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...
neuron-analyze-api
by H2OSLabsAnalyze arbitrary-format API lists and extract structured understanding for neuron-ui page generation. Use when users provide API documentation in any format (Swagger/OpenAPI, Postman collections, cURL commands, text descriptions, tables, screenshots) and need it analyzed before page generation. Triggers on requests like "analyze this API", "understand these endpoints", "what pages can I build from this API", or when preparing API context for the neuron-generate-page skill.
elfiee-be-dev
by H2OSLabsElfiee 后端开发专家 skill。适用于 Rust/Tauri 后端开发任务，包括：(1) Extension/Capability 开发 - 添加新区块类型和能力；(2) Tauri Command 开发 - 添加前后端接口；(3) Engine 核心修改 - 事件溯源和 Actor 模型。遵循事件溯源架构、CBAC 权限模型和 tauri-specta 类型生成规范。触发示例："添加新的块类型"、"实现一个 capability"、"添加后端接口"。
oneauth-oauth2
by H2OSLabsIntegrate client applications with OneAuth for OAuth2/OIDC authentication. Use when implementing user login/logout, token management, or identity integration via OneAuth (based on Ory Kratos + Ory Hydra). Covers Web OAuth2 Authorization Code + PKCE flow, token refresh/verify/revoke, UI customization, and multi-platform support (Web, mini-program, CLI). Trigger when user mentions OneAuth login, OAuth2 integration, SSO, or authentication with OneAuth.
elfiee-be-refactor
by H2OSLabsElfiee 后端重构 skill。将 Elfiee 从全能桌面编辑器收束为编排型 Agent， 通过删除 I/O 代码、合并 Extension、替换通讯层，实现后端能力的完整封装。 使用场景：(1) 执行重构步骤（删除/合并/新增代码）； (2) 验证重构结果（API 覆盖度、无用代码扫描、依赖清理）； (3) 处理产品 user-story testcase 到 API 的映射验证。 触发示例："执行重构步骤 X"、"验证 API 覆盖"、"清理无用代码"、 "检查 user-story 是否可通过 API 组合实现"。
skill-creator
by H2OSLabsInteractive guide for creating effective skills through structured Q&A. Use when users want to create a new skill or update an existing skill. This skill will ask targeted questions to gather requirements, identify needed materials (scripts, references, assets), and guide users through the complete skill creation process.
neuron-validate-schema
by H2OSLabsValidate neuron-ui Page Schema JSON against format, composition, binding, and token rules. Use when checking if a generated or manually-edited Page Schema is valid before loading into the page builder. Triggers on requests like "validate this page schema", "check my schema", "is this Page Schema correct", or automatically after neuron-generate-page produces output.
setup-lsp
by H2OSLabsHelp users configure and verify LSP (Language Server Protocol) setup for Python and JavaScript/TypeScript in Claude Code. This skill should be used when users ask about LSP configuration, need to check if LSP servers are properly installed, encounter LSP-related issues, or want to verify LSP functionality before starting development work.
domain-modeler
by H2OSLabsExtract domain model from user journeys/requirements. Reads user stories or journey docs, identifies business entities, relationships, attributes, and constraints, then produces structured data model documentation. Use when starting a new project, onboarding a new domain, or when user-journeys change significantly. Triggers: 'domain modeling', 'extract entities', 'data model from requirements', 'business abstraction', 'design data model', or when user-journeys.md is created/modified.
frontend-prototype-builder
by H2OSLabsBuild deployable frontend prototypes from Figma designs and test cases. Complete workflow: ensure services → validate data → generate pages → test with browser. Use when: (1) "构建前端原型" or "build frontend prototype" (2) "从 Figma 生成页面" or "generate pages from Figma" (3) "修复前端 404 问题" or "debug frontend 404" (4) "端到端测试前端" or "E2E test frontend" (5) Need to create testable UI for PM/designers Inputs: specs/design/pages.yaml, specs/design/figma/, specs/testcases/*.md Outputs: Working frontend pages in frontend/app/ and frontend/components/pages/
openapi-to-components
by H2OSLabsConvert Synnovator OpenAPI spec into fully integrated Next.js frontend components. Reads .synnovator/openapi.yaml and frontend/components/pages/*.tsx, then generates API client (lib/api-client.ts), TypeScript types (lib/types.ts), server-side data fetching functions (lib/api/*.ts), and updates existing page components to replace hardcoded mock data with real API calls using Next.js App Router Server Components. Use when: (1) Need to wire frontend components to backend API endpoints (2) Want to replace mock/hardcoded data in page components with real API fetching (3) Adding a new page component that needs API integration (4) Regenerating API types after OpenAPI spec changes
schema-to-openapi
by H2OSLabsConvert Synnovator data schema to OpenAPI 3.0 specification. Use when: (1) Need to generate REST API spec from Synnovator's content types and relations (2) Preparing input for api-builder skill to scaffold backend code (3) Want standardized, RESTful API design from the Synnovator data model Triggers: "generate openapi", "create api spec", "convert schema to openapi", "prepare for api-builder", "generate REST API from synnovator"
seed-designer
by H2OSLabsDerive seed data requirements from test cases. Reads specs/testcases/*.md, extracts implicit data preconditions from each test scenario, deduplicates and organizes by entity type, then produces a seed data requirements document and annotated seed script. Use when test cases are created/updated and seed data needs to stay in sync. Triggers: 'design seed data', 'seed data from testcases', 'update seed requirements', 'what data do tests need', or when specs/testcases/ files change.
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.