Improve/skill review optimization#59
Open
yogesh-tessl wants to merge 2 commits into
Open
Conversation
## Description Hey @ComeOnOliver 👋 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 | |-------|--------|-------|--------| | swiftui-pro | 10% | 100% | +90% | | skills-discovery | 10% | 86% | +76% | | yt-dlp-downloader-skill | 10% | 80% | +70% | | github-cli | 71% | 95% | +24% | | ue-benchmark | 74% | 81% | +7% | The three skills scoring 10% were failing validation entirely because they lacked YAML frontmatter — once that was added, the content quality underneath shone through (especially `swiftui-pro` which hit a perfect 100%). <details> <summary>What changed</summary> **skills-discovery, swiftui-pro, yt-dlp-downloader-skill** (10% → 86%, 100%, 80%): - Added YAML frontmatter with `name` and `description` fields — these were the only reason for the 10% scores - Wrote specific, action-oriented descriptions with natural trigger terms and "Use when" clauses - Converted opening text to third-person voice where needed - Preserved all existing content and domain expertise intact **github-cli** (71% → 95%): - Replaced vague description ("any GitHub-related task") with specific actions (managing repos, PRs, issues, reading READMEs, querying metadata) - Added natural trigger terms (pull requests, gh CLI, GitHub API endpoints) - Added concrete use cases to the "When to Use" section **ue-benchmark** (74% → 81%): - Rewrote description to include English trigger terms alongside the Chinese content - Added specific scoring dimensions (PackageGate, PVP protocol, token efficiency) and "Use when" clause </details> ## Type - [ ] Bug fix - [ ] New feature - [x] Refactor - [ ] Documentation ## Checklist - [x] `pnpm build` passes - [x] Changes are tested - [x] Documentation updated (if needed) - [x] No new TypeScript errors ## Related Issues N/A — unsolicited improvement contribution. --- 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 - [@yogesh-tessl](https://github.com/yogesh-tessl) - if you hit any snags. Thanks in advance 🙏
|
@yogesh-tessl is attempting to deploy a commit to the Pengzhou AI CLUB Team on Vercel. A member of the Team first needs to authorize it. |
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 @ComeOnOliver 👋
5,900+ skills from 500+ repos, resolved in one API call at ~200 tokens. That's a 250x efficiency claim backed by real architecture. The Drizzle + Neon stack is a clean choice for a registry at this scale. Wanted to suggest a few improvements to the SKILL.md.
I ran your skills through
tessl skill reviewat work and found some targeted improvements.The three skills scoring 10% were failing validation entirely because they lacked YAML frontmatter. Once that was added, the content quality underneath shone through (especially
swiftui-prowhich hit a perfect 100%).What changed
skills-discovery, swiftui-pro, yt-dlp-downloader-skill (10% → 86%, 100%, 80%):
nameanddescriptionfields - these were the only reason for the 10% scoresgithub-cli (71% → 95%):
ue-benchmark (74% → 81%):
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 - @yogesh-tessl - if you hit any snags.
Thanks in advance 🙏