Code Review
Automated code review and analysis
subagent-driven
by SipengXie2024
Use when executing implementation plans with independent tasks in the current session
license-check
by manastalukdar
License compliance checking and conflict detection
lecture-alchemist
by PrakharMNNIT
"Transform raw lecture transcripts (Zoom, YouTube, etc.) into structured, retention-optimized study notes. Use when the user provides a lecture transcript, class recording text, or asks to process/convert lecture notes. Handles WebDev, AI/ML, Web3, DSA, and general tech domains. Produces hierarchical topic breakdowns, cleaned code artifacts, intuition builders, flashcards, spaced repetition plans, and actionable study materials. Trigger phrases: 'process this transcript', 'convert lecture to notes', 'lecture notes', 'transcript to study material', 'Lecture Alchemist'."
@tank/idd
by tankpkg
Intent-Driven Development: define what and why before writing how. AI writes code; humans write intent. Covers the full IDD lifecycle — structured interviewing, design critique, section locking, phased TDD execution, and code-intent drift detection. Opinionated synthesis of ArcBlock/idd, Praxis, and FORGE (all MIT). Trigger phrases: "IDD", "intent driven development", "intent file", "INTENT.md", "intent interview", "intent critique", "intent review", "intent plan", "intent build", "intent sync", "intent check", "intent audit", "intent init", "intent driven", "implementation last", "AI native development", "intent standard", "intent approval", "drift detection", "convergence check", ".idd folder"
ask-vue-mechanic
by NavanithanS
Vue 3 + Inertia maintenance. Fixes navigation reloads, prop mismatches, reactivity loss.
analyze-video
by evillollive
Use when the user wants to analyze one or more videos (URLs or local files) and produce a Word document with embedded frames and a written timestamp-based analysis. Triggers on "analyze this video", "make a report from this video", "write up this YouTube link", "document what's in these videos", "analyze these clips", "video analysis", or any request that includes video URLs or local video paths and asks for a written deliverable.
prune-context-file
by RichardBray
Audit and prune bloated CLAUDE.md or AGENTS.md context files using evidence-based criteria from research on what actually helps coding agents. Use when a user asks to trim, audit, review, or improve their CLAUDE.md, AGENTS.md, or any repository context file for AI coding agents.
execute
by open-horizon-labs
Do the work. Pre-flight, build, detect drift, salvage if needed. Use when you have a clear aim and are ready to implement.
codex-review
by jrajasekera
Use after creating design docs or implementation plans to get cross-agent review from Codex. Auto-triggers for non-trivial plans; asks first for simple changes. Captures feedback, addresses critical issues, presents minor concerns for user decision.
ask-explaining-code
by NavanithanS
Explain code via analogies, ASCII diagrams, step-by-step walkthroughs.
bundle-analyze
by manastalukdar
Bundle size analysis and optimization for Webpack, Vite, and esbuild
pr-review
by brucehart
"Conduct a full review of a pending GitHub PR by reading all PR comments, inline review threads, and attached/subordinate PRs; validate expected behavior from code and PR text; and post severity-tagged security/functionality/code-smell issues as comments on the PR."
receiving-review
by SipengXie2024
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
aim
by open-horizon-labs
Clarify the outcome you want - a change in user behavior, not a feature shipped. Use at the start of any work to ground the session in strategic intent.
spike
by corygabrielsen
Implement N approaches as separate branches, then compare side-by-side. Removes "implementation effort" as a variable from the decision.
diff-check
by b1tank
Author's cleanup checklist before committing or submitting a PR. Use before any commit or PR to ensure code is clean, focused, and ready for review. Checks for debug code, secrets, redundant changes, and scope creep.
github-investigator
by range3
GitHub上の特定トピックに関するIssue・PR・コードの議論を調査し、要約レポートを作成するスキル。 ghコマンドを使用する。ユーザーがGitHubリポジトリでの議論の調査、Issue/PRの横断的な分析、 特定の機能・バグ・コンポーネントに関する経緯の把握、GitHubでの意思決定の追跡を求めた場合に使用すること。 「このリポジトリで○○についてどんな議論がある？」「○○の経緯を調べて」「関連するIssueやPRをまとめて」 「○○はなぜこういう設計になった？」といったリクエストにも対応する。 明示的にGitHubと言及していなくても、OSS の機能議論や設計経緯の調査であればこのスキルを使う。
gh-pr-feedback
by brucehart
Address GitHub pull request review feedback using the gh CLI. Use when given a PR number and asked to read the PR comments/reviews, implement unaddressed reviewer updates, prioritize project owner feedback, and submit the fixes as a stacked/sub-PR targeting the original PR branch.
ralpha-loop
by Idate96
Implement-test-review loop for coding tasks with strict iteration until reviewer has zero findings. Use when asked to implement changes, run tests, request review, address findings, retest, and repeat. Optimize for reusing the same reviewer agent across iterations instead of spawning new reviewers each cycle.
@tank/bdd-issue-fixer
by tankpkg
Resolve GitHub issues using BDD — read the issue, write a behavioral test, confirm it fails (RED), fix the code, confirm it passes (GREEN), open a PR with test + fix as proof. Covers issue triage (bug vs feature vs invalid vs duplicate), issue-to-Gherkin translation, the relentless RED-GREEN fix cycle, fix verification, PR submission with evidence, and related issue detection. Synthesizes Smart/Molak (BDD in Action), Beck (TDD By Example), Nicieja (Writing Great Specifications), SWE-bench (Princeton NLP), and Sweep.dev patterns. Trigger phrases: "fix this issue", "resolve issue", "fix GitHub issue", "BDD fix", "issue to test", "write test for issue", "red green fix", "triage issue", "duplicate issue", "related issues", "fix and PR", "issue fixer", "auto-fix issue", "resolve bug report"
domain-scoping
by Semprini
Use this skill when starting a new domain model, when the user says "model this domain" or describes a business area from scratch, when scoping or boundary questions arise, or when choosing between canonical and domain-driven modelling strategies. Also use when the user asks who should own a concept or whether two concepts are the same thing across different domains.
ask-code-reviewer
by NavanithanS
Start code reviews, PR checks, or bug analysis. Triggers: "review my code", "check this PR", "analyze for bugs", "code review". Do NOT use for: - Automating fixes (use ask-python-refactor). - Generating new features. Capabilities: - Static analysis: Correctness, Security, Performance, Style. - Feedback priority: Critical > Performance > Style.
review-skill
by corygabrielsen
Review a skill document using specialized reviewers. Each reviewer finds specific issue types.
pr-review-loop
by xpepper
Use when addressing open PR review comments from any reviewer (human or bot) within the current agent session. For a fresh-context-per-comment approach, use ralph-wiggum-loop instead.