Skip to content

Improve/skill review optimization#1

Open
yogesh-tessl wants to merge 2 commits into
Davidcreador:mainfrom
yogesh-tessl:improve/skill-review-optimization
Open

Improve/skill review optimization#1
yogesh-tessl wants to merge 2 commits into
Davidcreador:mainfrom
yogesh-tessl:improve/skill-review-optimization

Conversation

@yogesh-tessl

Copy link
Copy Markdown

Hey 👋 @Davidcreador

Branch-specific CLAUDE.md files that auto-swap on checkout. That's solving a pain point every multi-branch Claude Code user hits but nobody else has packaged this cleanly. Breaking it into save/load/list/status skills with both plugin and CLI modes shows you've thought about the full UX surface. Wanted to suggest a few improvements to the SKILL.md.

I ran your skills through tessl skill review at work and found some targeted improvements. Here's the full before/after:

score_card
Changes made

list & status - Added explicit "Use when..." clauses with natural trigger keywords (e.g. "show branches", "check memory status", "view what's stored"). These were the main gaps flagged by the evaluator, without a "Use when" clause, Claude has weaker signal for when to select the skill.

save - Expanded trigger terms ("persist settings", "store context", "snapshot branch state") and added brief error handling guidance for when CLAUDE.md doesn't exist. Also added confirmation of what was saved in the result output.

load - Already scoring 90% with solid "Use when" guidance and clean content. Left unchanged.

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 🙏

Hey 👋 @Davidcreador

I ran your skills through `tessl skill review` at work and found some targeted improvements. Here's the full before/after:

![Skill Review Score Card](score_card.png)

| Skill | Before | After | Change |
|-------|--------|-------|--------|
| list | 73% | 96% | +23% |
| status | 73% | 96% | +23% |
| save | 82% | 87% | +5% |
| load | 90% | 90% | — (already great, left untouched) |

<details>
<summary>Changes made</summary>

**list** & **status** — Added explicit "Use when..." clauses with natural trigger keywords (e.g. "show branches", "check memory status", "view what's stored"). These were the main gaps flagged by the evaluator — without a "Use when" clause, Claude has weaker signal for when to select the skill.

**save** — Expanded trigger terms ("persist settings", "store context", "snapshot branch state") and added brief error handling guidance for when CLAUDE.md doesn't exist. Also added confirmation of what was saved in the result output.

**load** — Already scoring 90% with solid "Use when" guidance and clean content. Left unchanged.

</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 - [@yogesh-tessl](https://github.com/yogesh-tessl) - if you hit any snags.

Thanks in advance 🙏
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant