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...
photos
by n0rvyn搜索和查看 Apple Photos 照片库。当用户需要查找照片、浏览相册、获取照片信息时使用。Use when the user needs to search photos, browse albums, or get photo information. Keywords: 照片, Photos, 相册, 图片搜索, 相片.
reminders
by n0rvyn查询、创建、完成、删除 Apple Reminders.app 提醒事项。当用户需要查看待办提醒、创建提醒、标记完成、搜索提醒事项时使用。Use for Apple Reminders.app operations. Keywords: 提醒事项, Reminders, 提醒, 待办, remind, reminder.
contacts
by n0rvyn搜索和查看 macOS 通讯录中的联系人信息。当用户需要查找联系人电话、邮箱、地址等信息时使用。Use when the user needs to find contact phone numbers, emails, or addresses. Keywords: 通讯录, Contacts, 联系人, 电话, 邮箱.
review-execution
by n0rvynUse when the user says 'review execution', 'parallel review', 'deep review', 'review my code', 'review after coding', 'execution review', '审查执行', '并行 review', '写完 review 一下', '代码 review 一下', '深度审查', '执行后审查', or wants a fresh-context multi-lens review of uncommitted changes BEFORE commit. Dispatches 4 parallel reviewer agents (correctness, test-coverage, breaking-changes, root-cause-depth) and consolidates findings into must-fix / nice-to-have. Standalone — does NOT require a plan or dev-guide. Not when: a plan exists and you want plan-vs-code audit — use implementation-reviewer. Not when: pre-commit semantic classification only — use review-before-commit. Not when project is Apple-only and you want only ASC pre-submit review — use /asc-submit-preview.
test-changes
by n0rvynUse when the user says 'test changes', 'run tests', 'test the build', or after execute-plan completes in a run-phase. Runs the project's build/test/lint suite and returns a filtered report with errors only. Branches on project type: Apple projects (.xcodeproj/.xcworkspace) run xcodebuild from the main session with diff-scoped -only-testing; other projects dispatch the dev-workflow:test-runner sub-agent.
write-dev-guide
by n0rvynUse when starting a new project's development after design is approved, OR when scoping a multi-unit refactor/migration that spans multiple independent components (e.g., 'refactor 6 cards across 4 tabs', 'migrate auth across 4 layers'), or the user says 'write dev guide', 'break down this project into phases', or '写开发指南'. Creates a phased development guide that serves as the cornerstone document for all subsequent /write-plan and /run-phase cycles. Each phase represents one conceptual unit (one component, one layer, one migration step) — phase size is determined by review boundary, not workload. Produces: docs/04-dev-guide/dev-guide.md with a phased task tree, dependency graph, and acceptance criteria per phase. Not for single-feature plans (use write-plan) or design exploration (use brainstorm).
omnifocus
by n0rvyn查询、创建、完成 OmniFocus 4 任务和项目。仅当用户明确提及 OmniFocus 或 OmniFocus 特有概念（项目、透视、上下文）时使用。Use only when the user explicitly mentions OmniFocus or OmniFocus-specific concepts (projects, perspectives, contexts). Keywords: OmniFocus, 项目, inbox, flagged, perspectives.
readback
by n0rvynUse when the user says '/readback', 'readback', 'echo my intent', 'restate my ask', 'play it back', '复述', '复述一下', '回读'. Triggers a manual 3-paragraph plain-language echo of the user's current intent via the intent-echoer agent — before substantial code/plan work, or to recover alignment after drift. '/readback status' shows current readback state. Not when: inside /brainstorm Step 2 (its Expectation Recap handles alignment via '对齐了'). Not when: a plan file already exists and user wants it validated (use /verify-plan). Not when: post-code review (use /review-execution). Not when: user wants a code or doc summary (use Read/Grep directly). Not when: user wants progress summary for next session (use /handoff). Not when: user wants to extract decisions from past discussion (use /crystallize or /distill-discussion).
demand-check
by n0rvynUse for a quick demand reality check on a product idea or project. Runs only the demand validation dimension and Elevator Pitch test. Fast first-pass filter before committing to build.
notion-page-sync
by n0rvynUse this skill to sync local markdown files or a directory to Notion pages under a configured parent page. Trigger phrases include "sync to Notion", "push docs to Notion", "同步到 Notion", "/notion-page-sync <path>". Project-level config lives in .claude/notion-sync.local.md.
plugin-master
by n0rvynUse when the user says 'plugin-master', 'orchestrate plugin creation', 'manage plugin lifecycle', 'review plugin', 'audit plugin', 'iterate skill quality', 'package plugin for marketplace', or wants to orchestrate the full lifecycle (create / review / iterate / package / insights) of Claude Code plugins. (also: insights based on real usage to propose plugin improvements) Not when: user wants to create a single atomic component — use `/plugin-dev:skill-development` / `agent-development` / `hook-development` / `command-development` / `plugin-structure` directly. plugin-master is the orchestrator; plugin-dev provides the atomic builders. Single entry /plugin-master with 5 routes: - create: brainstorm → design → scaffold (plugin-dev) → eval baseline (skill-creator) → review → iterate - review: 9-dimension audit from AI executor perspective + cross-plugin trigger conflict detection - iterate: fix → re-eval (skill-creator) → compare baseline → verify - package: full plugin or single component into target project -
project-kickoff
by n0rvynManual /project-kickoff invocation only (auto-routing disabled). Runs the project kickoff flow to clarify requirements, converge scope, and produce execution recommendations. Use when starting a new iOS/macOS project.
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.