Agent skills

Code Review & Quality skills

Read straight from the source repositories, not from submitted listings. Every skill shows what it does, what is inside, where it came from — and whether attention around its source is actually growing.

Toolclaude-code 29,140codex 4,755cursor 3,111copilot 976windsurf 55cline 34
CategoryWorkflow & Productivity 4,979AI & Agents 3,037Data & Analytics 2,345Code Review & Quality 1,376Backend & API 1,244Security 1,194Design & Presentation 1,154Documentation 965Content & Marketing 916Testing & QA 777DevOps & Cloud 576Databases 550Frontend 469Business & Finance 328Media & Video 257Other 9,833
2,936 found
913960 · page 20 / 62
lit-pmUse when coordinating comprehensive literature reviews requiring multi-stage pipeline (archival setup, scope refinement, parallel…majiayu000lit-reviewStructured literature search and synthesis with citation extraction and gap identificationmajiayu000writeslit-review-assistantSearch, summarize, and synthesize economics literaturebrycewang-stanfordlit-synthesizerSenior scientific author for literature review synthesis with authority to restructure, rewrite, and add analysis across outline…majiayu000lit-synthesizerSenior scientific author for literature review synthesis with authority to restructure, rewrite, and add analysis across outline…majiayu000literature-researcherSpecialized literature review skill with review discovery, deep targeted research (15-30 papers per section), recency surveys…majiayu000literature-researcherSpecialized literature review skill with review discovery, deep targeted research (15-30 papers per section), recency surveys…majiayu000literature-retrievalComplete literature retrieval capability combining search and filter skills. LOAD THIS SKILL WHEN: User needs "文獻檢索", "找文獻"…majiayu000literature-review-agentStep 3 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the literature search strategy from outline.json — discover…majiayu000literature-review-builderStructure a literature review that argues, not lists — thematic synthesis from your sources with the debate mapped and the gap…mohitagw15856Literature ReviewSystematic literature search, synthesis, gap identification, and narrative construction for academic researchmajiayu000literature-reviewSystematic search methodology, taxonomy construction, citation graph exploration, and related work synthesis for ML research.majiayu000literature-reviewConduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar…majiayu000writesliterature-reviewConduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar…majiayu000writesliterature-reviewConduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar…majiayu000literature-reviewConduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar…majiayu000writesliterature-review使用多个学术数据库(如 PubMed、arXiv、bioRxiv、Semantic Scholar 等)开展全面、系统化的文献综述。适用于系统综述、Meta 分析、研究综合,或跨生物医学、科学和技术领域的全面文献检索。可生成包含已验证引用的专业格式…majiayu000writesliterature-searchSearch and retrieve academic literature from multiple databases. LOAD THIS SKILL WHEN: User says "搜尋文獻", "search literature"…majiayu000literature-survey-generatorGenerate a complete academic literature survey from scratch using multi-agent orchestration. Searches academic databases…brycewang-stanfordwritesllm-evaluationImplement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use…majiayu000llm-evaluationImplement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use…majiayu000llm-evaluationImplement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use…majiayu000llm-evaluationImplement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use…majiayu000llm-evaluationImplement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use…majiayu000llm-evaluationImplement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use…majiayu000llm-evaluationImplement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use…majiayu000llm-evaluationImplement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use…majiayu000llm_evaluationImplement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use…majiayu000llm-evaluationImplement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use…wshobsonllm-judgeUse when comparing two or more code implementations against a spec or requirements doc. Triggers on \"which repo is better\"…majiayu000llm-mcp-builder-devGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through…majiayu000llm-prompt-optimizerUse when improving prompts for any LLM. Applies proven prompt engineering techniques to boost output quality, reduce…majiayu000ln-311-review-research-workerUse when an evaluation run needs mandatory official-doc, MCP Ref, Context7, and current best-practice research with a structured…majiayu000ln-311-review-research-workerUse when an evaluation run needs mandatory official-doc, MCP Ref, Context7, and current best-practice research with a structured…majiayu000ln-312-review-findings-workerUse when an evaluation coordinator needs normalized findings from target artifacts and research evidence.majiayu000ln-641-pattern-analyzerL3 Worker. Analyzes single pattern implementation, calculates 4 scores (compliance, completeness, quality, implementation)…majiayu000ln-641-pattern-analyzerAnalyzes single pattern implementation, calculates compliance/completeness/quality scores, identifies gaps. Use when auditing a…majiayu000ln-641-pattern-analyzerAnalyzes single pattern implementation, calculates compliance/completeness/quality scores, identifies gaps. Use when auditing a…majiayu000writesln-641-pattern-analyzerAnalyzes single pattern implementation, calculates compliance/completeness/quality scores, identifies gaps. Use when auditing a…majiayu000ln-641-pattern-analyzerL3 Worker. Analyzes single pattern implementation, calculates 4 scores (compliance, completeness, quality, implementation)…majiayu000logic-reviewFind logic bugs in a single file or function via semi-formal execution tracing (Premises → Trace → Divergence → Trigger →…sickn33lokalise-debug-bundleCollect Lokalise debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing…jeremylongshorelokalise-sdk-patternsApply production-ready Lokalise SDK patterns for TypeScript and Node.js. Use when implementing Lokalise integrations, refactoring…jeremylongshorewriteslongbridge-multifactorMulti-factor cross-sectional stock-selection strategy via Longbridge Securities — scores stocks in an index or candidate pool on…majiayu000longbridge-post-investmentPost-investment monitoring via Longbridge Securities — tracks portfolio holdings vs plan on a quarterly / monthly basis, extracts…majiayu000love2d-coreStructure and debug a LÖVE (Love2D) game in Lua: the love.load/update/draw loop, delta-time movement, input, and screen states.…gamedev-skillsLQF_Machine_Learning_Expert_GuideLQF Machine Learning Expert Guide - Auto-activating skill for ML/Statistical Modeling with Critical Discussion Mode. Triggers on…majiayu000writesM365 Declarative Agent Debugging SkillDebug non-functional M365 Copilot declarative agents.majiayu000
← Prev20 / 62Next →
How the catalog works
What is an agent skill?

A folder with a SKILL.md inside — instructions, and often scripts and assets, that an AI agent loads when the task matches. Claude Code, Codex, Cursor and Copilot all read the same format, so one skill usually works across them.

Where does this catalog come from?

We read 660 source repositories straight from their file trees rather than from submitted listings — what you see is what is actually published. 98 repositories were rejected because they advertise skills but contain none: link lists, not folders.

Why is there no install counter?

Because install counts live in the registry that serves `npx skills add`, and that is not ours — publishing a number we cannot verify would be worse than showing none. Instead we show where a skill comes from and whether attention around its source is actually growing, measured from our own weekly snapshots.

Do you deduplicate?

Yes, and it matters more than expected. Aggregator repositories republish the same skill in several places — one source carried 6,317 SKILL.md files for 2,001 actual skills. We collapse by folder name and keep the canonical copy, so the catalog counts things, not copies.

Keep going