Total 54,997 skills, Code Quality has 2472 skills
Showing 12 of 2472 skills
Execute coding tasks with a strict delivery workflow: build a full plan, implement one step at a time, run tests continuously, and commit by default after each step (`per_step`). Support explicit commit policy overrides (`final_only`, `milestone`) and optional BDD (Given/When/Then) when users ask for behavior-driven delivery or requirements are unclear.
Identifies silent failures, inadequate error handling, and inappropriate fallback behavior in code. Zero tolerance for errors that occur without proper logging and user feedback. Triggers: When reviewing error handling, checking for silent failures, analyzing catch blocks. Examples: - "Review the error handling" -> audits all error handling in recent changes - "Check for silent failures" -> hunts for swallowed errors and empty catch blocks - "Analyze catch blocks in this PR" -> reviews every try-catch for adequacy - "Are there any hidden failures?" -> finds errors that get silently ignored
Review existing code, diffs, branches, or pull requests using concern-specific reviewer personas and evidence. Use when auditing someone else's work, triaging risk in a PR, or producing a ship-it / needs-review / blocked verdict. Do not use to verify your own completed change; use `verify` for that.
Launch an isolated Claude reviewer for the current branch, a specific commit, or uncommitted changes. Uses Claude's agent runtime with worktree isolation so the review has an independent read-only view of the code before findings are reported back.
Run OpenAI Codex CLI as an independent reviewer over the current branch, a specific commit, or uncommitted changes. Builds a focused instruction file from the real diff and returns a compact review summary.
Acts as a Senior Staff Engineer to enforce high-quality software development standards. Use this skill when the user asks for code implementation, architectural review, debugging, or technical design. It ensures all code is production-ready, typed, and architecturally sound.
Enter this sub-process when conducting code optimization — handle tasks where 'behavior remains unchanged, structure changes' (structure / performance / readability). Shift single-module internal optimization from 'AI random refactoring' to 'first scan to generate a checklist, confirm each item with the user, execute step-by-step according to the method library, and require manual approval for each step'. Trigger scenarios: Users mention phrases like 'optimize it / refactor / rewrite / split it / poor performance / code is too long' without any accompanying behavior changes. Do not handle new requirements (route to feature), bugs (route to issue), or cross-module architecture restructuring (route to architecture + decisions).
Scans code for performance and scalability issues — N+1 queries, missing indexes, unbounded queries, memory inefficiencies, caching gaps, algorithmic complexity, concurrency bugs, and frontend performance problems. Generates severity-scored findings with copy-pasteable fix prompts. Trigger phrases: "performance audit", "performance check", "N+1 detection", "query optimization", "slow code", "performance review".
· Run combined code-review, anti-slop, security-audit, and update-docs pass. Triggers: 'full review', 'review everything', 'audit this repo', 'full check', 'run all checks'. Not for single-dimension audits.
Use when debugging bugs, test failures, build failures, performance regressions, or unexpected behavior and you need root-cause investigation before proposing fixes. Trigger on requests to debug, investigate why something broke, or find the source of a technical issue.
Data-driven modularity specialist - Masters ScriptableObjects, decoupled systems, and single-responsibility component design for scalable Unity projects
Language-specific verification for Python, TypeScript/JavaScript, and Go. Checks type safety, language idioms, and best practices. Use when asked to "verify language", "check types", or for language-specific checks.