Total 54,172 skills, Code Quality has 2444 skills
Showing 12 of 2444 skills
Use when reviewing code, pull requests, branches, diffs, or changed files for quality, correctness, security, performance, and style issues.
Adversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent changes, before merging a PR, or when you suspect Claude is being too agreeable about code quality. Forces perspective shifts through hostile reviewer personas that catch blind spots the author's mental model shares with the reviewer.
Designs and refactors software codebases to be AI-friendly by aligning the filesystem with domain/feature boundaries, creating deep (greybox) modules with small public interfaces, enforcing import boundaries, and tightening tests/feedback loops. Use when the user asks to "make the codebase AI-ready", "reduce coupling", "introduce deep modules", "create module boundaries", "restructure folders by feature", "define service interfaces", or "plan a refactor + tests so AI agents can work safely".
Scans the project and configures checks and reviews for Agent Validator for requests such as "set up validator", "configure checks and reviews", or "initialize validator for this repo".
Handles commit flows by detecting changes, optionally running validator validation, and completing commits for requests such as "commit with validator", "run checks before commit", "run validator then commit", or "skip validator and commit".
Generate a single-file interactive HTML code-review artifact for a GitHub PR. Fetches the diff via the gh CLI, performs an honest severity-coded self-review, and renders an artifact with: collapsible per-file diffs with colored inline annotations, severity filter chips, per-finding checkboxes, and a "Create feedback prompt" modal that aggregates the checked items into a paste-ready follow-up prompt ending with "Please address this feedback. Address each individual item in its own conventional commit." Use this skill whenever the user wants to review a pull request visually, asks for an HTML or static review artifact, says "review PR", "review this PR", "build a PR review", wants color-coded findings, feedback aggregation, or a review file they can share — even if they don't explicitly say "HTML". Also trigger on "code review artifact", "interactive review", "feedback prompt for a PR", or when the user mentions reviewing a specific PR number.
Selects, configures, and integrates a static analysis tool for the project's language. Covers tool selection, rule configuration, CI integration, fixing existing violations, and pre-commit hook setup. Invoked when the user asks to add linting, set up static analysis, or configure a code quality tool.
Run linting, formatting, and static type checks on a Django project using ruff and pyrefly, and fix any issues found. Use after making code changes, before committing, or whenever the user asks to lint, format, or type-check the codebase.
Investigate a bug observed in the running application by reading the generated code in plain_modules/, tracing the issue back to the specs, and fixing only the .plain files. Generated code is never modified. Use when the user reports unexpected behavior, visual glitches, crashes, or incorrect logic in the app.
Token-efficient GitHub source code exploration via tree-sitter AST parsing and structured retrieval
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.
Parallel adversarial review protocol that launches two independent blind judge sub-agents simultaneously to review the same target, synthesizes their findings, applies fixes, and re-judges until both pass or escalates after 2 iterations. Trigger: When user says "judgment day", "judgment-day", "review adversarial", "dual review", "doble review", "juzgar", "que lo juzguen".