Skip to content

Improve/skill review optimization#1

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

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

Conversation

@yogesh-tessl
Copy link
Copy Markdown

Hey @ZhenHuangLab 👋

README是中文的 — noted. The conservative default strategy for Gemini CLI (read-only, one-shot + file-focused) shows thoughtful guardrailing for the weaker attention mechanism. Nice bridge pattern between Codex and Gemini. 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:

Skill Before After Change
collaborating-with-gemini-cli 78% 100% +22%
Changes made

Description improvements:

  • Added explicit "Use when..." clause with natural trigger terms (ask Gemini to review code, get a second opinion, compare implementations, delegate analysis)
  • Removed inline backticks that were causing potential YAML parsing fragility
  • Kept all technical specificity while making the description more discoverable

Content improvements:

  • Trimmed introductory framing (removed comparison to collaborating-with-claude-code and generic "Use this skill when..." opener)
  • Replaced verbose access modes list with a compact table
  • Consolidated effective-context guardrails section - removed the separate "Session rotation guidance" subsection and integrated the key signal (over_effective_context_limit) into the multi-turn sessions section
  • Moved full parameter reference to a new REFERENCE.md for progressive disclosure, keeping only essential flags inline
  • Streamlined requirements section (removed redundant sub-bullets)

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 @ZhenHuangLab 👋

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 |
|-------|--------|-------|--------|
| collaborating-with-gemini-cli | 78% | 100% | +22% |

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

**Description improvements:**
- Added explicit "Use when..." clause with natural trigger terms (ask Gemini to review code, get a second opinion, compare implementations, delegate analysis)
- Removed inline backticks that were causing potential YAML parsing fragility
- Kept all technical specificity while making the description more discoverable

**Content improvements:**
- Trimmed introductory framing (removed comparison to `collaborating-with-claude-code` and generic "Use this skill when..." opener)
- Replaced verbose access modes list with a compact table
- Consolidated effective-context guardrails section — removed the separate "Session rotation guidance" subsection and integrated the key signal (`over_effective_context_limit`) into the multi-turn sessions section
- Moved full parameter reference to a new `REFERENCE.md` for progressive disclosure, keeping only essential flags inline
- Streamlined requirements section (removed redundant sub-bullets)

</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