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...
deepdive
by nemockProduce a long-form (~20+ min, 16:9) operator-narrated deep-dive video — an orchestrated film of many small `explainer` segments (cold-open → Act I → sponsor → Act II → sponsor → Act III → CTA), assembled RAM-safely into one master with chapters + captions. Use when the user wants a "deep dive", "long-form explainer", "YouTube tutorial video", "20-minute video", or runs "/deepdive <topic>". Brand-parameterized (FWF-first). You author the plan + per-segment script/deck and drive the record/review loop; a pure-Python pipeline does narrate→align→render →mux per segment and conform→concat→validate for the master. Generation only — it writes a labeled program dir + crash-safe manifest; it NEVER posts to social platforms (that's Phase 3).
explainer
by nemockTurn a topic (or source document) into a visually dynamic HTML explainer deck and a narrated vertical video, end-to-end, using only local/free tools (Kokoro TTS, torchaudio forced alignment, Playwright, ffmpeg) plus this Claude session. Use when the user wants to "make an explainer video", "turn this into a Short/ Reel/TikTok", "create an explainer deck", or "/explainer <topic>". Supports topic-only OR source-driven (ingest a PDF/URL and frame a real figure/screenshot); aspects 9:16, 16:9, 4:5; fixed theme. Generation only — it writes a labeled output dir + manifest.json; it does NOT post to social platforms.
cross-episode-arc
by nemockSurface themes that span multiple past episodes and suggest concrete callback opportunities for the next episode. Reads cleaned transcripts and topic shortlists across the recent run, clusters recurring themes (e.g., "AI commoditization", "Spotify ad strategy", "founder talent flight"), and produces a callbacks document that names the theme, when it last came up, what was said, and a suggested phrasing the host can drop in. Also writes a longer themes map that catalogs every running thread across the lookback window. Run this skill when the user says "what arcs are running across episodes", "find callbacks for EP043", "cross-episode themes", "what should I call back to", "callback opportunities", "what are the running threads", or any equivalent ask about story continuity. Run after episode-program for the next episode is drafted but before recording, so the host can absorb the callbacks during prep.
research-brief
by nemockBuild a one-page research brief on a single topic for an upcoming podcast episode. Produces fact-cited bullets the host can pull from extemporaneously — never paragraphs of prepared remarks. Each brief includes key facts with working source URLs, three contrarian or non-obvious angles, surprising stats, historical parallels, and named characters with quotes the host can reference. Cites every claim with a verified URL. Run this skill when the user says "research this topic", "build a brief on X", "research brief", "background for the segment on X", "give me ammunition on X", "go deep on T-20260501-01", or any equivalent ask for per-topic prep material. Run once per topic on the rundown.
distribution-pack
by nemockBuild the social distribution package for a published episode. Produces a LinkedIn post in the host's voice (1300–2000 characters), an X/Twitter single post plus a 4-tweet thread option, an Instagram caption built around the featured clip, a YouTube community post, and an optional newsletter tie-in section when the host runs a tie-in newsletter. Voice-checked against banned words and banned phrases. Schedules posts via Blotato when the connector is available; falls back to writing drafts to a local file. Run this skill when the user says "build the distribution pack", "draft the social posts", "social copy for EP042", "promote EP042", "make the LinkedIn post", "schedule the posts", "distribution pack", or any equivalent ask for episode promotion. Run after show-notes and clip-finder.
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.