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...
ai-risk-mapper
by totallyGregThis skill should be used when identifying, analyzing, and mitigating security risks in Artificial Intelligence systems using the CoSAI (Coalition for Secure AI) Risk Map framework. Use when users ask to "assess AI security risks", "analyze AI system threats", "map risks to controls", "run a risk assessment", "check compliance with MITRE ATLAS", "generate a CoSAI report", or "profile persona risks". Supports LLM applications, ML pipelines, model training/serving infrastructure, and compliance reporting aligned with MITRE ATLAS, NIST AI RMF, OWASP Top 10 for LLM, STRIDE, and ISO 22989 frameworks. Do NOT use for general software security scanning without an AI/ML component (use standard SAST/DAST tools instead).
kgateway
by totallyGregThis skill should be used when configuring kgateway (Kubernetes Gateway API implementation) for HTTP routing, Gateway resources, HTTPRoutes, and GatewayClass configuration. Use when the user asks to "create a Gateway resource", "configure HTTPRoute", "set up path-based routing", "check kgateway installation", "install kgateway", "upgrade kgateway helm chart", or "troubleshoot route attachment". Covers Gateway API standards, kgateway Backend CRD, and Envoy-based control plane on Kubernetes.
slack-toolkit
by totallyGregUse this skill when the Slack MCP server is not connected, when you need Canvas read/update operations, when you need to add/remove reactions, or when direct Slack API access is explicitly requested. Triggers on "read slack canvas", "update slack canvas", "create slack canvas", "rewrite slack canvas", "add slack reaction", "remove slack reaction", "get slack thread", "slack channel history", "parse slack url", "slack without mcp", "slack api curl". Do NOT use for channel/message operations when the Slack MCP server is available — use the official MCP plugin instead.
tui-experience
by totallyGregThis skill should be used when the user asks to "theme lazygit", "configure k9s skin", "set up fzf preview", "create a television channel", "configure tv channel", "customize btop theme", "configure gum prompt", "style glow markdown", "record a terminal session", "play asciinema cast", "convert asciinema to gif", "convert asciinema to svg", "convert cast to mp4", "render terminal recording with vhs", "share asciinema recording", or needs help with TUI application theming/keybindings/quirks (fzf, television/tv, gum, btop, lazygit, k9s, glow, charm) or terminal session recording (asciinema, agg, vhs, svg-term-cli). Do NOT use for the underlying color protocol (ANSI/256/truecolor) — use terminal-emulation. Do NOT use for tmux automation — use tmux-dev. Do NOT use for shell-level fzf composition pipelines — use environment-composition.
agentsmith
by totallyGregThis skill should be used when users ask to "evaluate my agent", "improve agent quality", "agent metrics", "check agent description", "agent isn't triggering", "validate agent", "agent score", "as-evaluate", "as-improve", "agent quality", "fix agent description", or "why isn't my agent triggering". Provides agent quality evaluation with 3 scored dimensions and an improvement loop that orchestrates skillsmith and marketplace-manager. Do NOT use for skill evaluation — route to skillsmith instead. Do NOT use for agent creation — route to plugin-dev:agent-development instead.
zsh-dev
by totallyGregThis skill should be used when the user asks to "create a zsh function", "configure fpath", "add a keychain secret", "set up keychainctl", "check shell startup", or needs help with autoload functions, completions, zsh testing, Plugin Standard compliance, storing tokens, retrieving secrets, or macOS keychain management via keychainctl. Do NOT use for terminal display issues or signal handling (use terminal-emulation or signals-monitoring skills instead).
agentgateway
by totallyGregThis skill should be used when configuring agentgateway for AI/LLM provider routing, MCP server routing, external processing, and traffic policies. Use when the user asks to "add an LLM provider backend", "configure MCP routing", "set up Ollama backend", "add OpenAI backend", "configure Anthropic", "add Vertex AI backend", "set up rate limiting", "configure CORS", "add external processing", "upgrade agentgateway", or "troubleshoot AI routing". Supports Ollama, OpenAI, Anthropic, Gemini, Vertex AI, Azure OpenAI, and Bedrock backends.
attache-analyst
by totallyGregThis skill should be used when analyzing OmniFocus system structure, discovering workflow patterns, running AI-enhanced GTD coaching, or learning the user's tool stack. Triggers when user asks "analyze my OmniFocus", "discover my system", "what's my structure", "AI coaching", "project health analysis", "system insights", "learn my workflow", "understand my patterns", "suggest improvements", "what tools do I use", or "update my tool stack". Do NOT trigger for: "show tasks" or "check inbox" (use omnifocus-core), "create OmniFocus plugin" (use omnifocus-generator), "what makes a good next action" (use gtd-coach for pure methodology). This skill is read-only against OmniFocus. It discovers patterns, infers structure, and persists learned insights via the Attache preferenceManager. It can read and update vault tool notes (status, usage patterns) via the archivist agent.
gtd-coach
by totallyGregThis skill should be used when users need GTD methodology coaching on productivity, workflow, or task management systems. Triggers when user asks "create a next action", "check my GTD system", "analyze my projects", "improve my workflow", "weekly review", "inbox zero", "someday maybe", or "GTD coaching". For OmniFocus-specific automation, use the omnifocus-core skill instead.
wtf
by totallyGregThis skill should be used PROACTIVELY to "create a friction report", "check for broken tooling", or "run a friction check" when you hit confusing errors, bad docs, missing prereqs, broken tools, misleading skills, flaky tests, auth/MCP failures, or any "this should've been easier" moment. Also trigger when the user says "file an issue", "report this friction", "log this feedback", "wtf", or "this should be easier". Do NOT use for fixing the friction itself (use skillsmith or agentsmith instead).
terminal-emulation
by totallyGregThis skill should be used when the user asks to "fix terminal colors", "configure $TERM", "debug terminfo", "set up truecolor", "test 256 color support", "fix unicode rendering", "fix garbled characters", "fix broken box drawing", "fix emoji rendering", "configure locale", "fix SSH terminal", "check $COLORTERM", "apply ANSI escape codes", "set up base16 theme", or needs help with the Unix terminal substrate — `$TERM`, terminfo database, ANSI escape codes, color tiers (16/256/truecolor), `$COLORTERM`, Unicode/UTF-8 rendering, locale configuration, and SSH terminal setup. Do NOT use for tmux automation (sessions, options, plugins, send-keys) — use tmux-dev. Do NOT use for TUI app theming (lazygit/k9s themes) — use tui-experience. Do NOT use for shell config — use zsh-dev.
therapist-practice-operations
by totallyGregThis skill should be used when the user asks to "help me with taxes", "organize my expenses", "plan estimated tax payments", "renew my license", "track my continuing education hours", "what are my compliance deadlines", "set up tax tracking", "compare licensing requirements", or mentions managing sole proprietor business operations, taxes, and licensing for mental health therapists.
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.