Improve/skill review optimization - #60
Open
yogesh-tessl wants to merge 3 commits into
Open
Conversation
Hey 👋 @sebbsssss 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 | |-------|--------|-------|--------| | clude-memory-mcp | 40%* | 95% | +55% | *The original name (Clude Memory MCP) wasn't in kebab-case, which caused the review to fail validation entirely (16% raw score). I fixed the name to clude-memory-mcp and re-ran to get a fairer 40% baseline before optimizing.* ## What changed Improved the clude-memory-mcp SKILL.md to score higher on tessl's skill review evaluation — covering description quality, content actionability, workflow clarity, and progressive disclosure. ## Why The skill had a solid foundation but scored low on the automated review because of a few structural issues: missing "Use when..." trigger clause, no concrete usage examples, no workflow with validation steps, and all content in a single file with no progressive disclosure. ### Specific changes Frontmatter: - Fixed name from Clude Memory MCP to clude-memory-mcp (kebab-case, required by validation) - Rewrote description with explicit "Use when..." clause and natural trigger keywords - Added metadata.version: "1.0.0" - Changed description format from YAML chevron to quoted string Description dimension (17% → 90%): - Added natural trigger terms users would actually say - Added explicit "Use when..." clause for skill selection - Removed infrastructure jargon from description Content dimension (38% → 100%): - Added concrete JSON examples for store_memory and recall_memories - Added 4-step workflow (Recall → Store → Search → Review) with validation checkpoints - Split detailed parameter lists and setup/modes into a new REFERENCE.md - Removed Architecture and License sections from SKILL.md (preserved in REFERENCE.md) - Separated required vs optional parameters with most common ones inline ## How to test 1. Run tessl skill review SKILL.md — should score 95% 2. Review the SKILL.md content reads naturally as a skill reference 3. Verify REFERENCE.md contains the full parameter details and setup instructions --- 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: https://docs.tessl.io/evaluate/optimize-a-skill-using-best-practices Ping me - @yogesh-tessl - if you hit any snags. Thanks in advance 🙏
|
@yogesh-tessl is attempting to deploy a commit to the Sebastien's projects 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 @asachs01 👋
1.96% hallucination rate on HaluMem versus an industry average of ~21%. That's a serious benchmark for a cognitive memory system. The differential decay model across episodic, semantic, procedural, and self-model memory types is a thoughtful architecture choice.
I ran your skills through tessl skill review at work and found some targeted improvements. Here's the full before/after:
Changes Summary
Honest disclosure. I work at https://github.com/tesslio where we build tooling around skills like these. Not a pitch - just saw room for improvement and wanted to contribute.
I also added a lightweight GitHub Action that auto-reviews any skill.md changed in a PR (includes min permissions, uses a pinned action version, only posts a review comment).
This means that it gives you and your contributors an instant quality signal before you have to review yourself (no signup, no tokens needed).
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 🙏