Total 50,522 skills, Code Quality has 2289 skills
Showing 12 of 2289 skills
Token-efficient GitHub source code exploration via tree-sitter AST parsing and structured retrieval
Reviews the current local diff or branch at the end of a coding session for high-confidence bugs and repository instruction-file compliance. Use when asked to run `/pr-reviewer` before commit, before push, or before handing changes off for PR creation or update, and when only certain, actionable findings should be reported while style feedback is ignored.
Guide for simplifying and refining code after coding sessions. Use when cleaning up complex code, reviewing PRs for readability, or applying consistent refactoring patterns.
Emulate supported AI code-review GitHub Actions locally and print a terminal-only review from portable skill instructions. Use when running /review-action or checking local PR-review feedback before publishing.
Run a read-only, fresh-context branch-diff code review and report findings. Use when running /review-code, before finishing issue work, or when a local review gate should inspect committed, staged, unstaged, and untracked changes without mutating code or GitHub state.
Detects misplaced classes and fixes component hierarchy problems — finds code that should belong inside a component but sits at the root level. Use when asking "clean up component structure", "find orphaned classes", "fix module hierarchy", "flatten nested components", or analyzing why namespaces have misplaced code. Do NOT use for dependency analysis (use coupling-analysis) or domain grouping (use domain-identification-grouping).
Guardião da qualidade de código e entregas no SynkOS. Use esta skill quando o usuário pedir para revisar código implementado, executar gates de qualidade, fazer code review, validar se uma story atende os critérios de aceite, checar segurança (OWASP), ou fazer perguntas como "revise o código da story X", "o que passou no gate de qualidade?", "há problemas de segurança?", "a implementação cobre os critérios de aceite?", "rode o code review automatizado". Ative também para documentar findings com severidade, decidir PASS/CONCERNS/FAIL/WAIVED para stories, e devolver ao dev com checklist de correções quando a story falha.
Use when the user asks to make something faster, try many variants, run recursive optimization, benchmark latency/throughput/cost, or choose the best implementation by repeated measured tests.
Perform thorough code reviews following Google's 5-step methodology. Use when reviewing pull requests, change lists, or any code changes to ensure quality, correctness, and maintainability.
Apply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach it, resist nil-check guards that silence crashes.
Use when reviewing a PR with contrarian inversion to stress-test changes via @coderabbitai, making specific factual claims about dependency behavior that Conejo can later verify by reading library source code. Triggers on proud-zanahoria, contrarian review, inverse review, devil's advocate PR, zanahoria.
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes