feat: improve skill review scores across 5 skills#1
Open
rohan-tessl wants to merge 2 commits into
Open
Conversation
Optimized 5 SKILL.md files using tessl skill review: | Skill | Before | After | Change | |---------------|--------|-------|--------| | notion | 60% | 96% | +36% | | skill-creator | 76% | 93% | +17% | | tavily-search | 83% | 100% | +17% | | book-search | 89% | 100% | +11% | | pdf | 83% | 90% | +7% | Key changes: - notion: added "Use when" clause, trigger terms, verification step, troubleshooting table, removed unknown frontmatter key - skill-creator: expanded description triggers, trimmed verbose intro - tavily-search: consolidated redundant path warnings, compact options table - book-search: removed unnecessary Features/Implementation Notes sections - pdf: consolidated repeated Korean font code into single reusable function
Hey @hainamchung 👋 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 | |-------|--------|-------|--------| | agent-framework-azure-hosted-agents | 0% | 94% | +94% | | agent-tool-builder | 7% | 96% | +89% | | agent-memory-systems | 7% | 89% | +82% | | agent-evaluation | 11% | 89% | +78% | | advogado-especialista | 25% | 81% | +56% | This PR intentionally caps changes at 5 skills to keep it reviewable. The included workflow (below) will surface Tessl feedback on future `SKILL.md` changes so the rest of the library can improve incrementally. <details> <summary>Changes summary</summary> - **agent-framework-azure-hosted-agents (0% → 94%):** Fixed invalid frontmatter — the entire skill was wrapped in a ` ```skill ` code fence, causing validation to fail completely. Removed the wrapping fences and quoted the description string. - **agent-tool-builder (7% → 96%):** Rewrote from a skeleton with persona-style description to a structured skill with clear workflow, JSON Schema design example, error handling patterns, and "Use when" trigger clause. - **agent-memory-systems (7% → 89%):** Rewrote from placeholder content to a structured skill covering memory types (working, episodic, semantic, procedural), chunking strategies, retrieval patterns, and anti-patterns. - **agent-evaluation (11% → 89%):** Rewrote from a skeleton to a complete evaluation framework skill with statistical testing patterns, behavioral contracts, evaluation types table, and anti-patterns. - **advogado-especialista (25% → 81%):** Trimmed from 1,109 lines to ~90 lines by moving detailed legal modules (14 areas of Brazilian law) to `references/modulos.md` for progressive disclosure. Added proper "Use when" trigger clause with both Portuguese and English terms. Preserved all domain expertise in reference files. </details> ## Tessl Skill Review GitHub Action This PR also adds `.github/workflows/skill-review.yml` — a lightweight workflow that automatically reviews `SKILL.md` changes on future PRs: - **What runs:** On PRs that change `**/SKILL.md`, the workflow runs [`tesslio/skill-review`](https://github.com/tesslio/skill-review) and posts **one** comment with Tessl scores and feedback (updated on new pushes). - **Zero extra accounts:** Contributors do **not** need a Tessl login — only the default `GITHUB_TOKEN` is used to post the comment. - **Non-blocking by default:** The check is feedback-only with no surprise red CI. No `fail-threshold` is set unless you want a hard gate. - **Not a build replacement:** This is review automation for skill markdown, not a substitute for your own pipelines. - **Optional gate:** Add `with: fail-threshold: 70` later if you want PRs to fail on low scores. - **Why only 5 skills here:** This PR caps manual optimization so it stays reviewable. After merge, every PR that touches `SKILL.md` gets automatic review comments, so the rest of the 1,400+ skills can improve incrementally. --- 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 @kyopark2014 👋
I ran your skills through
tessl skill reviewat work and found some targeted improvements.Here's the full before/after:
This PR intentionally caps changes at 5 skills to keep it reviewable. The included workflow (below) will surface Tessl feedback on future
SKILL.mdchanges so the rest of the library can improve incrementally.Changes summary
notion (60% → 96%)
homepageskill-creator (76% → 93%)
tavily-search (83% → 100%)
book-search (89% → 100%)
cwdapproach)pdf (83% → 90%)
register_korean_font()instead of re-implementing the font logicTessl Skill Review GitHub Action
This PR also adds
.github/workflows/skill-review.yml— a lightweight workflow that automatically reviewsSKILL.mdchanges on future PRs:**/SKILL.md, the workflow runstesslio/skill-reviewand posts one comment with Tessl scores and feedback (updated on new pushes).GITHUB_TOKENis used to post the comment.fail-thresholdis set unless you want a hard gate.with: fail-threshold: 70later if you want PRs to fail on low scores.SKILL.mdgets automatic review comments, so the rest of the library can improve incrementally.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 🙏