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...
build-without-dfinity-infra
by dfinityUse when you need to run a Bazel build or test outside DFINITY's internal infrastructure — i.e. without access to the internal remote cache / remote downloader (bazel-remote.idx.dfinity.network), e.g. on a personal machine, in a sandbox, or for a reproducibility check. Two ways: --config=local, or bypassing the workspace bazelrc.
run-in-dev-container
by dfinityUse when you need to run a command (build, test, tool) inside the IC dev container via ./ci/container/container-run.sh — including on a host that has Docker but not podman (set CONTAINER_RUNTIME=docker).
fix-build-determinism
by dfinityUse this when asked to fix a Bazel build reproducibility / determinism issue — a target whose outputs differ between builds (e.g. across machines, users, or checkout locations), typically because something bakes an absolute build path or a timestamp into an artifact.
upgrade-governance-backend
by dfinityGuide the governance backend canister upgrade process — pick RC commit, determine targets, create proposal texts, submit proposals, create forum posts, schedule votes, and update changelogs.
fix-flaky-tests
by dfinityUse this when asked to fix flaky bazel tests.
release
by dfinityRelease a new version of icp-cli. Use when the user asks to do a release or cut a new version. Requires a semver VERSION argument.
evm-rpc
by dfinityCall Ethereum and EVM chains from IC canisters (Rust) via the EVM RPC canister using the evm_rpc_client crate. Covers typed API calls, raw JSON-RPC, multi-provider consensus, ERC-20 reads, and sending pre-signed transactions. Use when calling Ethereum, Arbitrum, Base, Optimism, or any EVM chain from a Rust canister. Do NOT use for generic HTTPS calls to non-EVM APIs — use https-outcalls instead.
icp-brand-design
by dfinityICP / DFINITY visual design system v2: tokens, color, typography, layout, components, accessibility for DFINITY and Internet Computer surfaces. Pairs with icp-brand-voice. Use when building or reviewing visual surfaces (NNS, ICP.app, Internet Identity, dashboards, the main website, developer docs, marketing). Enforces the system that ships on internetcomputer.org: three faces (Newsreader, Inter, JetBrains Mono), single rust accent, light editorial parchment as the default theme with an opt-in dark theme for product surfaces that need it, sentence case, italic for asides only, no em-dashes (U+2014), tamperproof spelled as one word. Triggers: ICP design, DFINITY design, brand tokens, design review ICP, color palette, typography ICP, NNS redesign, light or dark mode ICP. OISY, Caffeine, and ecosystem products with their own brand are out of scope.
icp-brand-voice
by dfinityICP / DFINITY positioning, voice, and vocabulary v2 for surfaces under the DFINITY or Internet Computer (ICP) mark. Pairs with icp-brand-design (colors, typography, components). Use when writing or reviewing copy, UI strings, headlines, hero lines, buttons, errors, empty states, release notes, blog posts, marketing pages, developer docs, social posts, decks. Enforces the calm, factual, plain voice (no hyperbole, no em-dashes, no emoji), the locked positioning ("Sovereign frontier cloud / Scaling AI that builds"), the four voice attributes (Factual, Plain, Calm, Sovereign by math), and the strict ban on bare "onchain" and "on-chain" as nouns, attributes, or selling points. Triggers, ICP voice, DFINITY voice, brand voice, is this on brand copy, vocabulary check, tagline review, headline review, ICP positioning, how should we describe ICP, write a headline. Products with their own voice (OISY, Caffeine, future ecosystem products with their own verbal systems) are out of scope.
asset-canister
by dfinityDeploy frontend assets to the IC. Covers certified assets, SPA routing with .ic-assets.json5, content encoding, and programmatic uploads. Use when hosting a frontend, deploying static files, or setting up SPA routing on IC. Do NOT use for canister-level code patterns or custom domain setup — use custom-domains instead.
autosync-ic-skills
by dfinityOne-time installer that makes a Claude Code project keep its Internet Computer skills up to date automatically. Sets up a SessionStart hook plus a sync script so .claude/skills/ always mirrors the latest skills published at skills.internetcomputer.org. Use when a user wants to install, bootstrap, or enable "always-latest" Internet Computer / IC / ICP / Motoko skills in a project, or pastes the link to this skill. This is a one-time setup action, not ongoing IC knowledge — after it runs, the installed hook keeps skills current on every session. Do NOT use for IC coding questions themselves — this only configures auto-updating skills.
canhelp
by dfinityDisplay a human-readable summary of a canister's interface given its mainnet canister ID or a human-readable name. Like --help but for canisters. Only for mainnet canisters — for local canisters, read the generated .did file in your project directly.
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.