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...
sourcesage-cli
by Sunwood-ai-labsGenerate AI-friendly repository documentation with the SourceSage CLI. Use when Codex needs to run `sage` or `sourcesage` to create `.SourceSageAssets/Repository_summary.md`, analyze the current repository or another local repository, switch the output language between English and Japanese, use `--lite` to keep the summary small, change the output directory, or optionally create a deprecated tag-diff release report with `--diff`.
draw-io
by Sunwood-ai-labsCreate, edit, export, and review draw.io diagrams. Use for native .drawio XML generation, PNG/SVG/PDF export, SVG overlap, border-overlap, label-intrusion, label-rect, short-terminal, text-contrast, text-emphasis, and text-overflow linting, layout adjustment, and AWS icon usage.
logged-in-google-chrome
by Sunwood-ai-labsLaunch and reuse a Google Chrome session that is logged into a Google account by using a dedicated user-data-dir and attaching Playwright over CDP after manual login. Use when Codex needs to work with Gmail, Google Account pages, or other Google web apps without triggering the "browser or app may not be secure" login block from a Playwright-launched browser.
m5stack-arduino-cli
by Sunwood-ai-labsSet up, diagnose, flash, and support development for M5Stack boards with Arduino CLI on Windows. Use when Codex needs to install ESP32 board support, detect the correct COM port, explain why `arduino-cli board list` shows `Unknown`, attach a board/FQBN to a sketch, compile or upload to M5Stack devices such as M5Core2, prepare supporting libraries, add or update sample sketches, or troubleshoot CH9102/CP210x USB-serial behavior.
codex-mobile-remote-control-vm
by Sunwood-ai-labsSet up, repair, or verify an Ubuntu/Linux desktop VM that lets the ChatGPT/Codex mobile app remotely control Codex Desktop. Use when Codex needs to create a Proxmox or SSH-accessible Ubuntu VM, install a desktop session, run the Linux Codex Desktop port, configure remote_connections/remote_control, pair or troubleshoot mobile remote control, handle disappearing Connections rows, or document a third-party handoff.
ltx23-comfyui-ti2v-audio
by Sunwood-ai-labsUse when you need to run, configure, explain, or adapt Isi-dev style LTX 2.3 ComfyUI workflows for text-to-video or image-to-video with audio, including remote GPU machine bootstrap, App JSON controls, prompt handling, lip-sync audio flow, and model or custom-node setup.
midnight-memory
by Sunwood-ai-labsManage intro/main/outro subtitle sectioning, gap extraction, manifest sync, and Remotion lyric motion outputs for `midnight-memory`, while keeping viewer timeline metadata aligned.
pixal3d-image-to-3d
by Sunwood-ai-labsGenerate 3D GLB models from input images with the Pixal3D Docker workflow in this repository. Use when Codex needs to convert PNG/JPG/WebP images into Pixal3D 3D assets, run the Gradio Pixal3D app, inspect or serve generated GLB outputs, batch-convert solarpunk town assets, tune FOV/background-removal settings, or troubleshoot Docker/NVIDIA/Hugging Face cache issues for Pixal3D image-to-3D generation.
drawio-diagram-hygiene
by Sunwood-ai-labsImprove diagrams.net and draw.io diagrams by reducing overlap between connectors, boxes, and text, and by applying consistent routing, spacing, and label placement. Use when Codex edits `.drawio` or `mxfile` diagrams, reviews unreadable layouts, or needs to reroute connectors and clean labels without changing diagram meaning.
cities-skylines1-agent-skill
by Sunwood-ai-labsOperate Cities: Skylines 1 through the Skylines Agent Bridge mod and localhost API. Use when Codex needs to build, inspect, repair, resume, save, or continue a CS1 city using focused API calls rather than screenshot recognition, including road connectivity, service infrastructure, zoning, facilities, problem icons, and save verification.
remote-agent-onboarding
by Sunwood-ai-labsCreate, onboard, repair, and verify a remote-agent employee Linux VM, from VM provisioning through SSH, Linux GUI, Codex Desktop, Chrome, Browser/IAB, mobile remote control, Automations, and proof-surface checks. Use when the user asks to create a remote agent workstation, prepare or repair Codex Desktop/Chrome/Browser access, or document the end-to-end remote agent onboarding workflow.
google-calendar-api-direct
by Sunwood-ai-labsUse when Codex needs to call the Google Calendar API directly instead of the built-in connector, especially to create secondary calendars, set calendar colors, list calendars, create events on a specific calendar, or verify Calendar API writes with local OAuth credentials.
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.