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 13,945–13,968 of 15,938 skills
- Alexbaum Ai Neurm Claude Skills Deep Thinker SkillStructured reasoning for complex problems using Sequential Thinking MCP. Break down problems into stages, track thought progression, identify connections, and generate insights. Use for architectural decisions, complex debugging, research planning, or any problem requiring deep analysis.Votes: 0GitHub stars: 666
- 31 Analyze Think 150[31] ANALYZE. Universal deep thinking methodology for any situation requiring quality reasoning. Use when solving problems, debugging, making decisions, analyzing code, planning, reviewing, or anytime you need thorough thinking instead of surface-level responses. Triggers on \"think deeply\", \"analyze thoroughly\", \"reason carefully\", \"deep thinking\", \"understand completely\", or any task requiring careful thought.Votes: 0GitHub stars: 666
- 31 Analyze Think 150 Mykhailodmytriakha My Preacher Helper 3[31] ANALYZE. Universal deep thinking methodology for any situation requiring quality reasoning. Use when solving problems, debugging, making decisions, analyzing code, planning, reviewing, or anytime you need thorough thinking instead of surface-level responses. Triggers on \"think deeply\", \"analyze thoroughly\", \"reason carefully\", \"deep thinking\", \"understand completely\", or any task requiring careful thought.Votes: 0GitHub stars: 666
- Qwen Training Data Miner Prototype Foundup Foundups AgentQwen Training Data Miner (Prototype)Votes: 0GitHub stars: 666
- When Optimizing Prompts Use Prompt Optimization Analyzer DnyoussActive diagnostic tool for analyzing prompt quality, detecting anti-patterns, identifying token waste, and providing optimization recommendationsVotes: 0GitHub stars: 666
- Research React Pascallammers Mylo Travel ConciergResearch React 19 patterns, hooks, and best practices using Exa code search and Ref documentationVotes: 0GitHub stars: 666
- Qwen CoderProvides Qwen Coder CLI delegation workflows for coding tasks using Qwen2.5-Coder and QwQ models, including English prompt formulation, execution flags, and safe result handling. Use when the user explicitly asks to use Qwen for tasks such as code generation, refactoring, debugging, or architectural analysis. Triggers on "use qwen", "use qwen coder", "delegate to qwen", "ask qwen", "second opinion from qwen", "qwen opinion", "continue with qwen", "qwen session".Votes: 0GitHub stars: 666
- Prompt Improver Existential Birds BeagleOptimize prompts for code-related tasks following Claude best practices. Use when refining prompts for implementation, debugging, refactoring, code review, or testing.Votes: 0GitHub stars: 666
- Oracle GeminiThis skill should be used when the user asks to "use Gemini", "ask Gemini", "consult Gemini", "Gemini review", "use Gemini for planning", "ask Gemini to review", "get Gemini's opinion", "what does Gemini think", "second opinion from Gemini", mentions using Gemini as an oracle for planning or code review. NOT for implementation tasks.Votes: 0GitHub stars: 666
- Opencode ZenInvoke the 'opencode' CLI in headless mode for AI-powered code analysis, reviews, and second opinions. Use when you need a different AI perspective, the user mentions opencode, or requests batch code analysis.Votes: 0GitHub stars: 666
- Gemini Vero Ventures FuzzycatOffload tasks to Google Gemini CLI to preserve Claude credits. Gemini has internet access and strong code analysis. Use for code reviews, summaries, test generation, diff analysis, and general questions. Prefer Gemini over Ollama when internet/API knowledge is needed.Votes: 0GitHub stars: 666
- Sub Agent Patterns Dennislee928 Smart Zone 2Comprehensive guide to sub-agents in Claude Code: built-in agents (Explore, Plan, general-purpose), custom agent creation, configuration, and delegation patterns. Use when: creating custom sub-agents, delegating bulk operations, parallel research, understanding built-in agents, or configuring agent tools/models.Votes: 0GitHub stars: 666
- MetathinkMetathink - Optimize Claude Code usage through metacognitive strategies. Use extended thinking, context engineering, task decomposition, and chain-of-thought prompting. Use when planning complex tasks, debugging difficult issues, making architectural decisions, or improving AI collaboration effectiveness.Votes: 0GitHub stars: 666
- Behavioral Modes Darthlinuxer Agentic SkillsAI operational modes (brainstorm, implement, debug, review, teach, ship,Votes: 0GitHub stars: 666
- Atlas Agent DeveloperImplementation and troubleshooting agent - builds features and fixes bugsVotes: 0GitHub stars: 666
- Rich SkillA rich agent skill with extra metadataVotes: 0GitHub stars: 4
- Trust Boundaries AuthzEnsure designs define trust boundaries, authn/authz responsibilities, and propagation of identity/claims across services.Votes: 0GitHub stars: 4
- Security Privacy DesignReview data retention, deletion, backup residency, and cross-border data transfer.Votes: 0GitHub stars: 4
- Review Policy Standard UpstreamApplies standard AI review policy guidelines for upstream (design) phase reviews.Votes: 0GitHub stars: 4
- Pre Mortem変更が将来インシデントや技術的負債を引き起こすと仮定し、その原因と経路を逆算して設計の盲点を可視化するVotes: 0GitHub stars: 4
- Pr Template QaPRテンプレートの必須項目（日本語記載、Diátaxis、検証コマンド、チェックリスト）が明確かを確認し、抜けや誤解を生む文言を指摘するVotes: 0GitHub stars: 4
- Plangate Tdd EvidenceTDD を主張する実装の RED/GREEN/REFACTOR VERIFY 証跡（tdd-ledger）の妥当性を検査し、フェーズ順序・exitCode・test-cases との対応の欠落や偽装を検知するVotes: 0GitHub stars: 4
- Multitenancy Isolationマルチテナント前提の設計差分から、テナント分離（データ/権限/リソース/障害影響）の抜けや越境リスクを検出Votes: 0GitHub stars: 4
- External DependenciesEnsure designs document third-party dependencies, SLAs, quotas, failure modes, and vendor lock-in mitigation.Votes: 0GitHub stars: 4