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...
emergency-contraception
by GuttyoUse when a caller asks about emergency contraception (EC / 緊急避妊) after unprotected intercourse or contraceptive failure, including cases where a partner's method failed or the circumstances around consent are uncertain. Produces a three-way next-action decision — Call (hotline or crisis support in parallel with the medication pathway), Go (open pharmacy participating in the Japan OTC levonorgestrel program), or Wait (context-specific, typically when the time window has already closed and follow-up routing is the useful output) — with the Yorukusu safety boundary on every output. Integrates the caller's Personal Health Context for interacting medications and known contraindications. Never outputs a diagnosis and never recommends prescription medication outside the current Japan OTC-available options.
cough-respiratory
by GuttyoUse when a caller reports cough, wheezing, breathing difficulty, stridor, chest tightness, or any respiratory complaint in themselves or a dependent of any age — with a lower threshold to escalate for children. Produces a three-way next-action decision — Call (emergency or hotline), Go (open pharmacy), or Wait (home self-care) — with the Yorukusu safety boundary on every output. Inputs include age, cough character (dry, wet, barky, paroxysmal), respiratory work-of-breathing signs, duration, concurrent fever, known respiratory conditions, and the caller's Personal Health Context. Never outputs a diagnosis and never recommends prescription medication.
vomiting-diarrhea
by GuttyoUse when a caller reports vomiting, diarrhea, or both, in themselves or a dependent of any age, with or without accompanying fever. Produces a three-way next-action decision — Call (emergency or hotline), Go (open pharmacy), or Wait (home self-care with ORS and monitoring) — with the Yorukusu safety boundary on every output. Inputs include age, episode frequency and severity, onset timing, dehydration markers (urine output, activity, mucous membranes), concurrent symptoms (fever, blood, severe abdominal pain), and the caller's Personal Health Context. Never outputs a diagnosis and never recommends prescription medication.
adult-headache
by GuttyoUse when an adult (age 18 and over) reports a headache in themselves and is uncertain whether home care is appropriate, a pharmacy visit is needed, or emergency evaluation is required. Produces a three-way next-action decision — Call (emergency or hotline), Go (open pharmacy), or Wait (home self-care) — with the Yorukusu safety boundary on every output. Inputs include headache characteristics (onset, pattern, severity, location), concurrent neurological or systemic symptoms, recent trauma, known headache history, and the caller's Personal Health Context including anticoagulant use, blood-pressure control, and pregnancy status. Child and adolescent headache is out of scope for this skill. Never outputs a diagnosis and never recommends prescription medication.
minor-injury
by GuttyoUse when a caller reports a minor injury — a cut, scrape, burn, bump, fall, sprain, animal bite, or nosebleed — in themselves or a dependent of any age, and is uncertain whether home care is sufficient or a professional visit is needed. Produces a three-way next-action decision — Call (emergency or hotline), Go (open pharmacy for supplies or pharmacist review), or Wait (home wound care) — with the Yorukusu safety boundary on every output. Inputs include mechanism of injury, extent and location of the wound, bleeding status, consciousness after head injury, tetanus history, and the caller's Personal Health Context including any anticoagulant use. Never outputs a diagnosis and never recommends prescription medication.
pediatric-fever-triage
by GuttyoUse when a caregiver reports a child (age 0 to under 18) with fever or subjective warmth at night, with or without accompanying symptoms. Produces a three-way next-action decision — Call (emergency or hotline), Go (open pharmacy), or Wait (home self-care) — with the Yorukusu safety boundary on every output. Inputs include age, temperature (measured or subjective), fever duration, concurrent symptoms, antipyretic history, and the caller's Personal Health Context. Never outputs a diagnosis and never recommends prescription medication.
evidence-selector
by GuttyoUse as a preflight before any clinical triage Skill. Given the caregiver's message and the declared candidate evidence paths for the selected clinical Skill, returns a JSON list of filenames to load into the main Skill's Opus 4.7 call. Never outputs a diagnosis, never makes a clinical decision, never references a specific medication.
allergy-reaction
by GuttyoUse when a caller reports a possible allergic reaction in themselves or a dependent — hives, facial swelling, breathing difficulty, lip or mouth tingling, GI symptoms after ingestion, or any reaction following exposure to a known allergen or a newly introduced food or medication. Produces a three-way next-action decision — Call (emergency or hotline), Go (open pharmacy), or Wait (home observation) — with the Yorukusu safety boundary on every output. Integrates the caller's Personal Health Context for known allergens, prior-reaction severity, and carried rescue medication. Never outputs a diagnosis and never recommends prescription medication.
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.