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...
i18n-translate
by MiragonTranslate Camunda Modeler i18n plugin keys into a target language, using the German translation as the authoritative base. Use this skill whenever the user wants to add a new language, translate keys, fill in missing translations for an existing language, or update/complete a partial translation in the camunda-modeler-i18n-plugin repository. Also trigger when the user mentions locale codes, language names, or talks about translating the modeler UI.
bpmn-browser-testing
by MiragonInteract with the BPMN modeler webview running in a browser using Playwright MCP tools. Use this skill whenever the user asks to test, inspect, or interact with the BPMN modeler in a browser — including adding/modifying BPMN elements, checking the properties panel, verifying UI behavior, or debugging the webview. Also trigger when the user mentions "open the modeler in a browser", "add a task/event/gateway", "check the properties panel", or any visual/interactive testing of the BPMN webview.
bpmn-js
by Miragonbpmn-js modeler internals — EventBus, services, copy-paste architecture, clipboard polyfill, modeler lifecycle. Use when working on bpmn-webview, diagram interactions, copy-paste, clipboard, or element templates.
architecture
by MiragonInternal architecture of the modeler-plugin extension host (Node.js) — feature-folder layout with a four-layer split (domain, infrastructure, service, controller) inside each feature, host-capability ports + hexagonal engine ports, deployment subsystem (Camunda 7 & 8), per-feature register() composition root, WebviewMessageRouter dispatch, EditorSessionParticipant lifecycle, EditorSessionStore + VsCodeEditorHandle, echo-prevention session guards, webview message protocol (Query/Command), and the ArchUnitTS architecture tests. Use this skill when working on extension-host code — implementing features, fixing bugs, reviewing PRs, refactoring services, adding message types, understanding editor tracking, tracing webview message flow, integrating external systems, or modifying feature wiring. See also bpmn-js, vscode-webviews, vscode-custom-editors, and vscode-ux-guidelines for adjacent concerns.
i18n-translate
by MiragonAdd or complete translations for the BPMN/DMN modeler UI in the miranum-ide project. Use this skill whenever the user wants to add a new language, translate missing keys for an existing locale, update translations, or register a new locale in the i18n system. Also trigger when the user mentions locale codes, language names, or talks about translating modeler UI strings in this repository.
vscode-custom-editors
by MiragonVS Code CustomTextEditorProvider pattern — registration, document sync, lifecycle, disposables, the generic ModelerEditorController + EditorSessionParticipant pattern, BPMN/DMN differences. Use this skill whenever working on the editor controller, document synchronization, CustomTextEditorProvider, webview lifecycle, editor registration, resolveCustomTextEditor, EditorSessionStore, session participants, or understanding how BPMN/DMN files are opened and edited. Also consult this skill when debugging issues with editor state, hidden webviews, tab switching, or disposable cleanup — even if the user doesn't mention "custom editors" explicitly.
vscode-webviews
by MiragonVS Code webview internals — HTML serving, CSP, postMessage protocol, state persistence, theming. Use when working on webview HTML, postMessage, CSP, theme handling, vscode.getState/setState, acquireVsCodeApi, webview.asWebviewUri, retainContextWhenHidden, nonce generation, content security policy, or the Query/Command message protocol between extension host and webview.
vscode-ux-guidelines
by MiragonVS Code UX guidelines for this project — how to choose between notifications, status bar, quick picks, and output channels; how clipboard access works between sandboxed webviews and the extension host; webview theming; accessibility; and setContext for keybinding visibility. Use this skill whenever you are adding user-facing feedback (messages, errors, progress), wiring clipboard in webviews, implementing copy/paste, choosing how to surface information to the user, adding keyboard shortcuts or when-clause visibility, working on theming, or considering accessibility. Also use when deciding between notification types or between notifications vs. status bar vs. output channel.
new-slide
by MiragonAdd a new slide to an existing chapter
mcp-apps-builder
by Miragon**MANDATORY for ALL MCP server work** - mcp-use framework best practices and patterns. **READ THIS FIRST** before any MCP server work, including: - Creating new MCP servers - Modifying existing MCP servers (adding/updating tools, resources, prompts, widgets) - Debugging MCP server issues or errors - Reviewing MCP server code for quality, security, or performance - Answering questions about MCP development or mcp-use patterns - Making ANY changes to server.tool(), server.resource(), server.prompt(), or widgets This skill contains critical architecture decisions, security patterns, and common pitfalls. Always consult the relevant reference files BEFORE implementing MCP features.
mcp-builder
by MiragonDEPRECATED: This skill has been replaced by `mcp-app-builder`. Check if `mcp-app-builder` is available in the skills folder. If not, install it: `npx skills install mcp-use/mcp-use --skill mcp-app-builder` Use `mcp-app-builder` instead of this skill. Build Model Context Protocol (MCP) servers with mcp-use framework. Use when creating MCP servers, defining tools/resources/prompts, working with mcp-use, bootstrapping MCP projects, or when user mentions MCP development, tools, resources, or prompts.
angebot-lv
by MiragonErstellt Angebote in Lexware Office (Lexoffice) aus einem hochgeladenen LV (PDF). Daraus wird eine strukturierte Excel (Claude Desktop/Code) bzw. ein editierbares Live-Artefakt (Cowork), das per Knopfdruck zum Lexoffice-Angebot wird. Triggert bei "hier ist das LV", "kalkulier mir das LV", "Excel zum LV", "Angebot aus LV", oder wenn ein PDF mit "LV", "Leistungsverzeichnis" oder "Ausschreibung" hochgeladen wird. NICHT für: einfache Angebote ohne LV (→ lexoffice:angebot), Rechnungen aus Dimacon-Jobs (→ dimacon:abrechnung), Angebote aus Dimacon-Planungs-URLs (→ dimacon:lexware), Aufträge planen (→ dimacon:planung).
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.