Agent skills

Other 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
21,420 found
2,9292,976 · page 62 / 447
datamolPythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including…majiayu000writesdb-musik-app-beiDatenbankrecht für Musik-, Film- und Bildarchive: §§ 87a-87e UrhG für Mediendatenbanken, Schichtenschutz…majiayu000dbt-project-analyzerAnalyzes dbt projects for best practices, performance, maintainability, and generates actionable recommendations for improvement.a5c-aiwritesddd-context-mappingMap relationships between bounded contexts and define integration contracts using DDD context mapping patterns.sickn33ddd-tactical-patternsApply DDD tactical patterns in code using entities, value objects, aggregates, repositories, and domain events with explicit…sickn33bio-de-resultsExtract, filter, annotate, and export differential expression results from DESeq2 or edgeR. Use for identifying significant…majiayu000de2-factorizationApply DE2 Factorization to separate multiplicative components to understand relative contribution of each factor.majiayu000dead-code-eliminatorIdentify and safely remove dead, unused, and unreachable code from codebasesa5c-aiwritesdeb-package-builderBuild Debian packages with proper control files, dependencies, and maintainer scriptsa5c-aiwritesdebankQuery DeBank OpenAPI for wallet portfolios, token holdings, DeFi positions, and transaction history.majiayu000debugging-patternsRoot cause analysis frameworks including log-first investigation, git bisect correlation, and pattern-based diagnosis with…a5c-aiwritesdebugging-strategiesTransform debugging from frustrating guesswork into systematic problem-solving with proven strategies, powerful tools, and…sickn33decidePresent viable paths, detect decision type, and guide commitment with a user checkpoint. Use after synthesize to move from…majiayu000decision-analysisDecision modeling using decision tables, weighted scoring matrices, and decision trees. Structures complex decisions with clear…majiayu000decision-auditorAudits decisions for cognitive biases, runs premortems on plans, and reframes choices to reveal hidden assumptions. Use when…majiayu000decision-extractorScan recent notes for decision language and offer to update project Decision Logsmajiayu000writesdecision-frameworkThinking frameworks for decisions and problem analysis. Use when evaluating options, root causes, or prioritizing.majiayu000decision-frameworkThinking frameworks for decisions and problem analysis. Use when evaluating options, root causes, or prioritizing.majiayu000decision-frameworksUse when choosing between mutually exclusive strategic paths or building a repeatable decision process—constructs Decision…majiayu000Decision FrameworksDecision-making methodologies, scoring frameworks, and planning strategies for Group 2 agents in four-tier architecturemajiayu000decision-frameworksStructured decision-making patterns for common engineering choices — library selection, architecture, build vs buy…majiayu000decision-makingStructured approaches to decisions under uncertainty and complexity. Covers expected value, decision trees, multi-criteria…majiayu000de3-decompose-problemApply DE3 decomposition to partition a problem into modular subproblems.majiayu000decontextualizeCourse-correct when artifacts overfit to conversation context. Invoke when examples, names, or language are too specific to…majiayu000deep-analysisInvestigate a game from raw logs, trace bugs to source code, and file detailed issues. Use for deeper debugging than export-only…majiayu000deep-analysisExecute high-density analysis on complex ideas/tasks. Move from 'Vague' to 'Verified' by producing: constraints -> core modules…majiayu000deep-dive2-stage pipeline: trace (causal investigation) -> deep-interview (requirements crystallization) with 3-point injectionmajiayu000deep-executorDeep executor mode for complex goal-oriented tasksmajiayu000deep-executorDeep executor mode for complex goal-oriented tasksmajiayu000deep-learningBuild and train deep neural networks including CNNs, RNNs, Transformers, and advanced architectures. Use for image…majiayu000deep-learningBuild and train neural networks with PyTorch - MLPs, CNNs, and training best practicesmajiayu000deep-reflectAnalyzes development sessions to extract patterns, preferences, and learnings. Use after significant work sessions to capture…majiayu000writesDeep ResearcherInvestiga documentación oficial y valida soluciones en internet antes de implementar.majiayu000Deep ResearchComprehensive web research with synthesis and actionable insightsmajiayu000deep-researchUse when researching complex topics, evaluating technologies, investigating domains, or answering multi-faceted questions…majiayu000deep-researchConduct enterprise-grade research with multi-source synthesis, citation tracking, and verification. Use when user needs…majiayu000deep-researchPesquisa aprofundada com metodologia estruturadamajiayu000deep-researchDeep multi-round web research with query decomposition, iterative refinement, source triangulation, and structured synthesis. Use…majiayu000deep-researchRun deep research on any topic using parallel AI agentsmajiayu000deep_research**深度网络研究**。不仅搜索链接,还会自动访问结果页面,阅读正文,并生成深度整合的综合报告。majiayu000deep-researchDeep research and discovery before building something new. Explores local projects for reusable code, researches competitors…majiayu000deep-researchDeep research on technical topics using EXA tools with intelligent two-tier caching. Use when user asks to research a topic…majiayu000deep-researchConduct enterprise-grade research with multi-source synthesis, citation tracking, and verification. Use when user needs…majiayu000deep-researchUse when user requests research requiring multiple sources, comprehensive analysis, or synthesis across topics - technical…majiayu000deep-researchMulti-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with…majiayu000deep-researcherPerforms comprehensive, multi-layered research on any topic with structured analysis and synthesis of information from multiple…majiayu000deep-search다중 전략 코드베이스 심층 탐색 워크플로우. Grep, SemanticSearch, Glob를 병렬로 실행하여 심볼, 패턴, 의존성을 종합적으로 분석. Use when performing deep codebase analysis…majiayu000deepagents-cli使用 Deep Agents CLI - 终端界面、持久化内存(AGENTS.md)、项目约定、技能目录和 CLI 命令。majiayu000
← Prev62 / 447Next →
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