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...
bump-packages
by lifinanceBump every external npm dependency in this pnpm workspace to its latest version, then open a `chore: bump packages` PR. Use this whenever the user runs `/bump-packages`, asks to "bump/update/upgrade the (dev)dependencies", "update packages to latest", "do a dependency bump", or otherwise wants the monorepo's deps refreshed. Patch and (>=1.x) minor bumps apply automatically; major bumps — and 0.x minors, which are breaking under SemVer — are NEVER applied without first showing the user a breaking-changes report and getting an explicit go/no-go per package. The skill validates the result (build, types, lint, tests), adds a `fix:` changeset for any runtime-dependency bump on a publishable package, and finishes with an overview of what changed.
changeset
by lifinanceAuthor a Changesets changeset (a `.changeset/*.md` file) for the current changes. Use this whenever a change touches publishable library source under `packages/` and is about to be committed or opened as a PR, or whenever the user mentions a changeset, a version bump, release notes, or asks "what bump should this be". This repo uses Changesets (not Lerna/conventional-commit bumps), and CI fails any PR that changes a publishable package without a changeset — so adding one is part of finishing a change, even if the user didn't say "changeset" explicitly.
creating-user-stories
by lifinanceUse when drafting, maintaining, refining, or auditing a structured user-stories catalogue from a product spec + design-review notes + open-questions list. Outputs persona-grouped stories with explicit linkage to unresolved open questions, in a readable format suited for product, engineering, and audit review alike. Trigger on "write user stories for", "draft stories from this spec", "expand the user stories", "add a story for X", "audit the catalogue", "clean up the open questions", "refine the stories", or any request to produce or maintain a stories catalogue. Use this skill whenever the user is working on a structured stories catalogue or its companion open-questions page, even if they don't say "user story" explicitly. Skip for casual feature lists or one-off ticket descriptions.
check-open-prs
by lifinancePersonal PR inbox for LI.FI engineers — covers both outgoing PRs (yours) and incoming review queue (others'). Produces a single dry-run dashboard with (a) your OWN open PRs cross-referenced with their
start-linear-ticket
by lifinanceStart work on a Linear ticket — fetches the issue, creates a properly-named local git branch in the right repo, moves the ticket to "In Progress", and assigns it to the current user. Use when the user says "start ticket", "start linear ticket", "begin work on EXSC-XXX", "/start-ticket", "let's start <ID>", or supplies a Linear issue ID/URL with intent to begin work. Mirrors the "Create branch" button from Jira, but also handles the status flip and ownership claim in one step — designed for orgs where PR-auto-assign is off but starting work is the right moment to claim a ticket. Requires the Linear MCP server. Skip if the user is just asking about a ticket (read intent) rather than starting work, or if the ticket is already In Progress and has a linked branch — in that case just show the existing branch.
post-pr-for-review
by lifinancePost a pull request to the LI.FI `#dev-sc-review` Slack channel for smart-contract team review. Enables auto-merge (squash) on the PR by default, posts the PR URL + title as a top-level message (matching the existing channel format `<URL> << <title>`), then replies in-thread tagging the `@smartcontract_core` user group. Use when the user says "post PR for review", "send to sc review", "share PR with sc team", "post to dev-sc-review", or supplies a PR URL with intent to request review from the smart-contract core team. Requires the Slack MCP server to be connected.
changeset
by lifinanceAuthor a Changesets changeset (a `.changeset/*.md` file) for the current changes. Use this whenever a change touches publishable library source under `packages/` and is about to be committed or opened as a PR, or whenever the user mentions a changeset, a version bump, release notes, or asks "what bump should this be". This repo uses Changesets (not Lerna/conventional-commit bumps), and CI fails any PR that changes a publishable package without a changeset — so adding one is part of finishing a change, even if the user didn't say "changeset" explicitly.
lifi
by lifinanceLI.FI REST API for cross-chain and same-chain token swaps, bridging, DeFi deposits (Composer), yield discovery (Earn), and intent-based execution (Intents). USE THIS SKILL WHEN USER WANTS TO: - Swap tokens between different blockchains (e.g., "swap USDC on Ethereum to ETH on Arbitrum") - Bridge tokens to another chain (e.g., "move my ETH from mainnet to Optimism") - Swap tokens on the same chain with best rates (e.g., "swap ETH to USDC on Polygon") - Find the best route or quote for a token swap across chains - Deposit into DeFi vaults/lending/staking in one click, including cross-chain (Composer: Aave, Morpho, Pendle, EtherFi, Yearn, etc.) - Discover yield opportunities, vault APY/TVL data, or track DeFi positions (Earn) - Execute gasless or intent-based transfers via a solver network (LI.FI Intents) - Move stablecoins cheaply with optimized defaults (stablecoin preset) - Build multi-chain payment flows (accept any token, settle in specific token) - Check supported chains, tokens, bridges, or gas prices - T
start-linear-ticket
by lifinanceStart work on a Linear ticket — fetches the issue, creates a properly-named local git branch in the right repo, moves the ticket to "In Progress", and assigns it to the current user. Use when the user says "start ticket", "start linear ticket", "begin work on EXSC-XXX", "/start-ticket", "let's start <ID>", or supplies a Linear issue ID/URL with intent to begin work. Mirrors the "Create branch" button from Jira, but also handles the status flip and ownership claim in one step — designed for orgs where PR-auto-assign is off but starting work is the right moment to claim a ticket. Requires the Linear MCP server. Skip if the user is just asking about a ticket (read intent) rather than starting work, or if the ticket is already In Progress and has a linked branch — in that case just show the existing branch.
creating-user-stories
by lifinanceUse when drafting, maintaining, refining, or auditing a structured user-stories catalogue from a product spec + design-review notes + open-questions list. Outputs persona-grouped stories with explicit linkage to unresolved open questions, in a readable format suited for product, engineering, and audit review alike. Trigger on "write user stories for", "draft stories from this spec", "expand the user stories", "add a story for X", "audit the catalogue", "clean up the open questions", "refine the stories", or any request to produce or maintain a stories catalogue. Use this skill whenever the user is working on a structured stories catalogue or its companion open-questions page, even if they don't say "user story" explicitly. Skip for casual feature lists or one-off ticket descriptions.
lifi
by lifinanceCross-chain token swaps and bridges via the LI.FI protocol. Get quotes, execute transfers, track progress, and compose DeFi operations across 35+ blockchains.
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.