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...
update-graph-ui
by PipelexBump the pinned `@pipelex/mthds-ui` (and `elkjs`) version that the generated ReactFlow HTML loads from jsDelivr. Re-fetches the bundle, recomputes SRI hashes, and updates the Python constants in `standalone_assets.py`. Use when user says "update graph ui", "bump mthds-ui", "update graph viewer", "new version of mthds-ui", or any variation of updating the CDN-pinned graph viewer assets.
add-model
by PipelexAdd a new AI model to the Pipelex inference system. Guides through all required steps: backend TOML configuration (OpenAI, Azure, Anthropic, Google, etc.), kit sync, test profile collections, and fixture regeneration. Use when the user says "add a model", "add GPT-X", "add Claude X", "new model", "register a model", "add Gemini X", "support model X", "add model to backend", or any variation of introducing a new AI model to the inference configuration. Also use when the user mentions a model name that doesn't exist in the backend configs yet and wants to add it.
release
by PipelexAutomates the Pipelex release workflow: bumps the version in pyproject.toml, finalizes the CHANGELOG.md Unreleased section, runs quality checks, creates a release/vX.Y.Z branch, commits, pushes, and opens a PR to main. Use when user says "release", "cut a release", "bump version", "prepare a release", "make a release", "ship it", "create release branch", or any variation of shipping a new version of pipelex. The user can optionally provide changelog content inline when invoking the skill (e.g. "/release Added new extract backend"), which will be used as the changelog entry for this version.
temporal-e2e-validate
by PipelexFull end-to-end validation of Temporal distributed execution (Phases 2-5 + v1 routing + v2 queue options / worker-runtime profiles). Two modes: (1) pytest against a real Temporal server for detailed assertions on all test cases, and (2) true 3-process setup (server + separate worker process + submitter) that validates the actual deployment topology including cross-process serialization, LibraryCrate propagation, deferred hydration, concurrent isolation, image payload storage, cross-worker graph tracing with GraphSpec assembly, and cross-worker cost-report assembly (runner-side usage aggregated into a single submitter cost report, validated cheaply via the hidden `--dry-run --mock-usage` trigger). Step 8 validates v1 per-activity routing. Step 9 validates v2 per-queue submitter options (timeouts, retry, rate-limit), per-handle option overrides, named worker-runtime profiles selected via `--profile`, and the strict `--task-queue` CLI typo check with "did you mean?" suggestion. Mode 1 also folds in the error-han
temporal-test-crate
by PipelexRun and diagnose the LibraryCrate integration tests for Temporal. Tests that PipeSequence controllers execute on Temporal workers via LibraryCrate propagation, including concurrent isolation tests for conflicting concepts and pipes. Use when the user says 'test temporal crate', 'run crate tests', 'isolation tests', or wants to verify LibraryCrate on Temporal works.
test-model
by PipelexTest an AI model on a specific backend using the Pipelex inference test infrastructure. Handles test profile creation, fixture regeneration, and running the right test class for the model type (LLM, image gen, extract, search). Use when the user says "test model X", "test gpt-5.4 on openai", "test model on gateway", "run inference test for model", "try model X on backend Y", "verify model X works", or any variation of running inference tests against a specific model on a specific backend. Also use when the user mentions testing a model after adding it, or wants to verify a model works end-to-end with real API calls.
release
by PipelexAutomates the kajson release workflow: bumps the version in pyproject.toml, finalizes the CHANGELOG.md Unreleased section, runs quality checks, creates a release/vX.Y.Z branch, commits, pushes, and opens a PR to main. Use when user says "release", "cut a release", "bump version", "prepare a release", "make a release", "ship it", "create release branch", or any variation of shipping a new version of kajson. The user can optionally provide changelog content inline when invoking the skill (e.g. "/release Added new encoder feature"), which will be used as the changelog entry for this version.
release
by PipelexPrepare a new release for the pipelex-cookbook project. Bumps version in pyproject.toml, syncs uv.lock, updates CHANGELOG.md, manages the release/vX.Y.Z branch, runs lint and type checks, and commits. Use when the user says "release", "prepare a release", "bump version", "new version", or "cut a release".
add-pipeline-story
by PipelexAdd a new pipeline example to the Storybook from a .mthds bundle file. Generates both dry-run and live-run GraphSpecs via pipelex CLI, creates the data directory, spec file, wires it into mockGraphSpec.ts, and creates the story file. Use when user says "add example", "add pipeline", "new storybook story", "add a graph", "new pipeline example", or provides a .mthds file to visualize.
release
by PipelexAutomates the mthds-ui release workflow: bumps the version in package.json, finalizes the CHANGELOG.md Unreleased section, runs quality checks and tests, creates a release/vX.Y.Z branch, commits, pushes, and opens a PR to main. Use when user says "release", "cut a release", "bump version", "prepare a release", "make a release", "ship it", "create release branch", or any variation of shipping a new version of mthds-ui. The user can optionally provide changelog content inline when invoking the skill (e.g. "/release Added StuffViewer component"), which will be used as the changelog entry for this version.
release
by PipelexAutomates the Pipelex API release workflow: bumps the version in pyproject.toml, finalizes the CHANGELOG.md Unreleased section, runs quality checks, creates a release/vX.Y.Z branch, commits, pushes, and opens a PR to main. Use when user says "release", "cut a release", "bump version", "prepare a release", "make a release", "ship it", "create release branch", or any variation of shipping a new version of pipelex-api. The user can optionally provide changelog content inline when invoking the skill (e.g. "/release Added new auth backend"), which will be used as the changelog entry for this version.
postman-run-bundle
by PipelexTurn a Pipelex MTHDS bundle into an API request you can run — push it as a ready-to-run query into the live "Pipelex FastAPI" Postman collection, emit a curl command, execute it directly, or just dry-run validate it (no inference, no cost). Use this whenever the user points at a bundle directory or a .mthds file (often with an inputs.json) and wants to run, validate, or test it via the API — e.g. "make a Postman query for this bundle", "add a Postman request to run cv_batch_screening.mthds", "run the fashion_moodboard bundle against the API", "validate this bundle via the API", "dry-run this method against the API", "give me the curl for this bundle", or just "postman" said alongside a bundle path. It resolves the bundle exactly like `pipelex run bundle <path>` (auto-detects bundle.mthds / the single .mthds, reads main_pipe, loads the sibling inputs.json) and targets /v1/execute, /v1/start, and /v1/validate. Trigger it even when the user does not name the endpoint or the word "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.