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...
agent-environment-optimizer
by m2ai-portfolioAudit an agent's execution environment for cold-start patterns, missing warm caches, stale dependencies, and session persistence gaps. Scores against best practices from OpenAI Hosted Shell and METR research showing unoptimized environments negate AI productivity gains. Use when the user says "optimize agent environment", "cold start audit", "agent environment check", "why is my agent slow to start", "warm cache audit", "session persistence check", or wants to speed up agent execution by fixing the environment layer.
seedance-prompt
by m2ai-portfolioMaster AI Video Prompt Engineer for Seedance 2.0. Use when converting a user concept into a high-quality, cinematic Seedance 2.0 video prompt structured by the FRAMES framework (Frame, Reaction, Audio, Mood, Edit Plan, Shot). Trigger on "seedance prompt", "generate a seedance prompt", "convert this idea into a seedance prompt", "extend this video", or any request to turn an idea into a structured Seedance 2.0 prompt. Supports multi-shot timelines (0-14s) and video extensions via the @video1 syntax.
seedance-shot-prompt
by m2ai-portfolioUse when generating a Seedance 2 video prompt for a linear forward-motion shot — transitions, chase shots, establishing shots, A→B narrative clips. Trigger when the user asks for a "shot prompt", "transition shot", "video shot", "cinematic shot", "forward motion video", "A to B shot", "linear video generation", "narrative video clip", or describes a shot with a starting state and a different ending state. NOT for loops or backgrounds — for those use seedance-loop-prompt instead. Includes a 3-stage smoke-test protocol for identity-bound shots and a named taxonomy of 8 known failure modes (api_xor_constraint, identity_drift, motion_reversal, boomerang_interpolation, no_motion_reference_only, hallucination, text_garbling, input_stacking_ineffective) drawn from a 2026-04 production AAR.
spec-gap-detector
by m2ai-portfolioStress-test any agent prompt or specification for ambiguity, missing constraints, and edge cases that would cause random behavior at scale.
pre-turn-budget-guardian
by m2ai-portfolioEnforce a token budget ceiling on Claude Code sessions by checking projected usage BEFORE each turn and halting with a structured stop reason if the budget would be exceeded. Prevents runaway loops and silent token burn. Completes the token management trilogy alongside boot-tax-monitor (measures startup) and token-burn-auditor (measures waste).
self-healing-claudex
by m2ai-portfolioSelf-healing build pipeline with Planner/Builder + Codex adversarial review. Planner writes a test contract, Builder implements until tests pass, Codex pressure-tests the implementation with a different reviewer persona each round (engineer / security / ops), Builder revises, repeat until Codex agrees or max rounds reached. File-based state survives session interrupts. Use when the user says "self-healing claudex", "claudex build", "PBJ with codex review", "two-vendor build loop", or wants Codex (not just Claude) as a second set of eyes on a build. Sibling to /self-healing-pipeline (which uses an all-Claude Judge); this one swaps the Judge for real second-vendor adversarial review.
sensemaking-concentrator
by m2ai-portfolioAudit a multi-agent system for distributed sensemaking anti-patterns and recommend where to concentrate interpretation into a single agent, reducing conflicting signals and improving decision quality.
simulated-work-detector
by m2ai-portfolioRecurring audit that reviews agent fleet output and flags simulated work that generated artifacts but didn't close any loops or remove work from your plate
skill-maintenance
by m2ai-portfolioAudit Claude Code skills for content quality against Anthropic best practices. Use when Forge runs maintenance cycles, when the user asks to check skill quality, or when reviewing skills before publishing.
structured-elicitation
by m2ai-portfolioA conversational skill that interviews the user across five layers of operational knowledge -- operating rhythms, recurring decisions, dependencies, institutional knowledge, and friction -- with checkpoint approvals between each layer. Generates agent config artifacts (SOUL.md, USER.md, HEARTBEAT.md, operating-model.json, schedule-recommendations.json). Use when the user says "elicitation", "interview me", "extract my workflows", "bootstrap agent persona", "build my SOUL.md", "help me document what I do", or when onboarding a new agent that needs to understand a human's work patterns.
tldr
by m2ai-portfolioSave a summary of this conversation to the vault. Key decisions, things to remember, next actions. Store in the right folder automatically.
token-burn-auditor
by m2ai-portfolioAudit the live Claude Code environment for token waste -- measures per-session overhead, flags system prompt bloat, checks plugin/skill loading totals, and gives before/after deltas when changes are made. Real-time linter for AI workflows.
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.