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...
bytedance-seed-20
by BoomerAng9ByteDance Seed 2.0 Full Ecosystem skill for multi-modal AI routing. Use when: routing tasks to budget frontier LLMs, generating video/audio, selecting cost-effective models, or integrating Volcano Engine APIs.
kimi-k25
by BoomerAng9Kimi K2.5 Visual Agentic Model routing and configuration. Use when: a task requires visual reasoning, video input processing, multimodal agent orchestration, or deploying Moonshot AI's 1T-parameter agentic model for swarm tasks.
glm-5
by BoomerAng9GLM-5 Z.ai Frontier Model routing and configuration. Use when: a task needs budget-friendly frontier reasoning, MIT-licensed model output, agentic engineering, or cost-effective high-quality inference via OpenRouter.
gemini-31-pro
by BoomerAng9Gemini 3.1 Pro model routing and configuration. Use when: a task requires Gemini 3.1 Pro capabilities — deep reasoning, long-context analysis, code generation, or multimodal understanding — and the agent needs to select the correct thinking level and feature flags.
fdh-pipeline
by BoomerAng9FDH Pipeline (Foster/Develop/Hone) skill for driving work to completion. Use when: starting new projects, executing multi-phase development work, running ORACLE verification gates, or tracking pipeline state.
brave-search
by BoomerAng9Brave Search Pro AI — primary web search for all A.I.M.S. agents. Use when: search, web search, find online, look up, research.
claude-46
by BoomerAng9Claude Opus 4.6 and Sonnet 4.6 — Anthropic's frontier models with adaptive thinking, 1M context, agent teams, fast mode, and computer use. Use when: claude, opus, sonnet, adaptive thinking, agent teams, fast mode, computer use, claude code.
roo
by BoomerAng9Roo — Tier 2 ephemeral, vertical-pinned to Coastal Brewing Co. Loss Prevention floor team. Engages when a customer conversation has stalled past Sal's negotiation budget. Scripted interceptor (zero LLM tokens during LP states). Three-step assist (family → specifics → close). Above-ceiling routes to ACHEEVY. Transferable to Cyber Hawks (monitoring + incident-response) for cross-domain operational work.
bar-ang
by BoomerAng9Tate / Bar_Ang — Tier 2 vertical-pinned to Coastal Brewing Co. BREW Crew — pour-over master, syllable-timed pace. Charleston coastal heritage. Voice via Inworld TTS-2 (BREW-team voice canon). Customer-facing on the brewing.foai.cloud chat surface for pour-over guidance. Discount cap deferred to Sal; Bar_Ang focuses on craft + recipe.
peterson-negotiation-doctrine
by BoomerAng9Joel Peterson's negotiation doctrine for The Sett. Use whenever a Badger (Melli, Persona_Tah, Eve_Retti, Leu_Kurus) enters a B2B vertical deal, encounters counterparty manipulation, faces a HAVE-TO-HAVE-THE-DEAL pressure cooker, designs a Lock-the-Bracket template, builds rules of the road with a serial partner, or assesses brand drift across deal cycles. Surfaces eight load-bearing Peterson principles (Rule One, no-episodic-negotiations, solve-for-fairness, right-person-CCP, two-sided-BATNA, elephants-vs-ants, ineffective-tactics-defense, deliberate-brand-building) with verbatim source citations to the 2007 Stanford lecture and the 2026 posthumous tweet that surfaced it.
boomer-cfo
by BoomerAng9Boomer_CFO — Tier 2 with elevated permissions. Financial authority across FOAI verticals. Owns canonical pricing math, margin-floor canon, cost-envelope budgets per surface, AIMS gateway cost meter, supplier-payment ledger. LUC reports to Boomer_CFO for cross-vertical financial canon (LUC stays Coastal-vertical for floor accounting). Final financial sign-off pairs with ACHEEVY for any margin-floor exception.
sme-n8n-transition
by BoomerAng9Use when Chicken Hawk needs to inventory, replace, or refuse legacy n8n workflows and route the automation to SimStudio, OpenClaw cron, or another runtime instead
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.