Total 50,483 skills, Code Quality has 2287 skills
Showing 12 of 2287 skills
Build or update the code review knowledge graph. Run this first to initialize, or let hooks keep it updated automatically.
Use when restructuring existing code without changing observable behavior, especially when a feature or bug fix is hard because the current design is awkward, duplicated, confusing, or risky to modify.
Reliable end-to-end engineering workflow for debugging, root-cause analysis, minimal patching, and verification in production codebases. Use when Codex needs to investigate a failure systematically, trace execution, test hypotheses, implement a correct fix, validate the resolution, and check for regressions before declaring the task complete.
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".
Loads orchestrate mode — a disciplined delivery loop that enforces BDD specs in specs/, real integration tests (no mocks), PR CI and CodeRabbit babysitting, and mandatory end-user QA via computer-use or CLI dogfooding before anything is considered done. Use when starting any non-trivial implementation task, feature build, or delivery where you want the work driven from spec to proven-shipped state rather than stopping at "tests pass".
Ban `as` type assertions in a package via the `@typescript-eslint/consistent-type-assertions` lint rule, replacing them with compiler-verified type-safe alternatives. Use when enabling the assertion ban in a new package or fixing violations in an existing one.
Review changed code for reuse, quality, and efficiency, then fix any issues found.
Holistic, system-aware planning before implementing non-trivial tasks. Use when the task involves new features, architectural decisions, multi-file changes, unclear requirements, or multiple valid approaches. Triggers on "/plan", "plan this", "design an approach", "let's plan first".
· Audit AI-generated code slop: hallucinated APIs, over-abstraction, duplicate code, test theater, noisy comments. Triggers: 'slop', 'AI-generated code', 'cleanup', 'overengineered'. Not for prose (use anti-ai-prose).
Comprehensive pull request review using specialized agents
Generate a visual diff review page (ArchitectureGrid for impacted modules + CodeDiff for hunks + Callouts for risks) from a git range, PR URL, or pasted diff. Use whenever the user asks for a PR review, diff summary, change impact analysis, or pastes `git diff` output. Requires the `hyperscribe` skill (renderer engine).
Research the codebase to answer questions. Search for relevant files, gather context, and provide clear answers.