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...
ui-designer
by h00mankindUI/UX design and frontend visual implementation across React, Svelte (4 and 5 with runes), and plain HTML / single-file widgets. Use this skill whenever the user mentions component styling, layout work, CSS, Tailwind, design tokens or design systems, responsive design, breakpoints, spacing, padding, margin, alignment, flex, grid, fit-content, fill-available, icons or icon libraries, sliders, dropdowns, comboboxes, switches, toggles, image uploaders, canvas performance, motion, animation, transitions, gestures, or any visual polish work. Also trigger when the user asks to fix, improve, restyle, refactor, or audit any visual component, page, or widget — even when they don't explicitly say "design". Skip for backend logic, API routes, business logic, data fetching, database work, or test authoring.
to-html
by h00mankindProduce a single-file HTML artifact instead of a wall of markdown when the answer is spatial, side-by-side, interactive, or live-rendered — letting the reader see it at a glance rather than reconstruct it from prose. Use this skill whenever the user asks for an explanation, plan, design exploration, code review, diff or PR writeup, module or architecture map, design system or component sheet, prototype, animation tuning, clickable flow, slide deck, status report, incident timeline, post-mortem, research explainer, glossary, comparison table, flowchart, illustration set, custom editor, triage board, feature-flag toggler, prompt tuner, or any deliverable they'll skim, scan, point at, or hand off — even when they don't say "HTML" or "artifact". Skip for chat answers, quick replies, code snippets to paste into an editor, Word docs, .pptx, spreadsheets, or anything that must round-trip to a non-HTML format.
brand-name
by h00mankindGenerate and screen brand name candidates the way professional naming agencies do, across the full name-type taxonomy (descriptive, suggestive, invented, compound, portmanteau, acronym, synonym-driven, palindrome, reduplicative, foreign, altered-spelling, and more), screening on sound symbolism, syllable/pronounceability, distinctiveness (Abercrombie spectrum), and the standard evaluation criteria. Has two modes — quick (no questions, ~20 candidates, fast) and deep (a 5–10 question grill, then 100+ candidates down to a 20–30-name shortlist); defaults to deep when unspecified. Always outputs an interactive HTML artifact showing the whole candidate pool (naming matrix + score cards for the recommended set + compact chips for the rest), filterable by name-type and metaphor, where the user stars any candidate to build their own shortlist live, with reset and copy-as-markdown. Use whenever the user wants to name a company, product, feature, app, project, startup, band, or anything else; asks for "name ideas", "bra
variations
by h00mankindGenerate 3–5 radically different variations of a component, screen, or UX flow so the user can compare and pick — all rendered in one place, with a switcher. Use when the user wants design options, alternative takes on a component or flow, says "show me a few versions", "design it twice", or can't decide between directions.
learn
by h00mankindMulti-session learning workspace — teaches the user a topic through small self-contained HTML lessons grounded in a mission, with progress, glossary, and trusted sources tracked in docs/learn/<topic>/. Use when the user wants to learn or be taught something — a language, framework, concept, or practice — or says "teach me", "I want to learn", or "next lesson".
frontend-fable-mode
by h00mankindExperimental operating mode that pushes any capable model — Claude Opus, GPT, Gemini, anything — toward frontier-level frontend output through forced commitment, a design system, craft details, and a mandatory self-critique loop. Load before building or styling any UI — pages, components, artifacts, prototypes. Works as an agent skill or pasted straight into a system prompt. Skip for backend logic or data work.
idea
by h00mankindCapture, track, validate, and prototype ideas — one file per idea in docs/ideas/ with a status lifecycle (spark → validated → building → parked → dead). Capture is fast and question-free, and ends by offering a throwaway prototype to test the idea's riskiest assumption. Use when the user has a new idea to jot down, asks "what ideas do I have", wants to validate or kill an idea, or wants to prototype or sanity-check a data model, state machine, or logic before committing.
motion
by h00mankindAnimation and motion design for interfaces — what to animate, durations, easing, springs, gestures, performance, and reduced motion. Use when adding or tuning animations, transitions, micro-interactions, page transitions, scroll effects, drag/swipe gestures, or anything that moves.
improve
by h00mankindAudit-then-improve pass over UI, UX, code, security, or all of them at once (deep) — always starts by asking what area to improve and whether to just audit or audit-and-fix in one go. Produces severity-ranked findings with evidence; in execute mode it applies the fixes immediately after. Use when the user wants a review, audit, critique, security review, asks "is this safe to ship", or wants something polished, cleaned up, hardened, refactored, or improved.
frontend
by h00mankindBuilding and styling frontend UI — components, state, CSS, Tailwind, design tokens, layout (flex, grid, spacing, alignment), responsive design, interactive controls (dropdowns, sliders, switches, uploaders), icons, and accessibility, across React, Svelte, and plain HTML — driven by forced design commitment, a token system, craft details, and a mandatory self-critique loop. Use when building, extending, restyling, or fixing any UI feature, page, component, or widget — even when the user doesn't say "design". Also works pasted straight into another model's system prompt. Skip for backend logic, API routes, or data work. For animation use motion.
ship
by h00mankindPrepare and publish local git changes through branch, commit, push, and pull request with reviewer-ready discipline. Use when the user says "ship it", "commit this", "push this", "open a PR", "create a PR", "publish these changes", or "make a branch". Skip for read-only git inspection, CI debugging, or responding to PR review comments.
plan
by h00mankindTurn an idea or feature into a PRD plus thin vertical-slice issues, in one of two modes — grill (a relentless one-question-at-a-time interview to stress-test the idea first) or trust (no questions, synthesize from existing context and deliver). Maintains the project's knowledge base as it goes — a domain glossary in docs/CONTEXT.md and decision records in docs/adr/. Writes the plan to docs/plans/ and optionally files the slices as GitHub issues. Use when the user wants to plan or brainstorm a feature, stress-test a design, write a PRD, break down work into tickets, or says "grill me" or "plan this".
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.