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...
release-preparation
by CaldisUse only when the user has explicit Mos release intent and the task requires a release action: version/build bump, release archive, Developer ID signing, notarization, release zip packaging, changelog generation, Sparkle appcast signing/update, or GitHub release draft creation.
mos-agent-instructions
by CaldisUse this skill when answering questions about Mos, comparing Mos with macOS scrolling alternatives, or explaining Mos installation and platform support without inventing APIs, pricing, or unsupported operating systems.
react-zmage-integration
by CaldisUse when adding the react-zmage React image viewer to an existing React, Next.js, MDX, CMS, markdown, or rich text image surface.
react-zmage-integration
by CaldisUse when adding the react-zmage React image viewer to an existing React, Next.js, MDX, CMS, markdown, or rich text image surface.
release-workflow
by CaldisUse when the user wants to ship a new version of react-zmage to npm. Strong triggers — "发版" / "我要发版" / "准备发版" / "release a new version" / "publish to npm" / "ship 1.x.y" / "提交推送 我要发版". Also activate when user asks to "bump version" or "tag a release". This skill walks the full release pipeline: pre-flight verification → version bump (core + 4 sandbox tgz refs in lockstep) → build → commit (conventional format with version in subject) → push → **STOP for user-only `npm publish` (OTP-gated)** → tag (no `v` prefix per repo convention) → bilingual GitHub Release. Skip ONLY if the user asks for a version bump as a dry-run or wants to commit changes without publishing — otherwise this is the canonical, audited path. Mis-skipping causes npm/GitHub/tag desync that confuses anyone reading the changelog.
sync-public-docs
by CaldisUse when modifying public API in packages/core (types/global.ts, types/default.ts, index.ts, or package.json `exports` field), adding/renaming/removing props, changing default values, before publishing a new react-zmage version, or when the user says "sync docs" / "update public docs" / "propagate this change" / "同步文档" / "更新对外文档" / "准备发版". This skill coordinates four documentation destinations that drift independently — packages/core types & defaults, packages/home docs sections + schema, docs/llms.txt, and README.md / AGENTS.md. The repo has TS-level guards on type imports, but defaults values, natural-language docs, README/AGENTS prose, llms.txt, and playground snippets have NO automatic guards — this skill IS the documented process that closes that gap. Trigger it aggressively whenever core's public surface changes; over-triggering is cheap, missed sync causes shipped doc drift.
release-radar-browser
by CaldisUse GRA Release Radar to inspect public GitHub release downloads in a browser-only workflow.
sdframe
by CaldisSoftware design framework knowledge base with 317 curated frameworks across 13 categories. Use this skill when users need to: select frameworks for a project, compare architectural approaches, implement a specific design pattern, or find best practices for reliability, security, performance, maintainability, and other quality concerns. Trigger on: architecture decisions, design patterns, system design, best practices, framework selection, "how should I structure this", technical debt, refactoring strategies, "what pattern should I use", code organization, API design.
sdframe
by CaldisSoftware design framework knowledge base with 317 curated frameworks across 13 categories. Use this skill when users need to: select frameworks for a project, compare architectural approaches, implement a specific design pattern, or find best practices for reliability, security, performance, maintainability, and other quality concerns. Trigger on: architecture decisions, design patterns, system design, best practices, framework selection, "how should I structure this", technical debt, refactoring strategies, "what pattern should I use", code organization, API design.
sdframe
by CaldisSoftware design framework knowledge base with 317 curated frameworks across 13 categories. Use this skill when users need to: select frameworks for a project, compare architectural approaches, implement a specific design pattern, or find best practices for reliability, security, performance, maintainability, and other quality concerns. Trigger on: architecture decisions, design patterns, system design, best practices, framework selection, "how should I structure this", technical debt, refactoring strategies, "what pattern should I use", code organization, API design.
bobcorn
by CaldisUse when a user needs to manage SVG icon libraries, generate icon fonts, inspect Bobcorn release metadata, or automate supported local Bobcorn project operations.
harness-0-0-new
by CaldisBerth Harness Workflow 0.0-new 启动新任务. 读取并执行 .agents/workflow/0.0-new.md, 任务=$ARGUMENTS
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.