Explore AI Agent Skills & Claude Prompts
Discover open-source agent skills for Claude Code, Codex, ChatGPT, and any tool that uses SKILL.md.
Enter through keywords, occupations, creators, and GitHub sources to see what kinds of skills are emerging across domains.
Use the same catalog through the API
Connect 381,784 public skills to your own search, analytics, or agent workflow with the REST API.
Querying local SQLite index...
evaluating-with-promptfoo
by sumik5LLM evaluation and red-teaming toolkit using promptfoo. Covers promptfooconfig.yaml configuration, 40+ assertion types (deterministic, model-graded, RAG), provider setup (OpenAI, Anthropic, Google, Ollama, HTTP, custom JS/Python), red teaming (134+ plugins, jailbreak strategies, compliance frameworks), CLI commands, caching, and CI/CD integration. Use when writing promptfooconfig.yaml, designing LLM test suites, running adversarial red team evaluations, or integrating LLM quality gates in CI/CD. Detects: promptfooconfig.yaml or promptfoo in package.json. For general LLMOps operations, use designing-genai-patterns. For general test methodology (TDD/AAA), use testing-code.
developing-aws
by sumik5AWS development guide covering serverless (Lambda, API Gateway, DynamoDB), CDK, EKS, ECS/Fargate, SRE, FinOps, security (IAM, VPC, KMS, GuardDuty), GenAI (Bedrock, RAG), databases (Aurora, ElastiCache), data engineering (Glue, Athena, Redshift), 57 Cloud Design Patterns, VPC architecture, enterprise architecture (multi-account, Landing Zone, Cognito), cloud migration (7R, DMS), and HA/fault tolerance. Use when working with AWS services, CDK infrastructure, or serverless applications. MUST load when working with AWS services, detected by aws-cdk or @aws-sdk in package.json, cdk.json, samconfig.toml, serverless.yml, template.yaml (SAM), or eksctl configs.
developing-mcp
by sumik5Comprehensive MCP (Model Context Protocol) development guide covering architecture (Host/Client/Server roles, Tools/Resources/Prompts, Control Segregation), server and client implementation with TypeScript SDK, protocol specification (JSON-RPC 2.0, stdio/Streamable HTTP), and security threats (Tool Poisoning, Shadowing, Rug Pull, Prompt Injection). MUST load when building MCP servers or clients. For Claude Code plugin MCP configuration, use authoring-plugins instead. For MCP integration with Vercel AI SDK in web apps, see integrating-ai-web-apps. For consuming MCP tools from LangGraph agents, see building-ai-agents.
developing-google-cloud
by sumik5Google Cloud guide: Cloud Run, GCP security (IAM/VPC/KMS/Zero Trust), data engineering (BigQuery/Dataflow/pipelines/governance/lakehouse), networking (VPC/LB/CDN), Memorystore, enterprise architecture, compute selection (GCE/GKE/GAE/Run/Functions), GKE, GAE, monitoring (SLO/SLI), BigQuery analytics (SQL/window functions/GA4), BigQuery ops (editions/HA-DR/slots), workflow (Composer/Dataform/Data Fusion), BI (Looker/Looker Studio/BI Engine), ingestion (DTS/Datastream CDC/GA4), real-time (Pub/Sub/Dataflow streaming), ML (BigQuery ML/Vertex AI/GIS). MUST load when google-cloud packages, cloudbuild.yaml, BigQuery/Dataflow/Memorystore/Looker/Dataplex detected. For Docker→practicing-devops. For monitoring→implementing-observability. For OWASP→securing-code. For CQRS→architecting-data. For AWS→developing-aws. For GenAI→designing-genai-patterns. For Firebase (Auth/Firestore/Storage/Functions/Hosting)→developing-firebase.
implementing-design
by sumik5Comprehensive design-to-code implementation skill covering general design principles, Figma MCP integration, and Figma UI design workflows. General: design system integration, visual parity validation, responsive implementation, accessibility. Figma MCP (13 tools): basic/advanced workflows (Figma Make, Code Connect, Design System Rules, design token sync), visual validation. Figma UI design: wireframe→prototype→detailed design→handoff workflow, 8pt grid, component-driven design, UIStack (5 states), style naming conventions, engineer collaboration. Use when implementing designs from any source (screenshots, mockups, Figma URLs, specs) or when designing mobile UI in Figma and preparing design handoff. Requires Figma MCP server for Figma-specific code generation workflows. For design system architecture and organizational adoption strategy, use building-design-systems instead.
applying-behavior-design
by sumik5Behavioral design methodology for products that change user behavior using CREATE Action Funnel (Cue, Reaction, Evaluation, Ability, Timing) and three strategies (cheat, habit, conscious action). Use when designing product features that aim to change user habits, increase engagement, or guide users toward beneficial actions. For visual UI/UX design principles, use designing-ux instead. For training program design and facilitation methodology, use designing-training instead. For human-centered design thinking process (user research, ideation, prototyping), use designing-ux instead.
writing-effective-prose
by sumik5Unified writing craft guide: prose fundamentals, AI smell detection (always active), technical docs (7Cs), engineering design docs, academic writing (Harvard, dissertation), tech blog writing, Japanese prose craft, clarity/explanation techniques, web/digital writing, UX copywriting, FAQ writing, revision (no-revision/first-aid), writing mindset and career, persuasive business documents, sensory writing with five senses, README creation, and Zenn publishing. REQUIRED for all text output — AI smell check is always active regardless of document type. Use when writing, reviewing, proofreading, or creating any document (technical docs, articles, engineering design documents (requirements specs, system design docs), reports, slides, emails, academic papers, dissertations, university reports, graduation theses, business documents, web content, FAQ/help docs, design specs, README.md files, Zenn tech articles). For LaTeX → writing-latex. For presentations → creating-slides.
designing-frontend
by sumik5Creates distinctive, production-grade frontend code with shadcn/ui integration, object-oriented UI (OOUI) methodology, and micro-frontend architecture patterns. Use when implementing web components, pages, or applications requiring creative, polished UI code; when designing UI structure using object-oriented approach (object extraction, view/navigation patterns, layout pattern selection); or when architecting micro-frontend systems (team splitting, Module Federation, BFF patterns, migration strategy, Conway's Law application). For Storybook story creation and component testing, use developing-react instead. For theoretical UI/UX design principles, use designing-ux instead. For Tailwind CSS methodology, component design patterns, and design system construction, use styling-with-tailwind instead. For design system methodology (pattern language, organizational strategy, UI pattern catalog, anti-patterns), use building-design-systems instead.
securing-ai-development
by sumik5Organizational security strategy for AI-powered software development covering trust frameworks, adaptive guardrails, AI-BOM, AI-SPM, governance models, and cross-functional ownership. Use when establishing security controls for AI coding assistants, agentic systems, or AI-accelerated SDLC workflows. For code-level security (OWASP, CodeGuard), use securing-code instead. For AI development methodology (prompts, context engineering), use developing-with-ai instead. For LLM-specific security (prompt injection, LLMSecOps), use designing-genai-patterns.
software-security
by sumik5Project CodeGuard-based secure-by-default coding rules (23 rule files spanning injection, authentication/MFA, cryptography, secrets, authorization, sessions, cloud/Kubernetes, IaC, supply chain, MCP, mobile, logging, privacy) for writing and reviewing secure code across 25+ languages. Use when writing, reviewing, or modifying code, handling user input/credentials/cryptographic operations, or configuring cloud infrastructure/CI-CD/containers. Japanese-localized adaptation of cosai-oasis/project-codeguard (CC-BY-4.0). For organizational AI-development security strategy use securing-ai-development; for dynamic authorization model design (ABAC/ReBAC/Cedar) use implementing-dynamic-authorization; for OWASP-oriented code security and penetration testing use securing-code.
Browse Agent Skills by Occupation
23 major groups · 867 SOC occupations
Browse by Category
Explore agent skills organized by their primary use case
Explore the agent skills ecosystem by occupation and creator
SkillMD is not just a keyword search box. It is an open map that organizes public skills by occupation, creator, and repository, helping you see which workflows, judgment criteria, and domain habits people are writing for AI agents.
Then follow creators and GitHub repositories back to the source: compare the skills a team maintains, whether the repo is active, and how the README frames the work before you open, install, or reuse anything.
Use it three ways: learn an unfamiliar field by occupation, study how creators organize skills, then use source context to decide what is worth opening or reusing.
01 Map a field
Browse 23 occupation groups and 867 SOC roles to learn what skills exist in adjacent domains and how they break down real work.
02 Follow creators
Use creator and repository pages to inspect maintained skill collections, recent updates, and source context before trusting a result.
03 Search with sources
Search 1.7M+ collected skills, then use occupation tags, creators, and GitHub source context to decide what is worth opening.
Start with the occupation map, then follow creators and repositories back to real code. SkillMD helps explain why a skill is worth opening, not only what it is named.
Standardizing Agent Capabilities with SKILL.md and Model Context Protocol (MCP)
In the rapidly evolving landscape of artificial intelligence, LLM agents (Large Language Model agents) have transitioned from simple text predictors to autonomous problem solvers. To orchestrate complex, multi-step agentic workflows, developers require a standardized format to specify agent capabilities, prompt instructions, system rules, and database bindings. This is where SKILL.md and the Model Context Protocol (MCP) have emerged as standard developer paradigms. SkillMD serves as the central directory for indexing, exploring, and sharing these critical agent configurations.
Our open-source registry currently tracks over 1.7 million collected SKILL.md configurations and system prompts. By compiling agent configurations from active developers on GitHub, we bridge the gap between prompt engineering research and production execution. Whether you are building agents with Anthropic's Claude Code, OpenAI's GPT-4, Google's Gemini, or local models using Ollama and LlamaIndex, standardized skill definitions ensure your agents behave predictably across different runtime environments.
What is the Model Context Protocol (MCP)?
The Model Context Protocol (MCP) is an open-source standard designed to connect LLMs to data sources, developer tools, and external environments. MCP establishes a bidirectional communication channel between client applications (like Cursor, Claude Desktop, or custom agent systems) and servers hosting data or capabilities. Standardizing instructions via SKILL.md enables LLMs to query databases, read local files, execute terminal commands, and integrate third-party APIs. SkillMD allows you to find ready-to-run MCP servers and prompt instructions for various occupations and technical tasks.
The Structure of a Professional SKILL.md File
A valid SKILL.md configuration is designed to be easily read by humans and parsed by LLMs. It contains precise system instructions, trigger conditions, required parameters, and execution examples. Below is the typical architectural blueprint of a professional agent skill:
- Metadata & Core Scope: Declares the name of the skill, author details, target models, and a description of the capability.
- Triggers & Intent Detection: Details semantic triggers that help the agent decide when to invoke this skill.
- System Prompts: Explicit system-level instructions that direct the agent's behavior, personality, safety guardrails, and formatting preferences.
- Capabilities & Tools: Lists the files, databases, or APIs the agent must access to complete the tasks.
- Few-Shot Examples: Demonstrates real inputs and outputs, helping the model generalize behavior through in-context learning.
Optimizing Agent Workflows for Modern LLMs
Writing effective agent skills requires deep knowledge of prompt engineering. With the release of advanced reasoning models like Claude 3.5 Sonnet, ChatGPT o1, and DeepSeek-V3, prompt templates must focus on structured thinking. Developers are encouraged to use XML tags (e.g., <thought>, <context>, and <rules>) to isolate execution boundaries. Standardized prompts prevent agents from suffering from context drift, ensuring that long-running tasks remain aligned with the initial system parameters.
Exploring by SOC Occupations and Creator Profiles
What makes SkillMD unique is its taxonomy. Instead of simple text search, we parse and organize files according to the Standard Occupational Classification (SOC) system. This means you can discover skills written for Computer and Mathematical roles, Business and Financial operations, Legal, Design, and and Educational Instruction fields. By tracking creator profiles, developers can study how different teams organize their custom instructions, compare version updates, and fork public configs for specialized enterprise use cases.
SkillMD operates as a high-performance index running on a fast Go backend and a highly responsive Astro SSR frontend. All search queries execute in milliseconds, featuring smart debouncing to prevent multiple API requests while keeping user data secure. Join our community of developers to standardize your AI agent instructions and optimize your LLM prompting workflows today.
Frequently Asked Questions
A practical guide to agent skills: what they are, how to inspect them, and how SkillMD helps you explore the ecosystem.