Menu
Run the full quality gate — format, lint, tests, types. Use after changes to verify nothing is broken.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
| name | check |
| description | Run the full quality gate — format, lint, tests, types. Use after changes to verify nothing is broken. |
Run the pipeline in this order, stopping at the first real failure. Exact commands live in CLAUDE.md.
ruff format. Reformatted files are expected; stage them.ruff check. Auto-fix when safe (--fix); escalate anything that needs a design call.pytest -q. On failure, identify the test and the root cause — don't just relay the traceback.mypy. Report offending files and lines.Fix what you can. Only escalate when a failure needs a decision.
If everything passes, one line: <N> passed, format+lint+types clean.
Deep analysis of current changes before committing. Goes beyond lint — catches logic bugs, architectural violations, security, and performance issues.
Create a pull request from the current branch, matching the repo's PR conventions (What/Why/Testing for features, Summary/Test-plan for small PRs).
Review staged or unstaged changes before committing. Catches bugs, style drift, and missing coverage.
Cut a release — promote Unreleased → versioned in CHANGELOG, bump version, commit. CI auto-tags and publishes from the version-bump commit.
Create a release-tracking issue that organizes open issues into a phased roadmap. Pass a target version (e.g., `0.5.0`) to scope the plan.
Check GitHub Actions CI status. Shows recent runs, and if there are failures, reads the logs and suggests fixes.