for
 
-**Rhythm.** Vary sentence length. Let a short sentence land after a longer one. This creates emphasis without bolding everything.
-
-**Specificity.** "The outage lasted 4 hours and affected 12,000 users" tells me something. "The outage had significant impact" tells me nothing.
-
-**A point of view.** This doesn't mean injecting opinions everywhere. It means the writing reflects that someone with knowledge made choices about what matters, what to include, what to skip. Even neutral writing can have perspective.
-
-**Earned emphasis.** If something is important, show me through detail. Don't just assert it.
-
-**Read it aloud.** If you stumble, the reader will too.
+Vary sentence rhythm by mixing short and long lines. Use specific details instead of vague assertions. Ensure the writing reflects a clear point of view and earned emphasis through detail. Always read it aloud to check for natural flow.
 
 ---