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...
aversion-factoring
by EquiStampCFAR rationality technique for decomposing aversions into specific addressable components using the LEGO brick model. Use when the user: (1) avoids something they believe they should do, (2) says "I hate doing X" and wants to understand why, (3) wants to overcome a specific aversion, (4) practice decomposing emotional resistance, or (5) wants to understand the gap between what they want to want and what they actually want. Triggers: "aversion factoring", "I hate", "I avoid", "I can't make myself", "why do I resist", "overcome aversion", "ugh field", "CFAR", "decompose aversion".
focusing
by EquiStampGendlin's Focusing technique adapted by CFAR for accessing pre-verbal bodily knowledge ("felt sense") to gain insight on problems. Use when the user: (1) feels stuck and analytical thinking isn't helping, (2) wants to understand what they really feel about something, (3) needs to access intuition or gut feelings, (4) wants to check if their intellectual conclusions match their deeper sense, (5) is doing Internal Double Crux and needs to access each side's felt sense, or (6) wants to practice body awareness for better decision-making. Triggers: "focusing", "felt sense", "what do I really feel", "gut feeling", "body awareness", "Gendlin", "something feels off", "I can't put it into words", "check in with myself", "CFAR".
freedom-of-action
by EquiStampCFAR rationality technique for identifying where default frames artificially constrain perceived options and expanding the action space. Use when the user: (1) feels stuck with no good options, (2) wants to identify artificial constraints on their choices, (3) needs to expand their perceived action space, (4) feels obligated rather than choosing, (5) wants to explore what a "fair bid" from a situation looks like, or (6) wants to practice noticing where they've stopped considering alternatives. Triggers: "freedom of action", "no good options", "feel stuck", "feel obligated", "what are my options", "expand options", "default behavior", "comfort zone", "learned helplessness", "CFAR".
internal-double-crux
by EquiStampCFAR rationality technique for resolving internal conflicts by facilitating dialogue between competing motivations or "sub-agents" within the mind. Use when the user: (1) feels torn between two options or motivations, (2) experiences "should" vs "want" conflicts, (3) can't motivate themselves despite believing something is right, (4) wants to understand procrastination or self-sabotage, (5) has internal resistance they can't explain, or (6) wants to practice parts-work for better self-understanding. Related to IFS. Triggers: "internal double crux", "IDC", "torn between", "part of me wants", "I should but", "inner conflict", "self-sabotage", "competing motivations", "parts work", "IFS", "CFAR".
pride-self-recognition
by EquiStampCFAR rationality technique for discovering authentic values by converting frustrations and annoyances into positive value statements. Uses iterative loop of expressing annoyance, finding the underlying value, re-expressing, and checking if the emotional charge has shifted. Use when the user: (1) is frustrated or annoyed and wants to understand why, (2) wants to discover what they really care about, (3) needs to move from self-criticism to self-recognition, (4) wants to identify their authentic values (vs. "shoulds"), (5) practice converting complaints into values, or (6) wants to understand their "who-ness." Triggers: "what do I care about", "why am I frustrated", "values", "self-recognition", "pride", "who-ness", "what matters to me", "annoyance", "CFAR".
trigger-action-planning
by EquiStampCFAR rationality technique for installing reliable automatic behaviors by pairing specific triggers with specific actions. Based on implementation intentions research (0.65 SD effect size). Use when the user: (1) wants to build a new habit or change a behavior, (2) knows what they should do but keeps forgetting or failing to act, (3) wants to install a specific response to a recurring situation, (4) needs to bridge the gap between intention and action, (5) wants to automate a rationality technique so it fires reliably, or (6) wants to practice creating and installing TAPs. Triggers: "TAP", "trigger action", "implementation intention", "habit", "when I notice", "if-then plan", "I keep forgetting to", "I want to start doing", "build a habit", "behavior change", "CFAR".
bucket-errors
by EquiStampCFAR rationality technique for identifying where you've entangled questions that should be separate, causing you to flinch away from evidence. Use when the user: (1) feels defensive about acknowledging something true, (2) conflates unrelated beliefs ("Am I a good writer?" with "Did I spell this correctly?"), (3) has trouble accepting feedback, (4) wants to practice detecting question substitution, or (5) notices they avoid thinking about certain topics. Related to Kahneman's attribute substitution. Triggers: "bucket error", "conflating", "flinching away", "defensive about", "question substitution", "entangled beliefs", "CFAR", "can't accept feedback".
resolve-cycles
by EquiStampCFAR rationality technique using 5-minute time-boxed problem-solving to break through procrastination and analysis paralysis. Use when the user: (1) is overthinking and needs to just try solving something, (2) is stuck in analysis paralysis, (3) needs permission to attempt something imperfect, (4) wants to build problem-solving momentum, or (5) has a "bug" (life problem) that might be solvable with focused effort. Triggers: "resolve cycle", "just try it", "5 minutes", "stop overthinking", "analysis paralysis", "stuck", "procrastinating", "yoda timer", "bug hunt", "CFAR".
double-crux
by EquiStampCFAR rationality technique for resolving disagreements by finding shared underlying belief divergence points (cruxes). Use when the user wants to: (1) resolve a disagreement by finding the real point of contention, (2) prepare for a difficult conversation by mapping belief structure, (3) practice collaborative truth-seeking, (4) examine beliefs by finding what would change their mind, or (5) facilitate a structured disagreement between two positions. Triggers: "double crux", "disagree", "what would change my mind", "crux", "resolve disagreement", "find the real issue", "belief examination", "CFAR".
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.