Add Claude Code skills for bug reporting, fixing, PR review, and performance work#6090
Open
SanderMuller wants to merge 1 commit into
Open
Add Claude Code skills for bug reporting, fixing, PR review, and performance work#6090SanderMuller wants to merge 1 commit into
SanderMuller wants to merge 1 commit into
Conversation
…ormance work Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Follows the same pattern as the existing
regression-testskill: workflow guidance for Claude Code under.claude/skills/, complementingCLAUDE.md.Four skills, one per stage of contributing to PHPStan:
bug-reporting: turn an observation into a verified root cause and a reproducible issue.bug-fixing: reproduce, write the failing test first, fix the root cause, pass the full gate (tests, self-analysis, coding standard, e2e), then open the PR.pr-review-feedback: apply review feedback with critical evaluation, re-run the gate, and confirm CI is green before replying.performance-work: decide whether a perf problem is a fix or an issue, measure honestly on real code with the result cache cleared, and frame the change for review.These are distilled from the workflow behind my recent contributions here (e.g. #6086, #5933, #5992, #5961, #5929), not written in the abstract. Each skill ends with a verification step that runs the concrete gate and reads its output, so "done" means the checks actually passed. That discipline comes from real near-misses these caught during that work: a test fixture committed in the wrong state, a coding-standard slip found only after a push, and an optimization that silently never fired yet still passed byte-identical output.
They lean on
CLAUDE.mdfor the type-system principles instead of repeating them.