All categories
Code Review & Quality
Code review, refactoring, debugging, maintainability, and engineering quality
- 15,938
- 665
Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.
Open in full browserBrowse code review & quality skills
Showing 15,049–15,072 of 15,938 skills
- AnalyzeDeep analysis and investigationVotes: 0GitHub stars: 28
- Code ReviewerReview actual code implementations (Python, JavaScript, TypeScript, React) for correctness, maintainability, security hygiene, and adherence to project patterns. Use when reviewing pull requests to ensure code quality, proper error handling, adequate test coverage mapped to acceptance criteria, and alignment with architecture boundaries and review standards.Votes: 0GitHub stars: 37
- Ci Code ReviewerAutomated CI code review for GitHub PRs using OpenAI Codex. Validates PR descriptions, checks implementation alignment, enforces Quest architecture boundaries, and maps test coverage to acceptance criteria when PRs move to ready-for-review.Votes: 0GitHub stars: 37
- Prd WriterWrite PRD, 写产品需求文档。Use when: 需要写新功能 PRD（有UI/无UI）、第三方集成、功能重构、性能/安全优化需求。Votes: 0GitHub stars: 82
- ReviewRead the changeset yourself, review it with one Claude reviewer and one codex reviewer on the same target at once, triage their findings with /triage, and iterate until a round returns no breaking finding. TRIGGER on "review the changes", "code review", on the Review before a changeset is presented to the Architect, and when a /orchestrate or /verify-changes step names it. DO NOT TRIGGER for N identical reviewers on one Task (that is /independent-review).Votes: 0GitHub stars: 22
- Independent ReviewRun N identical parallel Subagents on the same Task for independent Verification. Use when the Architect wants consensus through redundancy — multiple Subagents independently analyze, review, or test the same thing, then the combined returns are triaged with /triage. Invocation /independent-review [count] "task"Votes: 0GitHub stars: 22
- TriageTriage PR review comments — assess, fix what's actionable, post status updateVotes: 0GitHub stars: 23
- Tell Me MoreElaborate on a concept just mentioned — explain from knowledge, not searchVotes: 0GitHub stars: 23
- Sp Writing SkillsUse when creating new skills, editing existing skills, or verifying skills work before deploymentVotes: 0GitHub stars: 23
- Sp Complete DesignCompletion phase for a written plan. Self-review, gather missing input, update state, and request review — with explicit output-channel partitioning so only summaries and open questions reach the human.Votes: 0GitHub stars: 23
- Code ReviewWhen running a code review, follow the process outlined here.Votes: 0GitHub stars: 270
- Architectural Analysis- git installed: !`which git 2>/dev/null || echo "not installed"` - CLAUDE.md: !`find . -maxdepth 1 -name "CLAUDE.md" -type f` - project-discovery.md: !`find . -maxdepth 3 -name "project-discovery.md" -type f` - personal config directory: !`bash "${CLAUDE_PLUGIN_ROOT}/scripts/han-config-dir.sh" 2>/dev/null || echo "$HOME/.claude"` - project .han/config.md: !`cat .han/config.md 2>/dev/null || echo ""`Votes: 0GitHub stars: 270
- Gitnexus GuideUse when the user asks about GitNexus itself — available tools, how to query the knowledge graph, MCP resources, graph schema, or workflow reference. Examples: \"What GitNexus tools are available?\", \"How do I use GitNexus?\"Votes: 0GitHub stars: 6
- Cli> Command-line tool for scaffolding, registering, and running agents on Nookplot.Votes: 0GitHub stars: 16
- OhmyclawOpenClaw 용 멀티프로바이더/멀티계정 라우팅 하네스. Z.ai 코딩플랜(Lite/Pro/Max) 모델 매트릭스 + ChatGPT Codex OAuth 다중 계정 풀(round-robin/cooldown/fan-out) + 추론 인식 모델 선택 + Plan→Work→Review 오케스트레이션 + 5관점 리뷰와 갭 감지. Use when: (1) Z.ai GLM 코딩 작업, (2) 다중 ChatGPT/Z.ai 계정으로 rate limit 분산, (3) 한국어 코딩/리뷰/리팩토링, (4) Plan→Work→Review 사이클로 다단계 작업 분해, (5) 같은 태스크를 여러 계정에 fan-out. NOT for: (a) 단순 1-line 수정, (b) read-only 탐색, (c) Z.ai/Codex 가 아닌 다른 프로바이더 단독 작업.Votes: 0GitHub stars: 61
- manimThis skill should be used when the user asks to "create an animation", "make a manim video", "animate this concept", "visualize this process", "create a GIF for my blog", "plot a graph", "animate a value", or mentions "manim", "mathematical animation", "code animation", "process visualization", "technical animation", "3D scene", "camera animation", "ValueTracker", "number animation". Provides ManimCE (Community Edition) syntax, patterns, and best practices for creating programmatic animations.Votes: 0GitHub stars: 6
- uni-imageUnified multi-platform AI image generation. Supports Volcengine Seedream, Alibaba Qwen Image, and Google Gemini (Nano Banana). Switch between models with a dropdown selector.Votes: 0GitHub stars: 2
- RefactoringRefactoring techniques for Object Pascal focused on improving readability, removing code smells, and preserving behavior through practices like Extract Method, Guard Clauses, and polymorphism.Votes: 0GitHub stars: 50
- Code ReviewDelphi code review checklist — quality, security, performance, SOLID, memoryVotes: 0GitHub stars: 50
- Clean CodePragmatic clean code standards for Delphi — concise, direct, no over-engineeringVotes: 0GitHub stars: 50
- Deep AnalysisAnalytical thinking patterns for comprehensive evaluation, code audits, security analysis, and performance reviews. Provides structured templates for thorough investigation with extended thinking support.Votes: 0GitHub stars: 43
- DebuggerDiagnose and fix code bugs with systematic analysisVotes: 0GitHub stars: 38
- Code AnalystDeep code review, quality analysis, and improvement suggestionsVotes: 0GitHub stars: 38
- Deep AnalysisAnalytical thinking patterns for comprehensive evaluation, code audits, security analysis, and performance reviews. Provides structured templates for thorough investigation with extended thinking support.Votes: 0GitHub stars: 188