feat: improve skill scores across 5 skills#2
Open
rohan-tessl wants to merge 1 commit intobitwikiorg:mainfrom
Open
feat: improve skill scores across 5 skills#2rohan-tessl wants to merge 1 commit intobitwikiorg:mainfrom
rohan-tessl wants to merge 1 commit intobitwikiorg:mainfrom
Conversation
Hey @bitwikiorg 👋 I ran your skills through `tessl skill review` at work and found some targeted improvements. Here's the full before/after: | Skill | Before | After | Change | |-------|--------|-------|--------| | chat-input | 16% | 75% | +59% | | advanced-search | 17% | 62% | +45% | | mcp-best-practices | 17% | 70% | +53% | | comparison-template | 17% | 73% | +56% | | check-bounding-boxes | 17% | 91% | +74% | This PR is intentionally scoped to 5 skills to keep things reviewable — more skills can be improved in follow-ups or via automated review on future PRs. <details> <summary>Changes summary</summary> **Across all 5 skills:** - Fixed `name` field from underscores to kebab-case (e.g. `chat_input` → `chat-input`) — this was the bitwikiorg#1 blocker, causing deterministic validation to fail entirely and zeroing out all LLM-judged dimensions - Replaced generic "Imported skill X from Y" descriptions with actionable "Use when..." descriptions as quoted strings - Added structured skill framing: "When to Use" sections, key component tables, and workflow steps - Preserved all original domain content (code, reference docs) intact - Used third-person voice throughout **Per-skill highlights:** - **chat-input**: Added component table (ChatInput, ChatTextArea, CompletionPopup), input behavior reference, and keybinding summary - **advanced-search**: Added intro paragraph covering scope (filters, strategies, connected sources) and "When to Use" trigger list - **mcp-best-practices**: Added comprehensive "When to Use" covering scaffolding, tool design, transport, security, and review use cases - **comparison-template**: Added 5-step workflow (define criteria → research → fill matrix → analyze → recommend) and a concrete database-comparison example - **check-bounding-boxes**: Added usage snippet, checks-performed table, and clear trigger conditions (post-PDF-analysis, CI gate) </details> Honest disclosure — I work at @tesslio where we build tooling around skills like these. Not a pitch - just saw room for improvement and wanted to contribute. Want to self-improve your skills? Just point your agent (Claude Code, Codex, etc.) at [this Tessl guide](https://docs.tessl.io/evaluate/optimize-a-skill-using-best-practices) and ask it to optimize your skill. Ping me - [@rohan-tessl](https://github.com/rohan-tessl) - if you hit any snags. Thanks in advance 🙏
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Hey @bitwikiorg 👋
I ran your skills through
tessl skill reviewat work and found some targeted improvements.Here's the full before/after:
This PR is intentionally scoped to 5 skills to keep things reviewable — more skills can be improved in follow-ups or via automated review on future PRs.
Changes summary
Across all 5 skills:
namefield from underscores to kebab-case (e.g.chat_input→chat-input) — this was the Github Pages #1 blocker, causing deterministic validation to fail entirely and zeroing out all LLM-judged dimensionsPer-skill highlights:
Honest disclosure — I work at @tesslio where we build tooling around skills like these. Not a pitch - just saw room for improvement and wanted to contribute.
Want to self-improve your skills? Just point your agent (Claude Code, Codex, etc.) at this Tessl guide and ask it to optimize your skill. Ping me - @rohan-tessl - if you hit any snags.
Thanks in advance 🙏