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
by dsteven12Generate a structured review of work done over a given time period by sweeping connected sources (Slack, Gmail, Google Calendar, Airtable, Obsidian vault) and producing a markdown note in the Work Brain vault. Supports daily, weekly, monthly, quarterly, and yearly cadences. Use when the user asks to look back at or summarize work — phrases like 'daily review', 'weekly review', 'what did I do today', 'what did I accomplish', 'recap my week', 'summarize my day', 'EOD review'. Do NOT use for ending the current session — that is session-wrapup.
ai-prompt-builder
by dsteven12Generate production-ready AI prompts for Airtable AI features — both Automation AI actions (Generate Text, Generate Structured Data, Generate Images) and Field Agents (Deep Match, Build Prototype, Generate Image, Research Companies, Analyze Attachment, Find Image from Web, custom agents). Use when writing prompts for any Airtable AI action or agent, converting task descriptions into prompt content, or optimizing existing prompts. MANDATORY TRIGGERS: AI prompt, write the prompt, generate prompt, prompt for this step, AI action prompt, structured data prompt, field agent prompt, deep match prompt, build prototype prompt, generate image prompt, agent instructions, prompt engineering for Airtable. ALWAYS invoke when an automation spec includes AI actions, a field agent needs instructions, or the user needs actual prompt content. Also invoke proactively when automation-architect produces a spec with AI steps or when configuring field agents on a new base.
health-check
by dsteven12Generate a scalability and risk assessment document (.docx) for any Airtable base. MANDATORY TRIGGERS: health check, risk assessment, scalability, base audit, production readiness, pre-production, system health, scaling concerns, performance issues, is this ready, check this base. ALWAYS invoke this skill when evaluating an Airtable base for risks, scaling concerns, or production readiness — even if the user just says 'check this base' or 'is this ready for production.' Inspects the live base via Airtable MCP and outputs a branded Word document with severity matrices, risk analysis, automation architecture review, and a prioritized readiness checklist.
solution-hub
by dsteven12Populate an Airtable Solution Hub base from engagement transcripts, meeting notes, SOWs, or architecture docs. Extracts structured records across 10 areas (Project, People, Timeline, Definitions, PBOs, Risks, Decisions, User Personas, Updates, Action Items), presents for review, then writes via MCP. MANDATORY TRIGGERS: solution hub, populate solution hub, populate the hub, extract from transcript, hub population, fill in the solution hub, update the solution hub, add to solution hub, sync to hub, log this call, process this transcript. ALWAYS invoke when the user provides a transcript, notes, SOW, or engagement input and wants extracted data written to a Solution Hub base — even if they just say 'here's the transcript' or 'log this to the hub'. Also invoke to review or update existing Hub records from new information. Do NOT invoke for schema design (airtable-design-advisor) or workflow documents (workflow-doc).
schedule
by dsteven12Create a reusable, scheduled shortcut from the current session. Use when the user explicitly wants to make work repeatable or time-triggered — phrases like 'schedule this', 'run every day', 'automate this', 'remind me', 'every Monday', 'every morning', 'at 9am', 'save as task', 'run on demand', 'do this again tomorrow'. Do NOT trigger on general mentions of scheduling or calendars — those are calendar operations, not task scheduling.
learning-loop
by dsteven12Two-mode skill for kinesthetic learning acceleration. BRIEF mode (session start): reads the project note and sets high-level learning objectives — 'here's what you're going to learn today' — anchored to the target patterns for the current use case. REFLECT mode (session end): extracts granular discoveries from the session, maps them back to the core learning themes, identifies platform constraints and skill gaps, and proposes concrete skill adaptations. MANDATORY TRIGGERS: brief me, what am I learning today, learning objectives, learning briefing, retro, retrospective, what did I learn, lesson extractor, skill adaptations, what did we discover, learning review, reflect on this session. ALWAYS invoke when starting or ending a learning-type engagement session — even if the user just says 'let's start UC2' (brief) or 'what did we learn' (reflect).
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.