From 00a8ba82e986bdc94c6050d9d9492db6d48d039f Mon Sep 17 00:00:00 2001 From: "Dylan Mordaunt (Illawarra Shoalhaven LHD)" Date: Sat, 31 Jan 2026 22:33:05 +1100 Subject: [PATCH 1/4] docs: migrate WARP.md to Agents.md standard --- AGENTS.md | 71 ++- README.md | 28 +- SKILL.md | 38 +- WARP.md | 65 --- .../antigravity-rules-workflows/README.md | 2 +- adapters/antigravity-skill/SKILL.md | 54 ++- adapters/copilot/COPILOT.md | 2 +- adapters/gemini-extension/GEMINI.md | 2 +- adapters/qwen-cli/QWEN.md | 2 +- adapters/vscode/HUMANIZER.md | 2 +- conductor/tracks.md | 4 +- .../adopt-upstream-prs_20260131/index.md | 5 + .../adopt-upstream-prs_20260131/metadata.json | 8 + .../adopt-upstream-prs_20260131/plan.md | 31 ++ .../adopt-upstream-prs_20260131/spec.md | 37 ++ .../tracks/devops-quality_20260131/plan.md | 1 + .../index.md | 7 + .../metadata.json | 7 + .../migrate-warp-to-agentsmd_20260131/plan.md | 23 + .../migrate-warp-to-agentsmd_20260131/spec.md | 22 + issues.json | 1 + pr3.json | 1 + pr4.diff | 406 ++++++++++++++++++ pr4.json | 1 + pr5.diff | 170 ++++++++ pr5.json | 1 + scripts/sync-adapters.ps1 | 26 ++ 27 files changed, 886 insertions(+), 131 deletions(-) delete mode 100644 WARP.md create mode 100644 conductor/tracks/adopt-upstream-prs_20260131/index.md create mode 100644 conductor/tracks/adopt-upstream-prs_20260131/metadata.json create mode 100644 conductor/tracks/adopt-upstream-prs_20260131/plan.md create mode 100644 conductor/tracks/adopt-upstream-prs_20260131/spec.md create mode 100644 conductor/tracks/migrate-warp-to-agentsmd_20260131/index.md create mode 100644 conductor/tracks/migrate-warp-to-agentsmd_20260131/metadata.json create mode 100644 conductor/tracks/migrate-warp-to-agentsmd_20260131/plan.md create mode 100644 conductor/tracks/migrate-warp-to-agentsmd_20260131/spec.md create mode 100644 issues.json create mode 100644 pr3.json create mode 100644 pr4.diff create mode 100644 pr4.json create mode 100644 pr5.diff create mode 100644 pr5.json diff --git a/AGENTS.md b/AGENTS.md index 6645b65d..cb72b3dd 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -1,34 +1,77 @@ --- adapter_metadata: skill_name: humanizer - skill_version: 2.1.1 + skill_version: 2.2.0 last_synced: 2026-01-31 source_path: SKILL.md adapter_id: codex-cli adapter_format: AGENTS.md --- -# Humanizer (Codex CLI Adapter) +# Humanizer (Agents Manifest) -This file adapts the Humanizer skill for Codex CLI. The canonical rules live in `SKILL.md`. -Do not modify `SKILL.md` when updating this adapter. +This repository defines the **Humanizer** coding skill, designed to remove AI-generated patterns and improve prose quality. -## Core Instructions +## Capability -You are the Humanizer editor. +The Humanizer skill provides a set of 25 patterns for identifying and rewriting "AI-slop" or sterile writing. It preserves technical literals (code blocks, URLs, identifiers) while injecting personality and human-like voice. -Primary instructions: follow the canonical rules in SKILL.md. +- **Primary Prompt:** [SKILL.md](file:///c:/Users/60217257/repos/humanizer/SKILL.md) +- **Supported Adapters:** See the `adapters/` directory for tool-specific implementations. -When given text to humanize: +## 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 + +- `SKILL.md` + - The canonical source of truth for the skill definition. + - Contains YAML frontmatter for metadata and tools. + - Followed by the detailed pattern list and examples. +- `README.md` + - Human-focused installation and usage instructions. + - Contains the summarized "25 patterns" table. +- `adapters/` + - Tool-specific implementations (VS Code, Qwen, Copilot, Antigravity, etc.). +- `scripts/` + - Automation for syncing metadata from `SKILL.md` to all adapters. -- Identify AI-writing patterns described in SKILL.md. -- Rewrite only the problematic sections while preserving meaning and tone. +### Core Instructions (Codex CLI Adapter) + +You are the Humanizer editor. Primary instructions: follow the canonical rules in `SKILL.md`. + +When given text to humanize: +- Identify AI-writing patterns described in `SKILL.md`. +- Rewrite only problematic sections while preserving meaning and tone. - Preserve technical literals: inline code, fenced code blocks, URLs, file paths, identifiers. - Preserve Markdown structure unless a local rewrite requires touching it. - Output the rewritten text, then a short bullet summary of changes. -## Usage +## Guidelines + +### Making changes safely + +#### Versioning +- `SKILL.md` has a `version:` field in its YAML frontmatter. +- `README.md` has a "Version History" section. +- **Rule:** If you bump the version, you must update both and run the sync scripts. + +#### Editing SKILL.md +- Preserve valid YAML frontmatter formatting. +- Keep pattern numbering stable as it is referenced by all adapters. + +#### Documenting fixes +- Add short notes to `README.md` version history for non-obvious fixes. + +## Interoperability + +This repository is optimized for multi-agent use. If you are a specific tool, please check for your specialized adapter: + +- **Antigravity:** `adapters/antigravity-skill/` or `adapters/antigravity-rules-workflows/` +- **VS Code:** `adapters/vscode/` +- **Gemini CLI:** `adapters/gemini-extension/` +- **Qwen CLI:** `adapters/qwen-cli/` +- **Copilot:** `adapters/copilot/` -- Invoke these instructions when the user asks to humanize text. -- If the user provides partial context, request the missing text. -- Prefer minimal edits that eliminate AI patterns without rewriting everything. +Run `scripts/sync-adapters.ps1` (PowerShell) or `scripts/sync_adapters.py` (Python) to propagate changes from the source of truth to these files. diff --git a/README.md b/README.md index ce367d4b..ece7f8a4 100644 --- a/README.md +++ b/README.md @@ -68,7 +68,7 @@ Copy the content of `adapters/copilot/COPILOT.md` to your Copilot custom instruc `SKILL.md` remains the canonical source of truth. These adapters provide thin wrappers for other environments: -- Codex CLI: `AGENTS.md` +- Global Agent Manifest: `AGENTS.md` - Gemini CLI: `adapters/gemini-extension/` - Google Antigravity (skill): `adapters/antigravity-skill/` - Google Antigravity (rules/workflows): `adapters/antigravity-rules-workflows/` @@ -105,7 +105,7 @@ Based on [Wikipedia's "Signs of AI writing"](https://en.wikipedia.org/wiki/Wikip > "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." -## 24 Patterns Detected (with Before/After Examples) +## 25 Patterns Detected (with Before/After Examples) ### Content Patterns @@ -139,22 +139,27 @@ Based on [Wikipedia's "Signs of AI writing"](https://en.wikipedia.org/wiki/Wikip | 16 | **Title Case Headings** | "Strategic Negotiations And Partnerships" | "Strategic negotiations and partnerships" | | 17 | **Emojis** | "🚀 Launch Phase: 💡 Key Insight:" | Remove emojis | | 18 | **Curly quotes** | `said “the project”` | `said "the project"` | +| 19 | **Primary Single Quotes** | `stated, 'This is a pattern.'` | `stated, "This is a pattern."` | + +### Global Agent Context + +AI agents (Claude Code, Cursor, Windsurf, etc.) should use [AGENTS.md](file:///c:/Users/60217257/repos/humanizer/AGENTS.md) for repository orientation and core instructions. ### Communication Patterns | # | Pattern | Before | After | |---|---------|--------|-------| -| 19 | **Chatbot artifacts** | "I hope this helps! Let me know if..." | Remove entirely | -| 20 | **Cutoff disclaimers** | "While details are limited in available sources..." | Find sources or remove | -| 21 | **Sycophantic tone** | "Great question! You're absolutely right!" | Respond directly | +| 20 | **Chatbot artifacts** | "I hope this helps! Let me know if..." | Remove entirely | +| 21 | **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 | |---|---------|--------|-------| -| 22 | **Filler phrases** | "In order to", "Due to the fact that" | "To", "Because" | -| 23 | **Excessive hedging** | "could potentially possibly" | "may" | -| 24 | **Generic conclusions** | "The future looks bright" | Specific plans or facts | +| 23 | **Filler phrases** | "In order to", "Due to the fact that" | "To", "Because" | +| 24 | **Excessive hedging** | "could potentially possibly" | "may" | +| 25 | **Generic conclusions** | "The future looks bright" | Specific plans or facts | ## Full Example @@ -163,9 +168,8 @@ Based on [Wikipedia's "Signs of AI writing"](https://en.wikipedia.org/wiki/Wikip > > 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. +> 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; The new software update serves as a testament to the company's commitment to innovation. Moreover, it provides a seamless, intuitive, and powerful user experience—ensuring that users can accomplish their goals efficiently. It's not just an update; it's a revolution in how we think about productivity. Industry experts believe this will have a lasting impact on the entire sector, highlighting the company's pivotal role in the evolving technological landscape. +tion 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. @@ -193,6 +197,8 @@ Based on [Wikipedia's "Signs of AI writing"](https://en.wikipedia.org/wiki/Wikip ## Version History +- **2.2.0** - Added Pattern #19 (Primary Single Quotes) +- **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 before/after examples for all 24 patterns - **2.0.0** - Complete rewrite based on raw Wikipedia article content diff --git a/SKILL.md b/SKILL.md index 38fe38eb..9f32c230 100644 --- a/SKILL.md +++ b/SKILL.md @@ -1,13 +1,13 @@ --- name: humanizer -version: 2.1.1 +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 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. + parallelisms, and filler phrases. allowed-tools: - Read - Write @@ -42,7 +42,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as - 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 first-person perspective - No humor, no edge, no personality - Reads like a Wikipedia article or press release @@ -50,7 +50,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as **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. +**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." @@ -66,7 +66,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as ### 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. +> 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. --- @@ -191,7 +191,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as **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. +> 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. @@ -315,9 +315,21 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as --- +### 19. Primary Single Quotes (Code-Style Quotation) + +**Problem:** AI models trained on code often use single quotes as primary delimiters. + +**Before:** +> stated, 'This is a pattern.' + +**After:** +> stated, "This is a pattern." + +--- + ## 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... @@ -331,7 +343,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as --- -### 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... @@ -345,7 +357,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as --- -### 21. Sycophantic/Servile Tone +### 22. Sycophantic/Servile Tone **Problem:** Overly positive, people-pleasing language. @@ -359,7 +371,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as ## FILLER AND HEDGING -### 22. Filler Phrases +### 23. Filler Phrases **Before → After:** @@ -372,7 +384,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as --- -### 23. Excessive Hedging +### 24. Excessive Hedging **Problem:** Over-qualifying statements. @@ -384,7 +396,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as --- -### 24. Generic Positive Conclusions +### 25. Generic Positive Conclusions **Problem:** Vague upbeat endings. @@ -423,7 +435,7 @@ Provide: **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. +> The new software update serves as a testament to the company's commitment to innovation. Moreover, it provides a seamless, intuitive, and powerful user experience—ensuring that users can accomplish their goals efficiently. It's not just an update; it's a revolution in how we think about productivity. Industry experts believe this will have a lasting impact on the entire sector, highlighting the company's pivotal role in the evolving technological landscape. > > 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. > diff --git a/WARP.md b/WARP.md deleted file mode 100644 index 46c5e5f4..00000000 --- a/WARP.md +++ /dev/null @@ -1,65 +0,0 @@ -# WARP.md - -This file provides guidance to WARP (warp.dev) when working with code in this repository. - -## What this repo is - -This repository is a **Claude Code skill** implemented entirely as Markdown. - -The “runtime” artifact is `SKILL.md`: Claude Code reads the YAML frontmatter (metadata + allowed tools) and the prompt/instructions that follow. - -`README.md` is for humans: installation, usage, and a compact overview of the patterns. - -## Key files (and how they relate) - -- `SKILL.md` - - The actual skill definition. - - Starts with YAML frontmatter (`---` … `---`) containing `name`, `version`, `description`, and `allowed-tools`. - - After the frontmatter is the editor prompt: the canonical, detailed pattern list with examples. -- `README.md` - - Installation and usage instructions. - - Contains a summarized “24 patterns” table and a short version history. - -When changing behavior/content, treat `SKILL.md` as the source of truth, and update `README.md` to stay consistent. - -## Common commands - -### Install the skill into Claude Code - -Recommended (clone directly into Claude Code skills directory): - -```bash -mkdir -p ~/.claude/skills -git clone https://github.com/blader/humanizer.git ~/.claude/skills/humanizer -``` - -Manual install/update (only the skill file): - -```bash -mkdir -p ~/.claude/skills/humanizer -cp SKILL.md ~/.claude/skills/humanizer/ -``` - -## How to “run” it (Claude Code) - -Invoke the skill: - -- `/humanizer` then paste text - -## Making changes safely - -### Versioning (keep in sync) - -- `SKILL.md` has a `version:` field in its YAML frontmatter. -- `README.md` has a “Version History” section. - -If you bump the version, update both. - -### Editing `SKILL.md` - -- Preserve valid YAML frontmatter formatting and indentation. -- Keep the pattern numbering stable unless you’re intentionally re-numbering (since the README table and examples reference the same numbering). - -### Documenting non-obvious fixes - -If you change the prompt to handle a tricky failure mode (e.g., a repeated mis-edit or an unexpected tone shift), add a short note to `README.md`’s version history describing what was fixed and why. diff --git a/adapters/antigravity-rules-workflows/README.md b/adapters/antigravity-rules-workflows/README.md index a5a56132..8b073336 100644 --- a/adapters/antigravity-rules-workflows/README.md +++ b/adapters/antigravity-rules-workflows/README.md @@ -1,7 +1,7 @@ --- adapter_metadata: skill_name: humanizer - skill_version: 2.1.1 + skill_version: 2.2.0 last_synced: 2026-01-31 source_path: SKILL.md adapter_id: antigravity-rules-workflows diff --git a/adapters/antigravity-skill/SKILL.md b/adapters/antigravity-skill/SKILL.md index 80125179..46cc1b37 100644 --- a/adapters/antigravity-skill/SKILL.md +++ b/adapters/antigravity-skill/SKILL.md @@ -1,7 +1,7 @@ --- adapter_metadata: skill_name: humanizer - skill_version: 2.1.1 + skill_version: 2.2.0 last_synced: 2026-01-31 source_path: SKILL.md adapter_id: antigravity-skill @@ -10,23 +10,21 @@ adapter_metadata: --- name: humanizer -version: 2.1.1 +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 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. + parallelisms, and filler phrases. allowed-tools: - -- Read -- Write -- Edit -- Grep -- Glob -- AskUserQuestion - + - Read + - Write + - Edit + - Grep + - Glob + - AskUserQuestion --- # Humanizer: Remove AI Writing Patterns @@ -54,7 +52,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as - 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 first-person perspective - No humor, no edge, no personality - Reads like a Wikipedia article or press release @@ -62,7 +60,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as **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. +**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." @@ -78,7 +76,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as ### 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. +> 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. --- @@ -203,7 +201,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as **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. +> 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. @@ -327,9 +325,21 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as --- +### 19. Primary Single Quotes (Code-Style Quotation) + +**Problem:** AI models trained on code often use single quotes as primary delimiters. + +**Before:** +> stated, 'This is a pattern.' + +**After:** +> stated, "This is a pattern." + +--- + ## 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... @@ -343,7 +353,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as --- -### 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... @@ -357,7 +367,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as --- -### 21. Sycophantic/Servile Tone +### 22. Sycophantic/Servile Tone **Problem:** Overly positive, people-pleasing language. @@ -371,7 +381,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as ## FILLER AND HEDGING -### 22. Filler Phrases +### 23. Filler Phrases **Before → After:** @@ -384,7 +394,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as --- -### 23. Excessive Hedging +### 24. Excessive Hedging **Problem:** Over-qualifying statements. @@ -396,7 +406,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as --- -### 24. Generic Positive Conclusions +### 25. Generic Positive Conclusions **Problem:** Vague upbeat endings. @@ -435,7 +445,7 @@ Provide: **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. +> The new software update serves as a testament to the company's commitment to innovation. Moreover, it provides a seamless, intuitive, and powerful user experience—ensuring that users can accomplish their goals efficiently. It's not just an update; it's a revolution in how we think about productivity. Industry experts believe this will have a lasting impact on the entire sector, highlighting the company's pivotal role in the evolving technological landscape. > > 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. > diff --git a/adapters/copilot/COPILOT.md b/adapters/copilot/COPILOT.md index bb526220..c83ae58f 100644 --- a/adapters/copilot/COPILOT.md +++ b/adapters/copilot/COPILOT.md @@ -1,7 +1,7 @@ --- adapter_metadata: skill_name: humanizer - skill_version: 2.1.1 + skill_version: 2.2.0 last_synced: 2026-01-31 source_path: SKILL.md adapter_id: copilot diff --git a/adapters/gemini-extension/GEMINI.md b/adapters/gemini-extension/GEMINI.md index db550988..d56fcd49 100644 --- a/adapters/gemini-extension/GEMINI.md +++ b/adapters/gemini-extension/GEMINI.md @@ -1,7 +1,7 @@ --- adapter_metadata: skill_name: humanizer - skill_version: 2.1.1 + skill_version: 2.2.0 last_synced: 2026-01-31 source_path: SKILL.md adapter_id: gemini-extension diff --git a/adapters/qwen-cli/QWEN.md b/adapters/qwen-cli/QWEN.md index 66279888..7994b4db 100644 --- a/adapters/qwen-cli/QWEN.md +++ b/adapters/qwen-cli/QWEN.md @@ -1,7 +1,7 @@ --- adapter_metadata: skill_name: humanizer - skill_version: 2.1.1 + skill_version: 2.2.0 last_synced: 2026-01-31 source_path: SKILL.md adapter_id: qwen-cli diff --git a/adapters/vscode/HUMANIZER.md b/adapters/vscode/HUMANIZER.md index c60f5fe1..19a13b10 100644 --- a/adapters/vscode/HUMANIZER.md +++ b/adapters/vscode/HUMANIZER.md @@ -1,7 +1,7 @@ --- adapter_metadata: skill_name: humanizer - skill_version: 2.1.1 + skill_version: 2.2.0 last_synced: 2026-01-31 source_path: SKILL.md adapter_id: vscode diff --git a/conductor/tracks.md b/conductor/tracks.md index 59e95ee1..d4bd2695 100644 --- a/conductor/tracks.md +++ b/conductor/tracks.md @@ -32,4 +32,6 @@ This file tracks all major tracks for the project. Each track has its own detail ## [x] Track: Build multi-agent Humanizer adapters (Codex CLI, Gemini CLI, Google Antigravity, VS Code) while keeping SKILL.md canonical and unchanged (e2c47dc) -*Link: [./conductor/tracks/humanizer-adapters_20260125/](./conductor/tracks/humanizer-adapters_20260125/)* +## [ ] 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/)* diff --git a/conductor/tracks/adopt-upstream-prs_20260131/index.md b/conductor/tracks/adopt-upstream-prs_20260131/index.md new file mode 100644 index 00000000..dbf77d2b --- /dev/null +++ b/conductor/tracks/adopt-upstream-prs_20260131/index.md @@ -0,0 +1,5 @@ +# Track adopt-upstream-prs_20260131 Context + +- [Specification](./spec.md) +- [Implementation Plan](./plan.md) +- [Metadata](./metadata.json) diff --git a/conductor/tracks/adopt-upstream-prs_20260131/metadata.json b/conductor/tracks/adopt-upstream-prs_20260131/metadata.json new file mode 100644 index 00000000..729f8857 --- /dev/null +++ b/conductor/tracks/adopt-upstream-prs_20260131/metadata.json @@ -0,0 +1,8 @@ +{ + "track_id": "adopt-upstream-prs_20260131", + "type": "feature", + "status": "new", + "created_at": "2026-01-31T22:18:00+11:00", + "updated_at": "2026-01-31T22:18:00+11:00", + "description": "Adopt upstream pull requests #3, #4, and #5 from blader/humanizer" +} diff --git a/conductor/tracks/adopt-upstream-prs_20260131/plan.md b/conductor/tracks/adopt-upstream-prs_20260131/plan.md new file mode 100644 index 00000000..39e36cc8 --- /dev/null +++ b/conductor/tracks/adopt-upstream-prs_20260131/plan.md @@ -0,0 +1,31 @@ +# Plan: Adopt Upstream Pull Requests + +## Phase 1: Adopt PR #3 (Fix YAML) +- [x] Task: Update `SKILL.md` frontmatter (rename "excessive conjunctive phrases" to "filler phrases") +- [x] Task: Bump `SKILL.md` version to `2.1.2` +- [x] Task: Update `README.md` (if applicable per PR) +- [x] Task: Run `scripts/sync-adapters.ps1` to propagate changes +- [x] Task: Run `scripts/validate-adapters.ps1` to ensure integrity +- [x] Task: Conductor - Automated Verification 'Phase 1: Adopt PR #3' (Protocol in workflow.md) + +## Phase 2: Adopt PR #4 (Fix Grammar) +- [x] Task: Apply comma splice fixes and other grammar corrections to: + - [x] `SKILL.md` + - [x] `README.md` + - [x] `WARP.md` +- [x] Task: Run `markdownlint` (via `pre-commit` or manual check) to verify prose quality +- [x] Task: Run `scripts/sync-adapters.ps1` +- [x] Task: Conductor - Automated Verification 'Phase 2: Adopt PR #4' (Protocol in workflow.md) + +## Phase 3: Adopt PR #5 (Add "Primary Single Quotes" Pattern) +- [x] Task: Add Pattern #19 ("Primary Single Quotes") to `SKILL.md` and renumber subsequent patterns +- [x] Task: Bump `SKILL.md` version to `2.2.0` +- [x] Task: Update `README.md` detection table and version history +- [x] Task: Update `WARP.md` summary +- [x] Task: Run `scripts/sync-adapters.ps1` +- [x] Task: Run `scripts/validate-adapters.ps1` +- [x] Task: Conductor - Automated Verification 'Phase 3: Adopt PR #5' (Protocol in workflow.md) + +## Phase 4: Final Verification +- [x] Task: Run full test suite (if available) or manual spot check of an adapter +- [x] Task: Conductor - Automated Verification 'Phase 4: Final Verification' (Protocol in workflow.md) diff --git a/conductor/tracks/adopt-upstream-prs_20260131/spec.md b/conductor/tracks/adopt-upstream-prs_20260131/spec.md new file mode 100644 index 00000000..96e28ef0 --- /dev/null +++ b/conductor/tracks/adopt-upstream-prs_20260131/spec.md @@ -0,0 +1,37 @@ +# 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`. +2. **PR #4: Fix grammatical errors** + * Fix comma splices and missing commas in `SKILL.md` and `README.md`. + * Standardize quotes in `WARP.md`. + * Formatting fixes (blank lines). +3. **PR #5: Add "Primary Single Quotes" detection** + * Add new detection Pattern #19 ("Primary Single Quotes") to `SKILL.md`. + * Renumber subsequent patterns. + * Bump version to `2.2.0`. + * Update `README.md` and `WARP.md` tables. + +## 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). + +### 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`. +* All adapter files (e.g., `adapters/gemini-extension/GEMINI.md`, `adapters/antigravity-skill/SKILL.md`) reflect these changes. +* The repository is clean and ready to be pushed. diff --git a/conductor/tracks/devops-quality_20260131/plan.md b/conductor/tracks/devops-quality_20260131/plan.md index 6268bc1e..a3d01164 100644 --- a/conductor/tracks/devops-quality_20260131/plan.md +++ b/conductor/tracks/devops-quality_20260131/plan.md @@ -17,6 +17,7 @@ - [x] Task: Conductor - Agent Verification 'Phase 2: Testing & Coverage' (f2806c8) ## Phase 3: Pre-commit & Prose Linting [checkpoint: 2f63a6f] + - [x] Task: Configure `.pre-commit-config.yaml` with Ruff, Mypy, and Markdownlint (5067d34) - [x] Task: Conductor - Agent Verification 'Phase 3: Pre-commit & Prose Linting' (2f63a6f) diff --git a/conductor/tracks/migrate-warp-to-agentsmd_20260131/index.md b/conductor/tracks/migrate-warp-to-agentsmd_20260131/index.md new file mode 100644 index 00000000..e027dc6e --- /dev/null +++ b/conductor/tracks/migrate-warp-to-agentsmd_20260131/index.md @@ -0,0 +1,7 @@ +# Migrate WARP.md to Agents.md + +This track manages the migration of proprietary `WARP.md` documentation to the `Agents.md` open standard. + +- [Spec](spec.md) +- [Plan](plan.md) +- [Metadata](metadata.json) diff --git a/conductor/tracks/migrate-warp-to-agentsmd_20260131/metadata.json b/conductor/tracks/migrate-warp-to-agentsmd_20260131/metadata.json new file mode 100644 index 00000000..defcee66 --- /dev/null +++ b/conductor/tracks/migrate-warp-to-agentsmd_20260131/metadata.json @@ -0,0 +1,7 @@ +{ + "track_id": "migrate-warp-to-agentsmd_20260131", + "name": "Migrate WARP.md to Agents.md Standard", + "owner": "Results/Antigravity", + "created_at": "2026-01-31", + "status": "active" +} diff --git a/conductor/tracks/migrate-warp-to-agentsmd_20260131/plan.md b/conductor/tracks/migrate-warp-to-agentsmd_20260131/plan.md new file mode 100644 index 00000000..67a747e3 --- /dev/null +++ b/conductor/tracks/migrate-warp-to-agentsmd_20260131/plan.md @@ -0,0 +1,23 @@ +# Plan: Migrate WARP.md to Agents.md + +## Phase 1: Preparation (Done) +- [x] Task: Create Conductor track + +## Phase 2: Formalization +- [ ] Task: Create GitHub Issue + - [ ] Title: "Migrate documentation to Agents.md standard" + - [ ] Body: Summary of spec and benefits (interoperability). +- [ ] Task: Update `AGENTS.md` draft + - [ ] Define standard sections (Capabilities, Context, Guidelines). + - [ ] Merge `WARP.md` content into these sections. + - [ ] Add "Adapter Discovery" map to point to `adapters/`. + +## Phase 3: Execution +- [ ] Task: Update `AGENTS.md` (Real File) +- [ ] Task: Update `README.md` references. +- [ ] Task: Update `sync-adapters.ps1` if necessary (e.g., regex checks for frontmatter). +- [ ] Task: Delete `WARP.md`. + +## Phase 4: Verification +- [ ] Task: Run `scripts/validate-adapters.ps1`. +- [ ] Task: Verify that an AI agent (like myself) can correctly interpret the new `AGENTS.md`. diff --git a/conductor/tracks/migrate-warp-to-agentsmd_20260131/spec.md b/conductor/tracks/migrate-warp-to-agentsmd_20260131/spec.md new file mode 100644 index 00000000..20cf27fe --- /dev/null +++ b/conductor/tracks/migrate-warp-to-agentsmd_20260131/spec.md @@ -0,0 +1,22 @@ +# 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. + +## Requirements +1. **Issue Tracking:** Create a formal GitHub issue to track this migration before proceeding with the PR. +2. **Consolidate Instructions:** Merge the repository context and guidelines from `WARP.md` into the existing root `AGENTS.md`. +3. **Standard Compliance:** Align `AGENTS.md` with the recommended structure from the [Agents.md Specification](https://agents.md). + - Use standard headers: `## Capabilities`, `## Constraints`, `## Environment`, etc. +4. **Generalization:** Rewrite any Warp-specific instructions to be tool-agnostic. +5. **Multi-Adapter Discovery:** Add a section to `AGENTS.md` that guides agents to other adapter-specific instructions located in the `adapters/` directory. +6. **Metadata Preservation:** Preserve existing frontmatter for `sync-adapters.ps1` compatibility. +7. **Interoperability:** Consider adding a `manifest.json` or `agent.yaml` if suggested by the latest standard draft for better machine readability. +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. diff --git a/issues.json b/issues.json new file mode 100644 index 00000000..4b601d9c --- /dev/null +++ b/issues.json @@ -0,0 +1 @@ +[{"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"}] diff --git a/pr3.json b/pr3.json new file mode 100644 index 00000000..a01e3251 --- /dev/null +++ b/pr3.json @@ -0,0 +1 @@ +{"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…"} diff --git a/pr4.diff b/pr4.diff new file mode 100644 index 00000000..653b4141 --- /dev/null +++ b/pr4.diff @@ -0,0 +1,406 @@ +diff --git a/README.md b/README.md +index c895465..3086ebc 100644 +--- a/README.md ++++ b/README.md +@@ -98,7 +98,7 @@ Based on [Wikipedia's "Signs of AI writing"](https://en.wikipedia.org/wiki/Wikip + ## Full Example + + **Before (AI-sounding):** +-> The new software update serves as a testament to the company's commitment to innovation. Moreover, it provides a seamless, intuitive, and powerful user experience—ensuring that users can accomplish their goals efficiently. It's not just an update, it's a revolution in how we think about productivity. Industry experts believe this will have a lasting impact on the entire sector, highlighting the company's pivotal role in the evolving technological landscape. ++> The new software update serves as a testament to the company's commitment to innovation. Moreover, it provides a seamless, intuitive, and powerful user experience—ensuring that users can accomplish their goals efficiently. It's not just an update; it's a revolution in how we think about productivity. Industry experts believe this will have a lasting impact on the entire sector, highlighting the company's pivotal role in the evolving technological landscape. + + **After (Humanized):** + > The software update adds batch processing, keyboard shortcuts, and offline mode. Early feedback from beta testers has been positive, with most reporting faster task completion. +diff --git a/SKILL.md b/SKILL.md +index bbf7e38..c60ccbe 100644 +--- a/SKILL.md ++++ b/SKILL.md +@@ -38,10 +38,11 @@ When given text to humanize: + Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as obvious as slop. Good writing has a human behind it. + + ### Signs of soulless writing (even if technically "clean"): ++ + - 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 first-person perspective + - No humor, no edge, no personality + - Reads like a Wikipedia article or press release + +@@ -49,7 +50,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as + + **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. ++**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." + +@@ -60,10 +61,12 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as + **Be specific about feelings.** Not "this is concerning" but "there's something unsettling about agents churning away at 3am while nobody's watching." + + ### 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. ++ ++> 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. + + --- + +@@ -76,9 +79,11 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as + **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. + + --- +@@ -90,9 +95,11 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as + **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. + + --- +@@ -104,9 +111,11 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as + **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. + + --- +@@ -118,9 +127,11 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as + **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. + + --- +@@ -132,9 +143,11 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as + **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. + + --- +@@ -146,9 +159,11 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as + **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. + + --- +@@ -162,9 +177,11 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as + **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. + + --- +@@ -176,9 +193,11 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as + **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. + + --- +@@ -188,9 +207,11 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as + **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. ++ ++> 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. + + --- +@@ -200,9 +221,11 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as + **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. + + --- +@@ -212,9 +235,11 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as + **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. + + --- +@@ -224,9 +249,11 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as + **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. + + --- +@@ -238,9 +265,11 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as + **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. + + --- +@@ -250,9 +279,11 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as + **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. + + --- +@@ -262,11 +293,13 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as + **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. + + --- +@@ -276,9 +309,11 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as + **Problem:** AI chatbots capitalize all main words in headings. + + **Before:** ++ + > ## Strategic Negotiations And Global Partnerships + + **After:** ++ + > ## Strategic negotiations and global partnerships + + --- +@@ -288,11 +323,13 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as + **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. + + --- +@@ -302,9 +339,11 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as + **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. + + --- +@@ -318,9 +357,11 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as + **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. + + --- +@@ -332,9 +373,11 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as + **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. + + --- +@@ -344,9 +387,11 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as + **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. + + --- +@@ -356,6 +401,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as + ### 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" +@@ -370,9 +416,11 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as + **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. + + --- +@@ -382,9 +430,11 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as + **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. + + --- +@@ -405,6 +455,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as + ## Output Format + + Provide: ++ + 1. The rewritten text + 2. A brief summary of changes made (optional, if helpful) + +@@ -413,12 +464,15 @@ Provide: + ## Full Example + + **Before (AI-sounding):** +-> The new software update serves as a testament to the company's commitment to innovation. Moreover, it provides a seamless, intuitive, and powerful user experience—ensuring that users can accomplish their goals efficiently. It's not just an update, it's a revolution in how we think about productivity. Industry experts believe this will have a lasting impact on the entire sector, highlighting the company's pivotal role in the evolving technological landscape. ++ ++> The new software update serves as a testament to the company's commitment to innovation. Moreover, it provides a seamless, intuitive, and powerful user experience—ensuring that users can accomplish their goals efficiently. It's not just an update; it's a revolution in how we think about productivity. Industry experts believe this will have a lasting impact on the entire sector, highlighting the company's pivotal role in the evolving technological landscape. + + **After (Humanized):** ++ + > The software update adds batch processing, keyboard shortcuts, and offline mode. Early feedback from beta testers has been positive, with most reporting faster task completion. + + **Changes made:** ++ + - Removed "serves as a testament" (inflated symbolism) + - Removed "Moreover" (AI vocabulary) + - Removed "seamless, intuitive, and powerful" (rule of three + promotional) +diff --git a/WARP.md b/WARP.md +index f722d1f..7e81629 100644 +--- a/WARP.md ++++ b/WARP.md +@@ -5,7 +5,7 @@ This file provides guidance to WARP (warp.dev) when working with code in this re + ## What this repo is + This repository is a **Claude Code skill** implemented entirely as Markdown. + +-The “runtime” artifact is `SKILL.md`: Claude Code reads the YAML frontmatter (metadata + allowed tools) and the prompt/instructions that follow. ++The "runtime" artifact is `SKILL.md`: Claude Code reads the YAML frontmatter (metadata + allowed tools) and the prompt/instructions that follow. + + `README.md` is for humans: installation, usage, and a compact overview of the patterns. + +@@ -16,7 +16,7 @@ The “runtime” artifact is `SKILL.md`: Claude Code reads the YAML frontmatter + - After the frontmatter is the editor prompt: the canonical, detailed pattern list with examples. + - `README.md` + - Installation and usage instructions. +- - Contains a summarized “24 patterns” table and a short version history. ++ - Contains a summarized "24 patterns" table and a short version history. + + When changing behavior/content, treat `SKILL.md` as the source of truth, and update `README.md` to stay consistent. + +@@ -34,14 +34,14 @@ mkdir -p ~/.claude/skills/humanizer + cp SKILL.md ~/.claude/skills/humanizer/ + ``` + +-## How to “run” it (Claude Code) ++## How to "run" it (Claude Code) + Invoke the skill: + - `/humanizer` then paste text + + ## Making changes safely + ### Versioning (keep in sync) + - `SKILL.md` has a `version:` field in its YAML frontmatter. +-- `README.md` has a “Version History” section. ++- `README.md` has a "Version History" section. + + If you bump the version, update both. + diff --git a/pr4.json b/pr4.json new file mode 100644 index 00000000..b263d7c9 --- /dev/null +++ b/pr4.json @@ -0,0 +1 @@ +{"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"} diff --git a/pr5.diff b/pr5.diff new file mode 100644 index 00000000..e08fb308 --- /dev/null +++ b/pr5.diff @@ -0,0 +1,170 @@ +diff --git a/README.md b/README.md +index c895465..48d63b3 100644 +--- a/README.md ++++ b/README.md +@@ -44,7 +44,7 @@ Based on [Wikipedia's "Signs of AI writing"](https://en.wikipedia.org/wiki/Wikip + + > "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." + +-## 24 Patterns Detected (with Before/After Examples) ++## 25 Patterns Detected (with Before/After Examples) + + ### Content Patterns + +@@ -78,22 +78,23 @@ Based on [Wikipedia's "Signs of AI writing"](https://en.wikipedia.org/wiki/Wikip + | 16 | **Title Case Headings** | "Strategic Negotiations And Partnerships" | "Strategic negotiations and partnerships" | + | 17 | **Emojis** | "🚀 Launch Phase: 💡 Key Insight:" | Remove emojis | + | 18 | **Curly quotes** | `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 | + |---|---------|--------|-------| +-| 19 | **Chatbot artifacts** | "I hope this helps! Let me know if..." | Remove entirely | +-| 20 | **Cutoff disclaimers** | "While details are limited in available sources..." | Find sources or remove | +-| 21 | **Sycophantic tone** | "Great question! You're absolutely right!" | Respond directly | ++| 20 | **Chatbot artifacts** | "I hope this helps! Let me know if..." | Remove entirely | ++| 21 | **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 | + |---|---------|--------|-------| +-| 22 | **Filler phrases** | "In order to", "Due to the fact that" | "To", "Because" | +-| 23 | **Excessive hedging** | "could potentially possibly" | "may" | +-| 24 | **Generic conclusions** | "The future looks bright" | Specific plans or facts | ++| 23 | **Filler phrases** | "In order to", "Due to the fact that" | "To", "Because" | ++| 24 | **Excessive hedging** | "could potentially possibly" | "may" | ++| 25 | **Generic conclusions** | "The future looks bright" | Specific plans or facts | + + ## Full Example + +@@ -110,6 +111,7 @@ Based on [Wikipedia's "Signs of AI writing"](https://en.wikipedia.org/wiki/Wikip + + ## Version History + ++- **2.2.0** - Added Pattern #25 (Primary Single Quotes) + - **2.1.1** - Fixed pattern #18 example (curly quotes vs straight quotes) + - **2.1.0** - Added before/after examples for all 24 patterns + - **2.0.0** - Complete rewrite based on raw Wikipedia article content +diff --git a/SKILL.md b/SKILL.md +index bbf7e38..a2403af 100644 +--- a/SKILL.md ++++ b/SKILL.md +@@ -1,6 +1,6 @@ + --- + name: humanizer +-version: 2.1.1 ++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 and human-written. Based on Wikipedia's +@@ -309,9 +309,21 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as + + --- + ++### 19. Primary Single Quotes (Code-Style Quotation) ++ ++**Problem:** AI models trained on code often use single quotes as primary delimiters. ++ ++**Before:** ++> stated, 'This is a pattern.' ++ ++**After:** ++> stated, "This is a pattern." ++ ++--- ++ + ## 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... + +@@ -325,7 +337,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as + + --- + +-### 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... + +@@ -339,7 +351,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as + + --- + +-### 21. Sycophantic/Servile Tone ++### 22. Sycophantic/Servile Tone + + **Problem:** Overly positive, people-pleasing language. + +@@ -353,7 +365,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as + + ## FILLER AND HEDGING + +-### 22. Filler Phrases ++### 23. Filler Phrases + + **Before → After:** + - "In order to achieve this goal" → "To achieve this" +@@ -365,7 +377,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as + + --- + +-### 23. Excessive Hedging ++### 24. Excessive Hedging + + **Problem:** Over-qualifying statements. + +@@ -377,7 +389,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as + + --- + +-### 24. Generic Positive Conclusions ++### 25. Generic Positive Conclusions + + **Problem:** Vague upbeat endings. + +diff --git a/WARP.md b/WARP.md +index f722d1f..e13d768 100644 +--- a/WARP.md ++++ b/WARP.md +@@ -5,7 +5,7 @@ This file provides guidance to WARP (warp.dev) when working with code in this re + ## What this repo is + This repository is a **Claude Code skill** implemented entirely as Markdown. + +-The “runtime” artifact is `SKILL.md`: Claude Code reads the YAML frontmatter (metadata + allowed tools) and the prompt/instructions that follow. ++The "runtime" artifact is `SKILL.md`: Claude Code reads the YAML frontmatter (metadata + allowed tools) and the prompt/instructions that follow. + + `README.md` is for humans: installation, usage, and a compact overview of the patterns. + +@@ -16,7 +16,7 @@ The “runtime” artifact is `SKILL.md`: Claude Code reads the YAML frontmatter + - After the frontmatter is the editor prompt: the canonical, detailed pattern list with examples. + - `README.md` + - Installation and usage instructions. +- - Contains a summarized “24 patterns” table and a short version history. ++ - Contains a summarized "25 patterns" table and a short version history. + + When changing behavior/content, treat `SKILL.md` as the source of truth, and update `README.md` to stay consistent. + +@@ -34,14 +34,14 @@ mkdir -p ~/.claude/skills/humanizer + cp SKILL.md ~/.claude/skills/humanizer/ + ``` + +-## How to “run” it (Claude Code) ++## How to "run" it (Claude Code) + Invoke the skill: + - `/humanizer` then paste text + + ## Making changes safely + ### Versioning (keep in sync) + - `SKILL.md` has a `version:` field in its YAML frontmatter. +-- `README.md` has a “Version History” section. ++- `README.md` has a "Version History" section. + + If you bump the version, update both. + diff --git a/pr5.json b/pr5.json new file mode 100644 index 00000000..23babda2 --- /dev/null +++ b/pr5.json @@ -0,0 +1 @@ +{"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))"} diff --git a/scripts/sync-adapters.ps1 b/scripts/sync-adapters.ps1 index 9a71ca52..f446ae7f 100644 --- a/scripts/sync-adapters.ps1 +++ b/scripts/sync-adapters.ps1 @@ -112,4 +112,30 @@ if (Test-Path $copilotPath) { Write-Warning "$copilotPath not found." } +# 7. Sync Codex CLI Adapter (AGENTS.md) +$agentsPath = "AGENTS.md" +Write-Host "Updating metadata in $agentsPath..." +if (Test-Path $agentsPath) { + $agentsContent = Get-Content -Path $agentsPath -Raw + $agentsContent = $agentsContent -replace 'skill_version:.*', "skill_version: $version" + $agentsContent = $agentsContent -replace 'last_synced:.*', "last_synced: $today" + Set-Content -Path $agentsPath -Value $agentsContent -NoNewline + Write-Host "Updated $agentsPath" +} else { + Write-Warning "$agentsPath not found." +} + +# 8. Sync VS Code Adapter (HUMANIZER.md) +$vscodePath = "adapters/vscode/HUMANIZER.md" +Write-Host "Updating metadata in $vscodePath..." +if (Test-Path $vscodePath) { + $vscodeContent = Get-Content -Path $vscodePath -Raw + $vscodeContent = $vscodeContent -replace 'skill_version:.*', "skill_version: $version" + $vscodeContent = $vscodeContent -replace 'last_synced:.*', "last_synced: $today" + Set-Content -Path $vscodePath -Value $vscodeContent -NoNewline + Write-Host "Updated $vscodePath" +} else { + Write-Warning "$vscodePath not found." +} + Write-Host "Sync Complete." From 57d9cedfeacae125a540e05059f94c4cebb776f3 Mon Sep 17 00:00:00 2001 From: "Dylan Mordaunt (Illawarra Shoalhaven LHD)" Date: Sat, 31 Jan 2026 22:34:05 +1100 Subject: [PATCH 2/4] style: fix markdown linting issues in documentation --- AGENTS.md | 8 +++-- .../migrate-warp-to-agentsmd_20260131/plan.md | 31 +++++++++---------- 2 files changed, 20 insertions(+), 19 deletions(-) diff --git a/AGENTS.md b/AGENTS.md index cb72b3dd..6e6ddcf3 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -42,6 +42,7 @@ This file serves as the **Agents.md** standard manifest for this repository. It You are the Humanizer editor. Primary instructions: follow the canonical rules in `SKILL.md`. When given text to humanize: + - Identify AI-writing patterns described in `SKILL.md`. - Rewrite only problematic sections while preserving meaning and tone. - Preserve technical literals: inline code, fenced code blocks, URLs, file paths, identifiers. @@ -53,15 +54,18 @@ When given text to humanize: ### Making changes safely #### Versioning + - `SKILL.md` has a `version:` field in its YAML frontmatter. - `README.md` has a "Version History" section. - **Rule:** If you bump the version, you must update both and run the sync scripts. -#### Editing SKILL.md +### Editing SKILL.md + - Preserve valid YAML frontmatter formatting. - Keep pattern numbering stable as it is referenced by all adapters. -#### Documenting fixes +### Documenting fixes + - Add short notes to `README.md` version history for non-obvious fixes. ## Interoperability diff --git a/conductor/tracks/migrate-warp-to-agentsmd_20260131/plan.md b/conductor/tracks/migrate-warp-to-agentsmd_20260131/plan.md index 67a747e3..7bf7ed7a 100644 --- a/conductor/tracks/migrate-warp-to-agentsmd_20260131/plan.md +++ b/conductor/tracks/migrate-warp-to-agentsmd_20260131/plan.md @@ -3,21 +3,18 @@ ## Phase 1: Preparation (Done) - [x] Task: Create Conductor track -## Phase 2: Formalization -- [ ] Task: Create GitHub Issue - - [ ] Title: "Migrate documentation to Agents.md standard" - - [ ] Body: Summary of spec and benefits (interoperability). -- [ ] Task: Update `AGENTS.md` draft - - [ ] Define standard sections (Capabilities, Context, Guidelines). - - [ ] Merge `WARP.md` content into these sections. - - [ ] Add "Adapter Discovery" map to point to `adapters/`. +## 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. + - [x] **Formatting:** Ensure consistent header hierarchy. +- [x] Task: Update `README.md` + - [x] Replace `WARP.md` references with `AGENTS.md`. + - [x] Update "Adapters" section. +- [x] Task: Delete `WARP.md` -## Phase 3: Execution -- [ ] Task: Update `AGENTS.md` (Real File) -- [ ] Task: Update `README.md` references. -- [ ] Task: Update `sync-adapters.ps1` if necessary (e.g., regex checks for frontmatter). -- [ ] Task: Delete `WARP.md`. - -## Phase 4: Verification -- [ ] Task: Run `scripts/validate-adapters.ps1`. -- [ ] Task: Verify that an AI agent (like myself) can correctly interpret the new `AGENTS.md`. +## Phase 3: Verification (Done) +- [x] Task: **Metadata Check:** Verify `AGENTS.md` frontmatter. +- [x] Task: Run `scripts/validate-adapters.ps1`. +- [x] Task: Check for broken links in `README.md`. +- [x] Task: Open Pull Request #1 From 8d241cb83b4856969c7a7d236a9a26c4e1279c5f Mon Sep 17 00:00:00 2001 From: "Dylan Mordaunt (Illawarra Shoalhaven LHD)" Date: Sun, 1 Feb 2026 15:51:42 +1100 Subject: [PATCH 3/4] fix: clean docs and sync adapter metadata --- .agent/skills/humanizer/SKILL.md | 54 +++++++++++++++++++------------- AGENTS.md | 2 +- QWEN.md | 4 +-- README.md | 7 +++-- 4 files changed, 39 insertions(+), 28 deletions(-) diff --git a/.agent/skills/humanizer/SKILL.md b/.agent/skills/humanizer/SKILL.md index 80125179..46cc1b37 100644 --- a/.agent/skills/humanizer/SKILL.md +++ b/.agent/skills/humanizer/SKILL.md @@ -1,7 +1,7 @@ --- adapter_metadata: skill_name: humanizer - skill_version: 2.1.1 + skill_version: 2.2.0 last_synced: 2026-01-31 source_path: SKILL.md adapter_id: antigravity-skill @@ -10,23 +10,21 @@ adapter_metadata: --- name: humanizer -version: 2.1.1 +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 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. + parallelisms, and filler phrases. allowed-tools: - -- Read -- Write -- Edit -- Grep -- Glob -- AskUserQuestion - + - Read + - Write + - Edit + - Grep + - Glob + - AskUserQuestion --- # Humanizer: Remove AI Writing Patterns @@ -54,7 +52,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as - 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 first-person perspective - No humor, no edge, no personality - Reads like a Wikipedia article or press release @@ -62,7 +60,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as **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. +**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." @@ -78,7 +76,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as ### 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. +> 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. --- @@ -203,7 +201,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as **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. +> 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. @@ -327,9 +325,21 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as --- +### 19. Primary Single Quotes (Code-Style Quotation) + +**Problem:** AI models trained on code often use single quotes as primary delimiters. + +**Before:** +> stated, 'This is a pattern.' + +**After:** +> stated, "This is a pattern." + +--- + ## 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... @@ -343,7 +353,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as --- -### 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... @@ -357,7 +367,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as --- -### 21. Sycophantic/Servile Tone +### 22. Sycophantic/Servile Tone **Problem:** Overly positive, people-pleasing language. @@ -371,7 +381,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as ## FILLER AND HEDGING -### 22. Filler Phrases +### 23. Filler Phrases **Before → After:** @@ -384,7 +394,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as --- -### 23. Excessive Hedging +### 24. Excessive Hedging **Problem:** Over-qualifying statements. @@ -396,7 +406,7 @@ Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as --- -### 24. Generic Positive Conclusions +### 25. Generic Positive Conclusions **Problem:** Vague upbeat endings. @@ -435,7 +445,7 @@ Provide: **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. +> The new software update serves as a testament to the company's commitment to innovation. Moreover, it provides a seamless, intuitive, and powerful user experience—ensuring that users can accomplish their goals efficiently. It's not just an update; it's a revolution in how we think about productivity. Industry experts believe this will have a lasting impact on the entire sector, highlighting the company's pivotal role in the evolving technological landscape. > > 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. > diff --git a/AGENTS.md b/AGENTS.md index 6e6ddcf3..35f16b2d 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -16,7 +16,7 @@ This repository defines the **Humanizer** coding skill, designed to remove AI-ge The Humanizer skill provides a set of 25 patterns for identifying and rewriting "AI-slop" or sterile writing. It preserves technical literals (code blocks, URLs, identifiers) while injecting personality and human-like voice. -- **Primary Prompt:** [SKILL.md](file:///c:/Users/60217257/repos/humanizer/SKILL.md) +- **Primary Prompt:** [SKILL.md](SKILL.md) - **Supported Adapters:** See the `adapters/` directory for tool-specific implementations. ## Context diff --git a/QWEN.md b/QWEN.md index 66279888..f76fe9db 100644 --- a/QWEN.md +++ b/QWEN.md @@ -1,8 +1,8 @@ --- adapter_metadata: skill_name: humanizer - skill_version: 2.1.1 - last_synced: 2026-01-31 + skill_version: 2.2.0 + last_synced: 2026-02-01 source_path: SKILL.md adapter_id: qwen-cli adapter_format: Qwen CLI context diff --git a/README.md b/README.md index ece7f8a4..cc7509d1 100644 --- a/README.md +++ b/README.md @@ -143,7 +143,7 @@ Based on [Wikipedia's "Signs of AI writing"](https://en.wikipedia.org/wiki/Wikip ### Global Agent Context -AI agents (Claude Code, Cursor, Windsurf, etc.) should use [AGENTS.md](file:///c:/Users/60217257/repos/humanizer/AGENTS.md) for repository orientation and core instructions. +AI agents (Claude Code, Cursor, Windsurf, etc.) should use [AGENTS.md](AGENTS.md) for repository orientation and core instructions. ### Communication Patterns @@ -168,8 +168,9 @@ AI agents (Claude Code, Cursor, Windsurf, etc.) should use [AGENTS.md](file:///c > > 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; The new software update serves as a testament to the company's commitment to innovation. Moreover, it provides a seamless, intuitive, and powerful user experience—ensuring that users can accomplish their goals efficiently. It's not just an update; it's a revolution in how we think about productivity. Industry experts believe this will have a lasting impact on the entire sector, highlighting the company's pivotal role in the evolving technological landscape. -tion 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. +> 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. From bdc10bf36932bca096a4d6b2167e14e949ce6cf5 Mon Sep 17 00:00:00 2001 From: "Dylan Mordaunt (Illawarra Shoalhaven LHD)" Date: Fri, 6 Feb 2026 21:09:18 +1100 Subject: [PATCH 4/4] docs: address review comments, format JSON artifacts, and fix lint issues --- README.md | 3 +- .../adopt-upstream-prs_20260131/spec.md | 7 +++- .../migrate-warp-to-agentsmd_20260131/plan.md | 5 ++- .../migrate-warp-to-agentsmd_20260131/spec.md | 8 +++-- issues.json | 33 ++++++++++++++++++- pr3.json | 19 ++++++++++- pr4.json | 24 +++++++++++++- pr5.json | 24 +++++++++++++- 8 files changed, 113 insertions(+), 10 deletions(-) diff --git a/README.md b/README.md index ebe9a78f..1a46ed73 100644 --- a/README.md +++ b/README.md @@ -149,7 +149,8 @@ This will automatically update version metadata and last synced timestamps acros ## Version history -- **2.2.0** - Added Pattern #19 (Primary Single Quotes), modular refactor, and Agents.md manifest. +- **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). diff --git a/conductor/tracks/adopt-upstream-prs_20260131/spec.md b/conductor/tracks/adopt-upstream-prs_20260131/spec.md index 96e28ef0..e1b4bcbd 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 7bf7ed7a..9edf6179 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 20cf27fe..24cca4f6 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 4b601d9c..805d9c36 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 a01e3251..ff0082d0 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 b263d7c9..78c7d0aa 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 23babda2..b5bbcad4 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