Total 50,472 skills, Code Quality has 2287 skills
Showing 12 of 2287 skills
Have Codex CLI review uncommitted code changes. Claude Code then fixes valid issues and rebuts invalid ones. Codex re-reviews. Repeat until consensus. Codex never touches code — it only reviews.
Review PyTorch pull requests for code quality, test coverage, security, and backward compatibility. Use when reviewing PRs, when asked to review code changes, or when the user mentions "review PR", "code review", or "check this PR".
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
Comprehensive toolkit for validating, linting, testing, and automating Ansible playbooks, roles, and collections. Use this skill when working with Ansible files (.yml, .yaml playbooks, roles, inventories), validating automation code, debugging playbook execution, performing dry-run testing with check mode, or working with custom modules and collections.
Systematic debugging methodology — binary search isolation, hypothesis-driven debugging, reproducing issues, and root cause analysis. Use when debugging errors, unexpected behavior, or test failures.
Manage global ignore patterns for lint-relative-paths. TRIGGERS - statusline ignore, add ignore pattern, lint ignore, path lint exclude.
Find orphan functions, dangling imports, and dead code via GitNexus CLI (npx gitnexus@latest). CLI ONLY - NO MCP server exists, never use readMcpResource with gitnexus:// URIs. TRIGGERS - dead code, orphan functions, unused imports, dangling references, unreachable code.
Unblock a PR: resolve conflicts, fix CI, address reviews. Composes: git-mastery conflict resolution, /fix-ci, /respond, /address-review. Use when: PR is blocked by conflicts, red CI, or unaddressed review feedback.
Diagnose and fix bugs with root-cause analysis and verification. Use when you have a concrete issue report, failing behavior, runtime error, or test regression that should be resolved safely. For ambiguous, high-risk, or broad-scope issues, stop and route to write-plan first.
Use when validating code quality after modifications. Runs sniper agent in isolated forked context for clean, fast validation.
Systematic code refactoring following Martin Fowler's catalog. Methodologies: characterization tests, Red-Green-Refactor, incremental transformation. Capabilities: SOLID compliance, DRY cleanup, code smell detection, complexity reduction, legacy modernization, design patterns, functional programming patterns. Actions: refactor, extract, inline, rename, move, simplify code. Keywords: refactor, SOLID, DRY, code smell, complexity, extract method, inline, rename, move, clean code, technical debt, legacy code, design pattern, characterization test, Red-Green-Refactor, functional programming, higher-order function, immutability, pure function, composition, currying, side effects. Use when: improving code quality, reducing technical debt, applying SOLID principles, fixing DRY violations, removing code smells, modernizing legacy code, applying design patterns.
Consult this skill when building evaluation or scoring systems. Use when implementing evaluation systems, creating quality gates, designing scoring rubrics, building decision frameworks. Do not use when simple pass/fail without scoring needs.