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...
context-modes
by bendourtheSwitch the agent's working posture by adopting a named mode (dev, review, research) that retunes priorities, tool preferences, and stopping conditions. Make sure to use this skill whenever the user says "switch to dev mode", "switch to review mode", "switch to research mode", "enter review posture", "act as a reviewer", "we are researching", "research mode", "code-first mode", or otherwise asks the agent to behave like a different specialist for the rest of the session, even when the word "mode" is not used. Also trigger when the user pivots from one phase of work to another (e.g., from designing to reviewing, or from researching to implementing) and the prior posture would now be wrong. SKIP, do NOT use for, one-off tone changes, single-message rephrasing requests, persona role-plays unrelated to engineering work, or selecting between competing implementation approaches (use plan-before-code for that).
google-antigravity-sdk
by bendourtheDesign, implement, and debug autonomous AI agents using the Google Antigravity SDK -- the async agent loop, declarative tool-call policies, lifecycle hooks, MCP integration, multimodal ingestion, triggers, subagents, and Pydantic structured output. Make sure to use this skill whenever the user mentions the Google Antigravity SDK, AGY SDK, antigravity SDK, a Gemini agent loop, an antigravity agent, LocalAgentConfig, Conversation, or ConnectionStrategy, even if they do not say the word "agent" explicitly. SKIP, do NOT use for, a standalone Gemini API client with no agent loop (use multi-provider-ai or claude-api instead), one-off Gemini text-completion calls, or Antigravity CLI install / configuration work (that is owned by the Antigravity20Integration installer path, not this skill).
context-optimization
by bendourtheOptimize AI coding session context window usage by compressing command output, minimizing verbose logs, and avoiding context bloat. Use when sessions are hitting token limits, commands produce excessive output, you want to maximize effective session length, or you notice the context window filling up quickly. Covers the internal nexus-context-compressor engine for Claude Code and prompt-level output reduction for Gemini, Codex, and Copilot.
bug-localization
by bendourthePinpoint bug locations using stack traces, error logs, code flow analysis, spectrum-based fault localization, and bisection techniques. Use when debugging failures, analyzing stack traces, tracing error origins, or narrowing down faulty code regions.
docstrings
by bendourtheGenerate comprehensive function, class, and module docstrings following language conventions (JSDoc, PyDoc, JavaDoc, XML docs, godoc, Doxygen). Use when documenting APIs, adding inline documentation, improving code discoverability, or generating API reference documentation.
internal-comms
by bendourtheDraft structured internal communications using six named templates - 3P Update (Progress / Plans / Problems), Weekly Status Report, Leadership Update, Company FAQ entry, Incident Report, Project Update. Use whenever the user asks to write a status update, weekly summary, leadership briefing, exec brief, FAQ, post-mortem, incident write-up, project update, one-pager, or any internal-audience message that needs structure to land. The skill always picks the right template before drafting and resists the urge to free-form. SKIP: external-audience marketing copy (use writing-editing), long-form decision docs / RFCs / ADRs (use doc-coauthoring), single-paragraph Slack messages, or commit messages.
creative-generation
by bendourtheCreative direction for image prompts, presentation slides, and ideation. Use when asked to generate image prompts, design slide decks, brainstorm ideas, create visual concepts, or produce creative content.
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.