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...
review-slide-visual
by kzarzyckiVisually review a PowerPoint slide for layout issues, spacing problems, contrast errors, and alignment inconsistencies. Spawns an independent reviewer with no conversation context. Use after completing slide edits to verify visual quality — not for initial inspection. Trigger on "review the slide", "how does it look", "check the visual", "verify the layout", or proactively after slide editing is complete.
powerpoint-mcp
by kzarzyckiManipulate live, open PowerPoint presentations on macOS via Office.js MCP server. Use when Claude needs to: (1) create, edit, or inspect slides in a running PowerPoint instance, (2) add shapes, text, tables, or formatting to live presentations, (3) capture visual slide screenshots, (4) enable/configure the PowerPoint MCP server in a project, (5) execute Office.js code against open presentations. Distinct from the pptx file-editing skill — this works on presentations currently open in PowerPoint.
gemini-deep-research
by kzarzyckiPlatform knowledge for Gemini Deep Research at gemini.google.com. Standalone: spawns browser-researcher agent. Or loaded by browser-researcher at runtime via skill_path. Trigger on "gemini deep research", "use gemini to research", "run deep research on gemini", "google deep research", or when explicitly requesting Gemini's native deep research capability.
deep-research
by kzarzyckiOrchestrate multi-round, multi-source deep research using parallel agents and multiple search providers (Perplexity, Tavily, Exa, Gemini, native WebSearch). Produces comprehensive reports with citations, confidence scores, and identified gaps. Use this skill whenever the user wants thorough, multi-angle research on any topic — trigger on "deep research", "research this thoroughly", "comprehensive analysis of", "what does the internet say about", "gather everything about", "investigate X in depth", "multi-source research", "find all recent info on", or any request implying broad internet research beyond a simple search. Also trigger when the user needs cited research for a presentation, report, or decision, wants to compare sources, triangulate information, or needs source quality assessment. Even casual requests like "look into X for me" or "what's the latest on X" should trigger this if the topic is complex enough to benefit from structured multi-source research.
product-discovery
by kzarzyckiStructured grilling to clarify a vague product/feature need before any implementation. Invoke only on /product-discovery. Produces a discovery log + the artifact the user requests (PRD, RFC, design note, message, or just chat clarity).
find-conversation
by kzarzyckiSearch through past Claude Code conversations to find specific sessions by topic, content, date, or working directory. Use when the user asks to find a previous conversation, recall what was discussed, locate a session they worked on, or resume past work. Trigger on "find that conversation", "which session did we", "we talked about X before", "find the session where", "I was working on X yesterday", "resume that conversation", "open that session", or any reference to past Claude Code conversations.
autopilot
by kzarzyckiAutonomous brainstorm→PR pipeline. Invoke on /autopilot. Runs an interactive brainstorming session to an approved spec, then launches a background Workflow that plans, builds, reviews, verifies, and opens a PR with no further human input. Resumes a halted run when re-invoked.
communicating-in-html
by kzarzyckiOptional enrichment layer. When loaded, the agent communicates with the user in self-contained HTML instead of Markdown wherever a rendered page beats a chat dump — reports, interviews/intake, and option/mockup choices. Orthogonal and zero-coupling: other skills keep working in plain Markdown when this isn't loaded. Fires when you are about to deliver a report / summary / analysis / dashboard / scorecard, interview the user for more than ~3 fields, or offer options / mockups to choose from — and the content has comparison, layout, interaction, color/charts, or would exceed ~100 lines of Markdown. Output is one offline-safe .html file; forms and option pages hand answers back via a copy-paste token. Trigger on "report", "write it up nicely", "dashboard", "summarize visually", "interview me", "intake form", "gather requirements", "show me options", "mockups to choose from", "as HTML", "nicer than chat".
tech-options
by kzarzyckiUse when approved needs require comparing implementation approaches before planning.
workflow
by kzarzyckiUse when the user wants to run a work item through the workflow engine, e.g. "/workflow <prompt>", "start a workflow for ...", or "run the workflow engine on ...".
flow
by kzarzyckiDEPRECATED — do not activate. Superseded by the workflow engine skill (workflow:workflow) and the OMP workflow core. Kept for historical reference only; the .work/ directory convention it describes is obsolete.
chatgpt-deep-research
by kzarzyckiPlatform knowledge for ChatGPT Deep Research at chatgpt.com. Standalone: spawns browser-researcher agent. Or loaded by browser-researcher at runtime via skill_path. Trigger on "chatgpt deep research", "run this through ChatGPT", "ask ChatGPT to research", "delegate to ChatGPT deep research", "use ChatGPT for this research". Does NOT trigger on generic "deep research".
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.