Skip to content

Improve/skill review optimization#1

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

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

Conversation

@yogesh-tessl
Copy link
Copy Markdown

Hey @ishaan-jaff 👋

21 skills covering the full CRUD surface of the LiteLLM proxy API - users, teams, keys, orgs, models, MCP servers, and agents with a clean one-folder-per-skill layout. Really like how each SKILL.md walks the user through setup and API calls interactively rather than just documenting endpoints. Wanted to tighten up a few of these skill files.

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

score_card
What changed
  • Added explicit "Use when..." clauses to all 5 skill descriptions — helps Claude (and other agents) know exactly when to select each skill
  • Expanded trigger terms in add-model and delete-model descriptions (e.g. "register", "deploy", "configure", "remove", "unregister") so natural user phrasing matches better
  • Standardised description format from YAML block scalars (>) to quoted strings across all 5 skills
  • Added verification steps to add-key (GET /key/info to confirm creation) and add-team (GET /team/info to confirm creation)
  • Added explicit error handling with specific HTTP status codes (401, 400) and remediation steps to add-key, add-team, and view-usage
  • Aligned variable names in add-key and add-team — added BASE=$LITELLM_BASE_URL / KEY=$LITELLM_API_KEY assignment lines so the curl commands are consistent with the Setup section

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 @ishaan-jaff 👋

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 |
|-------|--------|-------|--------|
| add-team | 82% | 100% | +18% |
| add-model | 87% | 100% | +13% |
| delete-model | 87% | 100% | +13% |
| add-key | 82% | 94% | +12% |
| view-usage | 92% | 97% | +5% |

<details>
<summary>What changed</summary>

- **Added explicit "Use when..." clauses** to all 5 skill descriptions — helps Claude (and other agents) know exactly when to select each skill
- **Expanded trigger terms** in `add-model` and `delete-model` descriptions (e.g. "register", "deploy", "configure", "remove", "unregister") so natural user phrasing matches better
- **Standardised description format** from YAML block scalars (`>`) to quoted strings across all 5 skills
- **Added verification steps** to `add-key` (GET `/key/info` to confirm creation) and `add-team` (GET `/team/info` to confirm creation)
- **Added explicit error handling** with specific HTTP status codes (401, 400) and remediation steps to `add-key`, `add-team`, and `view-usage`
- **Aligned variable names** in `add-key` and `add-team` — added `BASE=$LITELLM_BASE_URL` / `KEY=$LITELLM_API_KEY` assignment lines so the curl commands are consistent with the Setup section

</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