feat: improve skill scores for roopik#84
Open
yogesh-tessl wants to merge 1 commit intoRoopikLabs:developfrom
Open
feat: improve skill scores for roopik#84yogesh-tessl wants to merge 1 commit intoRoopikLabs:developfrom
yogesh-tessl wants to merge 1 commit intoRoopikLabs:developfrom
Conversation
Hey @HumbleBee14 👋 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 | |-------|--------|-------|--------| | accessibility | 87% | 94% | +7% | | fix-errors | 90% | 100% | +10% | | unit-tests | 89% | 95% | +6% | | integration-tests | 90% | 100% | +10% | | memory-leak-audit | 97% | 97% | — | <details> <summary>What changed</summary> **accessibility** (+7%) - Narrowed the `Use when` trigger clause to explicitly mention accessibility context (ARIA, screen readers, keyboard navigation) — prevents false activation on general UI work - Removed duplicate import lines in the help dialog code example - Trimmed sections 6–7 (keyboard navigation, ARIA labels) to VS Code-specific guidance only — general WAI-ARIA knowledge Claude already has - Moved advanced `IInstantiationService` pattern to a separate EXAMPLES.md for progressive disclosure **fix-errors** (+10%) - Tightened the "do NOT fix at the crash site" section — same message, fewer words - Condensed the data flow tracing guidance for better conciseness **unit-tests** (+6%) - Moved compilation prerequisite to the top so it's seen before any test commands - Consolidated the duplicate "bare file paths" and `--run` sections into one - Replaced the vague "conceptual example" for `runTests` with a concrete tool invocation showing exact parameters - Removed redundant compilation section at the bottom **integration-tests** (+10%) - Removed the Examples section that duplicated commands already shown under each option - Cross-referenced the `unit-tests` skill in the "Distinction from unit tests" section instead of re-explaining </details> I kept this PR focused on the 4 skills with the biggest improvements to keep the diff reviewable. Happy to follow up with the rest in a separate PR if you'd like. 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 🙏
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
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 @HumbleBee14 👋
I ran your skills through
tessl skill reviewat work and found some targeted improvements. Here's the full before/after:What changed
accessibility (+7%)
Use whentrigger clause to explicitly mention accessibility context (ARIA, screen readers, keyboard navigation) - prevents false activation on general UI workIInstantiationServicepattern to a separate EXAMPLES.md for progressive disclosurefix-errors (+10%)
unit-tests (+6%)
--runsections into onerunTestswith a concrete tool invocation showing exact parametersintegration-tests (+10%)
unit-testsskill in the "Distinction from unit tests" section instead of re-explainingI kept this PR focused on the 4 skills with the biggest improvements to keep the diff reviewable. Happy to follow up with the rest in a separate PR if you'd like.
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 🙏