Improve/skill review optimization#3156
Open
yogesh-tessl wants to merge 2 commits into
Open
Conversation
Hey @stalniy 👋 Really solid set of skills here — the `setup()` function DI pattern baked into `console-tests` is a great convention, and the progressive disclosure to reference files keeps the main skill lean without losing depth. ## Why 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 | |-------|--------|-------|--------| | console-tests | 89% | 94% | +5% | | linear-issue | 90% | — | unchanged | | branch-namer | 90% | — | unchanged | I focused on `console-tests` because it had the most improvement headroom and is the most central skill — it's the one referenced in your CLAUDE.md as required for all testing work. ## What <details> <summary>Changes made</summary> **Conciseness improvements:** - Replaced the verbose "Deciding What Type of Test to Write" section with a compact decision table — removed explanations of what each test type is (Claude already knows) and kept only your project-specific criteria and mocking strategies - Removed generic preamble ("read the source file thoroughly") that doesn't add value for an AI agent - Consolidated "Comments Answer WHY, Not WHAT" (generic advice) into the error handling section and tightened the wording **Workflow clarity (biggest impact):** - Added an "After Writing Tests" verification checklist with 5 concrete steps — `npm test`, `npx tsc --noEmit`, `npm run lint -- --quiet`, review output, verify coverage - This was the main judge feedback: the skill lacked explicit validation checkpoints, which is critical for a testing skill **Net result:** 11 fewer lines, tighter content, same domain expertise preserved. </details> I also stress-tested your `console-tests` skill against a few real-world task evals and it held up really well on functional tests with whitebox DB seeding and nock-based blockchain node mocking. 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 🙏
Contributor
|
ℹ️ Recent review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (1)
📝 WalkthroughWalkthroughThis PR refines the console test-writing skill guide by introducing a structured decision framework for test level selection, narrowing error-path testing guidance to explicitly handled exceptions, and adding a post-writing verification checklist for completeness and correctness. ChangesTest Guide Improvements
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~3 minutes ✨ Finishing Touches🧪 Generate unit tests (beta)
Tip 💬 Introducing Slack Agent: The best way for teams to turn conversations into code.Slack Agent is built on CodeRabbit's deep understanding of your code, so your team can collaborate across the entire SDLC without losing context.
Built for teams:
One agent for your entire SDLC. Right inside Slack. Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Hey @stalniy 👋
these skills are pretty good. The setup() DI pattern baked into console-tests is honestly a great convention, i like it. and the way you've done progressive disclosure into reference files, keeps the main skill lean but the depth is still there if you need it.
I ran your one of your skill through
tessl skill reviewat work and found targeted improvements in your skill. Here's the before/after:I focused on
console-testsbecause it had the most improvement headroom and is the most central skill. It's the one referenced in your CLAUDE.md as required for all testing work.Changes made
Conciseness improvements:
Workflow clarity (biggest impact):
npm test,npx tsc --noEmit,npm run lint -- --quiet, review output, verify coverageI also stress-tested your
console-testsskill against a few real-world task evals and it held up really well on functional tests with white-box DB seeding and nock-based blockchain node mocking. Kudos for that.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.
Summary by CodeRabbit