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...
brief
by Praneeth-496One-sentence-or-paragraph answer, zero preamble. TRIGGER when user says "in one line", "one sentence", "TL;DR", "short answer", "quick", "just the answer", "don't explain", or the question is a factual lookup that doesn't need elaboration. Style change — apply for one turn.
compare
by Praneeth-496Side-by-side comparison table + verdict. TRIGGER when user says "X vs Y", "compare A and B", "which should I use", "should I pick X or Y", "what's better, A or B", or names two-or-more concrete alternatives (libraries, models, approaches, file structures, designs) and asks to choose.
consistency-checker
by Praneeth-496Source-free hallucination triage (SelfCheckGPT-style). Re-generates an answer or claim several times independently and flags the sentences that change across samples — divergence is a strong hallucination signal, consistency is a weak confidence signal. Use when you have no reference source to check against but want to know which parts to trust. TRIGGER on "is this made up?", "how confident is this?", "check this for hallucination".
council
by Praneeth-496Convene a panel of 4 Claude subagents (architect, reviewer, simplifier, adversary) on a single hard decision — architecture choice, security review, "should we?" questions. Each gives an independent ≤300-word opinion in parallel; main thread synthesizes consensus and dissent. Result is written to .claude/council/ for later audit. Use only for high-stakes one-shot decisions, not daily code edits.
critique
by Praneeth-496Harsh critical review — finds faults in code, prose, or a plan. TRIGGER when user says "critique this", "review this", "find faults", "tear this apart", "be harsh", "what's wrong with this", "is this any good", or pastes work and asks for honest feedback. Stronger than a normal review — assumes user wants the unflattering version.
debate
by Praneeth-496Judged multi-round debate for contested-correctness questions where a single pass over-commits to its first answer. 2-3 independent agents answer, read each other's reasoning, and revise over a capped number of rounds; a separate judge declares consensus or the best-supported position. Use for hard yes/no or "is this correct?" questions. TRIGGER on "is this actually safe/correct?", "settle this", "stress-test this conclusion".
devil
by Praneeth-496Steelman the opposing view. Construct the strongest possible case AGAINST a position. TRIGGER when user says "argue against this", "what's the counter-argument", "steelman", "play devil's advocate", "stress-test this idea", "convince me I'm wrong", or asks for the opposing view on a decision they've stated.
env-bootstrap
by Praneeth-496Create a mandatory isolated environment for a project so package/module versions never collide with the system or other projects. uv-first for Python (falls back to python -m venv), local node_modules for Node. Idempotent; never installs anything globally. TRIGGER when starting work in a new repo, when the user says "set up the environment", "create a venv", "isolate dependencies", or before any package install.
explainlikeim5
by Praneeth-496Simple, jargon-free explanation with one analogy. TRIGGER when user says "explain like I'm 5", "ELI5", "explain simply", "in plain English", "I don't understand X", "explain to a non-technical person/PM/my mom", "what does X actually mean", or asks to truly understand a concept rather than just look it up.
memory-graph
by Praneeth-496Build or extend a Graphiti-style knowledge graph (nodes + edges as JSONL) under the project's memory directory. Captures files, modules, concepts, decisions, and their relationships so future sessions can recall a 1-hop subgraph instead of re-reading flat memory snapshots. Modes; build (first run), add (incremental), rebuild (destructive). Project-agnostic; works on any git repo. TRIGGER when user says "build memory graph", "graph this project", "graphiti memory", "memory graph", or states a durable relationship worth remembering ("X depends on Y", "we superseded Z with W", "remember that A owns B", "decision: ..."). Also auto-trigger after `auto-memory` finishes on a project with ≥30 source files where no `graph/` directory exists yet — propose it before suggesting more flat snapshots.
orchestrate
by Praneeth-496Operator/orchestrator pattern. Decomposes a task into subtasks, picks the right specialist agent for each (code-reviewer, security-auditor, test-runner, simplifier, doc-writer, adversary), dispatches them in parallel where independent and sequential where dependent, then synthesizes one final result. Use when a task has 3+ distinct concerns (e.g. "review + test + update docs" or "audit security + check perf + write changelog").
pitch
by Praneeth-49630-second spoken pitch (~75 words). TRIGGER when user says "elevator pitch", "pitch this", "30 seconds", "summarize for my supervisor/committee/investor", "how would I introduce this in a defense", or asks for a quick spoken summary of the project/topic for a non-specialist audience.
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.