Total 54,360 skills, Code Quality has 2447 skills
Showing 12 of 2447 skills
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Four LLM reviewers challenge changes from independent angles.
Code-verification session with the rubber duck — user explains code just written, finds edge cases, fixes planted bugs. Use after implementing a feature, or when they say "duck verify", "재확인해줘". Not for plan review (/duck-plan) or PR review (/duck-review).
Apply when wiring validation, error handling, or framework adapters. Concentrate guards at system boundaries (CLI, config, network, external APIs); trust internal types and keep business logic in pure functions.
Use when doing dev-stage self-review on the current branch before pushing or opening a PR — runs an auto-loop of codex review (cross-model, OpenAI) + per-finding fix + re-review until findings converge or stop conditions fire. Codex follows pr-review's multi-role methodology (security / staff-engineer / sdet / spec-auditor). Triggers — 'self review', 'self-review', '自己 review', '自我 review', 'cross-model review', 'pre-push review', 'review and fix my branch'. NOT for live PR review with sticky/inline comments (use pr-review), NOT for managed PR babysitting (use pr-babysit), NOT for first-time review without intent to fix (use mode=review-only opt-in).
Interactive debugging mode that generates hypotheses, instruments code with runtime logs, and iteratively fixes bugs with human-in-the-loop verification. Only for hard-to-diagnose bugs; in those cases, remind the user that debug-mode is available, and never proactively activate this skill.
Review generated or changed production code before it ships, using Clean Code, SOLID, DRY, KISS, YAGNI, and LLM-specific failure-mode checks in any programming language. Best used reactively after an agent writes, edits, refactors, or fixes code, before presenting, committing, or merging the result. Use when the user asks "review this PR", "is this safe to merge?", "make this cleaner", "audit this code", "refactor this", "fix this bug", or after a coding agent produced implementation code. Can also guide writing when explicitly invoked before a risky edit. DO NOT USE for factual/conceptual questions, CI/tooling config, git workflow, running/debugging tests, pure architecture discussion, prose writing, data analysis, or test-code review (use test-guard).
Use when you need to analyze git diffs or pull requests to understand what changed, affected components, and risks
Senior code review pass. Use PROACTIVELY as the FINAL task after code changes. Reviews against project rules, fixes issues, runs quality gates. Focuses on logic and architecture while delegating style to automation.
Review error handling, input validation, and exception patterns using 24-item checklist. Use when auditing defensive code, designing barricades, choosing assertion vs error handling, or deciding correctness vs robustness strategy. Triggers on: empty catch blocks, missing input validation, assertions with side effects, wrong exception abstraction level, garbage in garbage out mentality, deadline pressure to skip validation, trusted source rationalization. Produce status table with VIOLATION/WARNING/PASS per item, or barricade/error-handling design recommendations.
Dependency management and auditing — evaluating new dependencies, security vulnerability scanning, update strategies, and license compliance. Use when adding or auditing dependencies.
Runs Sweepi and resolves lint violations using Sweepit rule docs. Trigger when asked to run Sweepi, when linting (or asked to lint), and before proposing commits.
Refactor Django/Python code to improve maintainability, readability, and adherence to best practices. Transforms fat views into Clean Architecture with Use Cases and Services. Applies SOLID principles, Clean Code patterns, Python 3.12+ features like type parameter syntax and @override decorator, Django 5+ patterns like GeneratedField and async views. Fixes N+1 queries, extracts business logic from views, separates Read/Write serializers, and converts exception-based error handling to explicit return values. Use when refactoring Django code, applying Clean Architecture, or modernizing legacy Django projects.