fix functional-tests skill frontmatter + add skill-review CI#4
fix functional-tests skill frontmatter + add skill-review CI#4fernandezbaptiste wants to merge 1 commit into
Conversation
|
Hi ! , I Check that today ! With all testing and more update ! Thanks ! |
Enrich the skill description with specific trigger terms (WebTestCase, TDD, bug reports, regression, test coverage) so Claude can better match user intent. Inspired by PR #4 suggestions. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
Hey @fernandezbaptiste, thanks for the PR and the kind words! 🙏 I've cherry-picked the useful part of your contribution — the enriched Regarding the two other changes, I'm not merging them for the following reasons:
Closing this PR since the description improvement has been integrated. Thanks again for taking the time to |
|
thanks for cherry-picking the description improvement @MakFly - glad it was useful! totally fair on the other two points. curious - you mentioned you validate with if it's helpful, I'd be happy to keep contributing improvements to other skills as well and open more PRs where I see clear wins. you've got one thing to flag is that even after a skill is improved once, it can still drift over time as prompts evolve. longer-term value is having review + improvement as part of CI flows so regressions get caught early. keen to hear how you would imagine this to be part of your CI approach - looking to get feedback on how to approach this in a secure way, so that it gives maintainers and their contributors an instant quality signal on every skill.md change, as well as concrete improvements when you need them. |
hey @MakFly, thanks for building superpowers-symfony. really like the breadth of Symfony skills you've put together in one place. Kudos on soon reaching
100stars! I've just starred it.ran your functional-tests skill through agent evals and spotted a quick fix:
fixed
allowed-toolsfrom YAML array to string format (required for valid frontmatter parsing)expanded description with trigger terms like TDD, regression tests, bug reports, functional coverage
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).
these were easy changes to bring the skill in line with what performs well against Anthropic's best practices. honest disclosure, I work at tessl.io where we build tooling around this. not a pitch, just fixes that were straightforward to make! happy to answer any questions on the changes.