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...
lean-prover
by zachmayerMulti-agent Lean 4 theorem proving system using blueprint-driven coordination. Use when the user says "prove", "formalize", "Lean", "Mathlib", "theorem", "lemma", or mentions competition problems (Putnam, IMO, MiniF2F). Also use for orchestrating complex proof campaigns across multiple lemmas. Do NOT use for general programming, non-Lean math, or single-tactic proofs that need no orchestration.
mental-models
by zachmayerApplies mental models to decisions, tradeoffs, failures, biases, complexity, epistemology. Use when: think through, trade-offs/pros/cons, should I, analyze decision, missing angles, steel man, devil's advocate, debug this, root cause, five whys, post/pre-mortem, overthinking, analysis paralysis, what went wrong, why did this fail, what could go wrong. Triggers: too complex, over-engineering, keep it simple/KISS, simplify, grug brain, premature abstraction, clever code, one/two-way door, opportunity cost, exploit vs explore, decision paralysis, bottleneck, feedback loop, leverage point, emergent, compounding, technical debt, bias, sunk cost, anchoring, confirmation bias, Dunning-Kruger, impostor syndrome, incentives, Goodhart, Chesterton's fence, antifragile, margin of safety, hidden assumptions, framing, bad faith, reframe, first principles, defense in depth, wrong framework, circle of competence, scout mindset, second order effects, unintended consequences. Do NOT use for implementation tasks.
kaggle
by zachmayerKaggle CLI for downloading competition/dataset data and managing submissions. Use when the user says "kaggle", "download dataset", "submit to competition", "kaggle competition", or works with Kaggle data/competitions. Do NOT use for general data science tasks (use data-science skill) or non-Kaggle data sources.
concise-writing
by zachmayerEnforces tight, scannable prose in all writing output. Use when the user says "write", "draft", "summarize", "document", "README", "message", "announcement", or any task producing prose — technical docs, commit messages, PR descriptions, emails, reports. Applies conciseness rules: cut filler, active voice, lead with the point, concrete over abstract. Do NOT use for creative writing, fiction, or when the user explicitly asks for verbose/detailed explanations.
superforecaster
by zachmayerCalibrated forecasting for real-world future events, plus prediction market checks. Use when the user wants the probability of a future outcome in politics, economics, technology, policy, or world events. Triggers: "what's the probability of X?", "will X happen?", "how likely is Y?", "what are the odds of X?", "check prediction markets", "what do Metaculus/Manifold/Polymarket say about", "give me calibrated odds". Best for binary or date-bounded questions about external events. Also searches Metaculus, Manifold, PredictIt, Polymarket, Kalshi, Betfair, and Smarkets for current market-implied probabilities. Do NOT use for sports betting odds, current asset prices, numeric time-series forecasting from CSV data (use forecast skill), or internal predictions like whether code, tests, or builds will pass.
usage-cost
by zachmayerComputes what your Claude Code usage would cost at pay-as-you-go API prices by replaying the exact per-request token usage recorded in local transcripts (~/.claude/projects). Use when comparing subscription vs API billing, or when the user asks "what would my Claude Code usage cost", "how many tokens have I used", "is the Max plan worth it", "estimate my usage under the rate limit", or "subscription vs pay-as-you-go". Do NOT use for live Anthropic Console billing data, claude.ai web/desktop usage, or direct API-key usage logs — it only sees this machine's Claude Code transcripts.
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.