feat: fix skill frontmatter validation across 106 skills#39
Open
popey wants to merge 1 commit into
Open
Conversation
Hullo @jumsay 👋 I ran your skills through `tessl skill review` at work and found some targeted improvements. Here's the before/after for the top movers (all 106 skills went from 0% to passing): | Skill | Before | After | Change | |-------|--------|-------|--------| | nginx-expert | 0% | 83% | +83% | | airflow-expert | 0% | 77% | +77% | | elasticsearch-expert | 0% | 77% | +77% | | kafka-expert | 0% | 77% | +77% | | django-expert | 0% | 77% | +77% | | quantum-expert | 0% | 77% | +77% | | codeql-expert | 0% | 77% | +77% | | tableau-expert | 0% | 75% | +75% | | fastapi-expert | 0% | 74% | +74% | | python-expert | 0% | 74% | +74% | All 106 skills were failing validation (0% score) due to three structural issues in the frontmatter. After fixing these, the average score across the stdlib is ~62%. <details> <summary>Changes made</summary> ### 1. Fixed `allowed-tools` format (all 106 skills) The `allowed-tools` field was a YAML list (array) but the spec requires a comma-separated string. Changed from: ```yaml allowed-tools: - Read - Write - Edit ``` to: ```yaml allowed-tools: Read, Write, Edit ``` ### 2. Moved unknown frontmatter keys to `metadata` (104 skills) Keys like `version`, `category`, `author`, `tags`, and `requirements` were at the top level of frontmatter but aren't recognized fields. Moved them under the `metadata` key where they belong: ```yaml metadata: version: 1.0.0 category: languages author: PCL Team tags: [python, async, type-hints] ``` ### 3. Added "Use when..." trigger clauses to descriptions (104 skills) Most descriptions lacked explicit trigger guidance. Added `Use when working with X, asking about X concepts, or reviewing X code and configurations` to help agents select the right skill. ### 4. Fixed `compatibility` field format (3 skills) `docker-expert`, `typescript-expert`, and `code-review-expert` had `compatibility` as a YAML list instead of a string. </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 - [@popey](https://github.com/popey) - 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.
Hullo @jumsay 👋
I ran your skills through
tessl skill reviewat work and found some targeted improvements. Here's the before/after for the top movers (all 106 skills went from 0% to passing):All 106 skills were failing validation (0% score) due to three structural issues in the frontmatter. After fixing these, the average score across the stdlib is ~62%.
Changes made
1. Fixed
allowed-toolsformat (all 106 skills) Theallowed-toolsfield was a YAML list (array) but the spec requires a comma-separated string. Changed from:to:
2. Moved unknown frontmatter keys to
metadata(104 skills) Keys likeversion,category,author,tags, andrequirementswere at the top level of frontmatter but aren't recognized fields. Moved them under themetadatakey where they belong:3. Added "Use when..." trigger clauses to descriptions (104 skills) Most descriptions lacked explicit trigger guidance. Added
Use when working with X, asking about X concepts, or reviewing X code and configurationsto help agents select the right skill.4. Fixed
compatibilityfield format (3 skills)docker-expert,typescript-expert, andcode-review-experthadcompatibilityas a YAML list instead of a string.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 - @popey - if you hit any snags.
Thanks in advance 🙏