Loading...
Loading...
Found 194 Skills
Interactive Code Review: Inspect architecture, code quality, testing, and performance section by section. Can review git diff, specified files, or entire PRs. Trigger words: /code-review, review code, code review, code review
Patterns for Ralph loop tasks. Auto-loaded to provide guidance on completion signals, progress tracking, and iteration patterns. Ralph = autonomous issue-to-merged-PR loop.
AI-powered code review via the OpenAI Codex CLI. This skill should be used when reviewing branch diffs before merging a PR, auditing uncommitted changes during development, inspecting a specific commit, performing custom-scoped reviews, or whenever changes touch security-sensitive paths or exhibit risky patterns.
Use this skill to process bot review feedback on a pull request (for example coderabbitai and chatgpt-codex-operator). Invoke when bot comments arrive and the user wants triage, decision making, and implementation of required fixes.
Resolve all PR review comments (human and bot) on current PR. Fetches unanswered comments, evaluates each one, fixes real issues, dismisses false positives, and replies to every comment with the outcome.
Review all unresolved PR review threads, address them by making necessary code changes, and commit the changes appropriately.
Adversarial code review with anti-trust verification. Verifies every implementer claim against the actual diff. Use when reviewing PRs, branches, or recent commits.
Use when a PR has reviews and is ready for final validation, to verify minimum 3 different agents reviewed and no critical concerns were raised before merging
GitHub PR の CI ステータス (`gh pr checks`)・コード品質・セキュリティ (OWASP Top 10)・Conventional Commits 準拠をレビューする。`gh pr review --approve/--request-changes/--comment` でレビュー投稿も可能。「PR #N をレビュー」「PR レビューして」などで使用。ローカル diff のレビューには implement-review を使用。
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.
Scans other open issues to find ones a given PR may also fix or accidentally break. Outputs adjacent-fix opportunities and contradiction risks with file:line evidence. Use when reviewing a PR to discover bundling opportunities or downstream impact across the issue queue.
Conduct thorough code reviews with structured feedback on security, performance, architecture, and testing. Generates trackable review documents with prioritized issues (critical/required/suggestions) and educational content. Use when reviewing PRs or code changes. Triggers on "review this code", "code review", "review PR".