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...
ai-tutor
by ShawhinTUse when user asks to explain, break down, or help understand technical concepts (AI, ML, or other technical topics). Makes complex ideas accessible through plain English and narrative structure.
youtube-strategy
by ShawhinTTurn a pain point, topic, or rough idea into a compelling YouTube package — title, thumbnail, intro hook, motivation/story, and outro — for Shaw's channel. Use any time Shaw is writing, brainstorming, or iterating on YouTube content. Triggers include "title ideas for this video", "help me title this YouTube video", "punch up this title", "thumbnail ideas", "design the thumbnail for X", "title and thumbnail for X", "package this video", "what would this look like as a YouTube video", "write the intro", "write the hook", "draft the motivation", "write the outro", "iterate on the script", "Ed Lawrence-style intro". Casual mentions like "title this for me", "thumbnail this", "I'm making a video about X", or "help me write the open" should also trigger. Do NOT use for LinkedIn posts (use linkedin-post-writer), newsletters (use newsletter-writer), or sales copy (use conversion-copy or sales-letter-writer) — this skill is specifically for YouTube packaging and scripting.
sales-letter-writer
by ShawhinTDraft long-form sales letters and one-pagers for Shaw's offers (intensives, workshops, courses, productized services) using Hormozi's $100M Offers principles. Use this skill whenever Shaw asks to write, draft, or iterate on a sales letter, one-pager, offer page, landing page copy, sales page, "offer brief," or any long-form copy designed to sell a specific paid offer. Triggers include "write a one-pager for X", "draft a sales page for my new offer", "help me write the sales letter for my [intensive / workshop / cohort / program]", "turn this offer into a sales page", or any time Shaw is putting together written copy whose job is to sell a specific package. Even casual mentions like "I need to write up my new offer" or "let's put the offer in writing" should trigger this skill. Do NOT use for short-form content like LinkedIn posts, tweets, or newsletters (use linkedin-post-writer or newsletter-writer instead) — this skill is specifically for long-form sales copy that walks a buyer from headline to CTA.
skill-helper
by ShawhinTWalk someone through building their first (or next) high-leverage Claude skill, end-to-end. Gather context silently, diagnose their level, run a time study, score time-vs-complexity for their level, suggest 3-5 candidate skills, hand off to skill-creator, and close with a one-line opt-in CTA to share what they built with Shaw. Use whenever someone is figuring out what skill to build, what to automate, or where to start with skills. Triggers include "help me build a skill", "what should I automate", "where do I start with skills", "I don't know what to build", "walk me through my first skill", "help me find a skill to build", "what's worth automating", "give me skill ideas", "what's a good first skill". Also fires when someone shares a calendar or workflow and asks what's automatable, when a new Claude user wants guided onboarding to skill-building, or when an experienced builder is hunting higher-leverage targets. Casual phrasing like "I should probably automate something" counts too.
stripe-helper
by ShawhinTHandle Shaw's Stripe operations — creating and sending invoices, generating payment links, and pulling reporting data (balance, recent payments, customer history). Use this skill whenever Shaw mentions Stripe, invoicing a client, billing someone, sending a payment link, checking what someone has paid, or any reference to charges, refunds, or revenue activity. Triggers include "send X an invoice", "bill X for Y", "create a Stripe invoice", "make a payment link", "how much did X pay", "what's my Stripe balance", "did X's invoice go through", "void this invoice", "refund X", "check my Stripe", or any casual phrasing like "throw an invoice on the books for X". Even when Shaw doesn't say "Stripe" explicitly — anything about billing a client, generating a paid link, or looking up payment history — this skill should fire.
workshop-use-case-researcher
by ShawhinTResearch and brainstorm practical use case ideas for custom AI workshops and training proposals. Use this skill whenever Shaw is preparing a workshop, training session, or proposal for a client and needs to identify relevant use cases for a specific audience. Triggers include: "brainstorm use cases", "what use cases should I cover", "help me prep the workshop for [company]", "I need use case ideas for [role/audience]", "research topics for the training", "what should I demo", or any reference to building out a custom workshop or training proposal. Also trigger when Shaw mentions a specific client engagement where the deliverable is a training session, workshop, or enablement program. Even casual mentions like "what should I teach them" or "I need to figure out the use cases for this one" should trigger this skill.
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.