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...
ux-design-system
by VictorHueniAuthor a project's single visual design system once and generate the canonical token sheet every com-* artefact consumes. Adapts Anthropic's brand-guidelines pattern (a design system as a shared, on-demand resource) kept domain-agnostic: scaffolds a fillable design-system.md (brand rationale + token tables for palette, typography, spacing, and semantic tokens) and generates docs/ux/tokens.css, a :root variable contract. com-slide-deck and com-artefact-viz reference these via var() and never hard-code colour/font/radius, so editing the design system re-themes every deck and view with no renderer change. Modes: scaffold, generate/refresh. Use when the user wants to define a design system, brand tokens, theme, colour palette, typography, or shared visual style for generated decks and visualisations. Triggers on: design system, design tokens, brand guidelines, theme, colour palette, typography tokens, tokens.css. Output: docs/ux/. Mints no IDs; cross-cutting foundation for the presentation layer.
domain-glossary
by VictorHueniCreate and maintain the Ubiquitous Language glossary — the shared vocabulary between domain experts and developers scoped per bounded context. Each term has a stable GT-NN ID, canonical definition, examples, deprecated aliases, cross-context translations, and code convention note. Synthesises Evans Domain-Driven Design (2003) Chapter 2 + Vernon DDD Distilled (2016) Chapter 2 + Martin Fowler ubiquitous language pattern. Use when asked to define domain vocabulary, create a glossary, document ubiquitous language, deprecate synonyms, manage domain terms, or align terminology between business and engineering. Triggers on: ubiquitous language, domain glossary, domain vocabulary, shared language, term definition, domain terms, DDD glossary, terminology alignment, domain dictionary, term deprecation, glossary management. Output: docs/domain/02c-glossary.md. Scoped to bounded contexts (BC-NN from domain-bounded-context).
util-toolkit-doctor
by VictorHueniAudit and repair the Claude Code setup health — chezmoi state, dotfiles + homemade-claude-kit repo sync, and ~/.claude/ symlink integrity. Auto-fixes safe drift but stops on uncommitted local changes. Use when the user asks to check, audit, sync, repair, doctor, or initialize their Claude setup, dotfiles, kit repo, skills, or commands installation.
business-capability-map
by VictorHueniCreate a strategic business capability map (L0 + L1, optionally L2) using the canonical synthesis of TOGAF G189 + Cutter Rosetta Stone + SAP Business Architecture + BABOK. Use when the user asks to build a capability map, define business capabilities, model the WHAT-the-business-does layer, scaffold an enterprise / product capability tree, or prepare a business-IT alignment artefact. Triggers on: business capability map, capability map, BC map, BCM, define capabilities for, what does {product} do, strategic capabilities, TOGAF capability map, capability decomposition, L0 L1 capabilities. Domain-agnostic; works for any product, service, or enterprise scope. Stays strategic — does NOT decompose to features / functionality (that belongs in an FBS).
dev-git-init
by VictorHueniScaffold the deterministic git enforcement stack for a Node or Python project — husky/pre-commit hooks, commitlint/commitizen with Conventional Commits, gitleaks, .gitignore + .gitattributes + .editorconfig, CONTRIBUTING.md, GitHub PR template + CODEOWNERS + 3 issue templates, CI workflows, scripts/setup-branch-protection.sh. Two modes: audit (read-only) and scaffold (3-question Q&A: stack · branching strategy · reviewer model). Uniformly skip-if-exists. Emits install + branch-protection commands; never executes them. Post-scaffold prompt asks whether to record decisions as an ADR via arch-adr. Triggers on: scaffold git, git init, set up git hooks, install husky, install commitlint, install commitizen, install pre-commit, set up commit conventions, set up PR template, set up CODEOWNERS, branch protection, git workflow setup, dev workflow setup, repo conventions, scaffold contributing.
arch-service-contract
by VictorHueniDefine the external interface contract for a bounded context or a product-level API — REST resources, async events published, and commands consumed. BC-scoped (one artefact per BC-NN, ID: BC-NN.CTR-NN) or product-level spanning multiple BCs (ID: CTR-NN). Placed after the domain model (Step 7c). Derives contracts from BC-NN.AGG-NN, BC-NN.ENT-NN, BC-NN.EVT-NN. Modes: scaffold, contract-first (design from domain model outward), document-existing (reverse-engineer from code), refresh (detect drift + emit deprecation notices). Use when asked to define an API, design the interface surface, document HTTP endpoints, define event schemas, or formalise the public contract of a service. Triggers on: API design, REST API, interface contract, endpoint design, event schema, async surface, public API, service contract, HTTP API, interface surface, API surface. Output: docs/architecture/interfaces/{bc-slug}.md (BC-scoped) or docs/architecture/interfaces/{slug}.md (product-level).
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.