Skip to content

feat: improve android-coroutines skill score (59% → 90%)#938

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

feat: improve android-coroutines skill score (59% → 90%)#938
yogesh-tessl wants to merge 1 commit into
livekit:mainfrom
yogesh-tessl:improve/skill-review-optimization

Conversation

@yogesh-tessl
Copy link
Copy Markdown

Hey @davidliu 👋

ran your skills through tessl skill review at work and found some targeted improvements for android-coroutines. Here's the before/after:

Skill Before After Change
android-coroutines 59% 90% +31%

picked android-coroutines because it had the most improvement headroom among the core skills, and coroutines are central to the SDK's async real-time communication patterns.

Changes made to android-coroutines
  • Rewrote frontmatter description with explicit "Use when..." clause and natural trigger terms (suspend functions, Flow, StateFlow, GlobalScope, callbackFlow, repeatOnLifecycle) so the skill gets selected reliably
  • Added a 4-step implementation workflow (Identify scope → Wire data layer → Connect UI → Verify) with concrete validation steps including ./gradlew test and ./gradlew detektDebug, plus a diagnostic checklist for common failure modes
  • Removed meta-sections ("Responsibilities" and "Applicability") that restated the description without adding actionable value - saves tokens without losing any guidance
  • Tightened rule prose - trimmed explanatory text Claude already knows (main-safety rationale, cooperative cancellation basics) while keeping all rules and code patterns intact

Net result: 29 lines removed, 11 added - a smaller, sharper skill file.


quick 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.

if you want to self-improve your skills, or define your own scenarios to pressure test, just ask your agent (Claude Code, Codex, etc.) to evaluate and optimize your skill with Tessl. Ping me @yogesh-tessl, if you hit any snags.

Hey @davidliu 👋

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

| Skill | Before | After | Change |
|-------|--------|-------|--------|
| android-coroutines | 59% | 90% | +31% |
| android-testing | 59% | 59% | — |
| kotlin-concurrency-expert | 82% | 82% | — |
| gradle-build-performance | 86% | 86% | — |
| android-gradle-logic | 59% | 59% | — |

I picked `android-coroutines` because it had the most improvement headroom among the core skills, and coroutines are central to the SDK's async real-time communication patterns.

<details>
<summary>Changes made to <code>android-coroutines</code></summary>

- **Rewrote frontmatter description** with explicit "Use when..." clause and natural trigger terms (`suspend functions`, `Flow`, `StateFlow`, `GlobalScope`, `callbackFlow`, `repeatOnLifecycle`) so the skill gets selected reliably
- **Added a 4-step implementation workflow** (Identify scope → Wire data layer → Connect UI → Verify) with concrete validation steps including `./gradlew test` and `./gradlew detektDebug`, plus a diagnostic checklist for common failure modes
- **Removed meta-sections** ("Responsibilities" and "Applicability") that restated the description without adding actionable value — saves tokens without losing any guidance
- **Tightened rule prose** — trimmed explanatory text Claude already knows (main-safety rationale, cooperative cancellation basics) while keeping all rules and code patterns intact

Net result: 29 lines removed, 11 added — a smaller, sharper skill file.

</details>

I also stress-tested your `kotlin-concurrency-expert` skill against a few real-world task evals and it held up really well on diagnosing `CancellationException` swallowing in nested `runCatching` blocks. Kudos for that.

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 🙏
@changeset-bot
Copy link
Copy Markdown

changeset-bot Bot commented May 12, 2026

⚠️ No Changeset found

Latest commit: 0192613

Merging this PR will not cause a version bump for any packages. If these changes should not result in a new version, you're good to go. If these changes should result in a version bump, you need to add a changeset.

This PR includes no changesets

When changesets are added to this PR, you'll see the packages that this PR includes changesets for and the associated semver types

Click here to learn what changesets are, and how to add one.

Click here if you're a maintainer who wants to add a changeset to this PR

@CLAassistant
Copy link
Copy Markdown

CLAassistant commented May 12, 2026

CLA assistant check
All committers have signed the CLA.

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.

2 participants