Skip to content

feat: improve skill score for kalibr-sdk-python#164

Open
yogesh-tessl wants to merge 1 commit intokalibr-ai:mainfrom
yogesh-tessl:improve/skill-review-optimization
Open

feat: improve skill score for kalibr-sdk-python#164
yogesh-tessl wants to merge 1 commit intokalibr-ai:mainfrom
yogesh-tessl:improve/skill-review-optimization

Conversation

@yogesh-tessl
Copy link
Copy Markdown

Hey @devonakelley 👋

Self-healing execution harness with Thompson Sampling on real production outcomes, that's a bold architecture bet that moves past static benchmarks. The kalibr auth → kalibr init → kalibr verify onboarding flow is agent-friendly by design. 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
kalibr 46% 93% +47%
What changed
  • Description rewritten - replaced marketing-style tagline with a functional skill description listing concrete actions (configures routers, sets up execution paths, defines success criteria, instruments LLM calls) and an explicit "Use when..." clause with natural trigger terms
  • Trimmed trigger list - consolidated 8 overlapping bullet points down to 4 distinct triggers
  • Removed comparison section - the "How it's different" block explained competitors, which doesn't help Claude use the skill correctly
  • Removed duplicate "How it works" section - the intro paragraph already covers Thompson Sampling and canary traffic
  • Added error handling example - shows ValueError for config errors and exception re-raising when all paths fail, matching the actual SDK behavior in router.py
  • Cleaned up metadata - flattened nested openclaw metadata to simple string key-value pairs
  • Removed OpenClaw install section - secondary install method that added noise without aiding skill selection

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 🙏

Hey @devonakelley 👋

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 |
|-------|--------|-------|--------|
| kalibr | 46% | 93% | +47% |

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

- **Description rewritten** — replaced marketing-style tagline with a functional skill description listing concrete actions (configures routers, sets up execution paths, defines success criteria, instruments LLM calls) and an explicit "Use when..." clause with natural trigger terms
- **Trimmed trigger list** — consolidated 8 overlapping bullet points down to 4 distinct triggers
- **Removed comparison section** — the "How it's different" block explained competitors, which doesn't help Claude use the skill correctly
- **Removed duplicate "How it works" section** — the intro paragraph already covers Thompson Sampling and canary traffic
- **Added error handling example** — shows `ValueError` for config errors and exception re-raising when all paths fail, matching the actual SDK behavior in `router.py`
- **Cleaned up metadata** — flattened nested openclaw metadata to simple string key-value pairs
- **Removed OpenClaw install section** — secondary install method that added noise without aiding skill selection

</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