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...
terminal
by DojoCodingLabsCommand line, npm, git, and shell basics. Activated when Claude runs Bash commands. Demystifies the terminal for non-technical users.
fundamentals
by DojoCodingLabsCore programming concepts: variables, functions, conditionals, loops, and data types. Activated when Claude writes basic code structures. Provides teaching context for CodeSensei explanations at the foundational level.
premortem
by DojoCodingLabsRun a premortem on any plan, launch, product, hire, strategy, or decision. Assumes it already failed 6 months from now and works backward to find every reason why. Produces a revised plan with blind spots exposed. MANDATORY TRIGGERS: "premortem this", "premortem my", "run a premortem", "what could kill this", "future-proof this", "stress test this plan", "what am i missing here", "find the blind spots". STRONG TRIGGERS: "what could go wrong", "am i missing anything", "poke holes in this", "where will this break", "devil's advocate this". Do NOT trigger on simple feedback requests, factual questions, or LLM Council requests. DO trigger when someone has a plan or commitment where the cost of being wrong is high.
review-open-prs
by DojoCodingLabsCross-references open PRs across all repos in the current org with Linear issues, checks Greptile review scores, forces mergeable calculation, and generates an actionable report with merge/rebase/fix recommendations. Use when the user asks "show me open PRs", "what PRs need attention", "review PRs", "check Greptile scores", "what's ready to merge", or wants a comprehensive PR status overview. Do NOT trigger for: creating PRs, code review, or single PR inspection.
design-system-analyzer
by DojoCodingLabsAuto-activates when the user discusses design system gap analysis, component catalogs, or cross-referencing their Flutter project against a design system. Triggers on: "design system gap", "component catalog", "what components am I missing", "Material 3 components", "cross-reference design system", "compare against Carbon", "what widgets does Primer have that I don't", "design token audit". Do NOT trigger for: generating specific feature widgets (use /generate command), or general Flutter development questions.
three-horizons
by DojoCodingLabsClassifies a portfolio of ventures into Three Horizons (H1/H2/H3) from Lean Enterprise (Humble/Molesky/O'Reilly, 2015) cap. 2, and recommends resource allocation across horizons (classic 70/20/10 by Google, or studio-specific). Use when the user asks "three horizons", "portfolio allocation", "H1 H2 H3", "cómo asigno recursos entre ventures", "70/20/10", "studio portfolio balance", "/three-horizons", or has a multi-venture portfolio and needs to decide where to invest time/money. Complementary to explore-exploit categorization and cost-of-delay-cd3 prioritization.
services-hub-setup
by DojoCodingLabsSets up a "Services Hub Model" — a central Services LLC that contracts bilateral MSAs with each independent Venture LLC in a multi-venture portfolio. Middle ground between serial-entrepreneur-with-Multi-LLCs and formal-venture-studio-with-holding. Generates MSA template + SOW template + transfer pricing methodology + IP assignment rider + billing calendar. Use when the user asks "services hub", "MSA template", "shared services setup", "central services entity", "transfer pricing methodology", "/services-hub-setup", or has chosen Services Hub pattern (patrón #6) via structure-decision skill. STRONG LEGAL DISCLAIMER — MSAs are legal contracts that require lawyer review.
when-to-become-studio
by DojoCodingLabsHelps a serial entrepreneur decide whether to formalize their multi-venture operation into a Services Hub or a formal Venture Studio. Evaluates 3 operating modes (not binary): serial entrepreneur puro / services hub operator / formal studio with fund. Use when the user asks "when to become a studio", "serial entrepreneur vs studio", "systematize multi-venture", "formalize studio", "services hub readiness", "venture studio readiness", "/when-to-become-studio".
accelerator-launchpad
by DojoCodingLabsMatches a startup's profile (stage, vertical, geography, equity tolerance, urgency) against a curated catalog of 12+ external accelerator programs and produces ranked recommendations with application checklists. Use when the user asks "which accelerator", "accelerator matching", "apply to YC", "Techstars vs 500 Startups", "accelerator for LATAM", "CIHUBS accelerator network", "RevTech Labs", "Plug and Play", "SOSA corporate partners", "/accelerator-launchpad", or needs to decide among external acceleration programs. Implements CIHUBS-style meta-broker logic for LATAM founders seeking international acceleration.
research-cadence
by DojoCodingLabsSets up and maintains a continuous research cadence using the 3-12-1 format from Lean UX: 3 users tested per week, by 12:00 noon on 1 day (usually Thursday). Use when the user asks for "research cadence", "weekly user testing", "continuous discovery", "3-12-1", "Thursday user tests", "investigacion continua", "testing semanal", "/research-cadence", or wants to establish a sustainable weekly rhythm for UX research instead of big-bang research events. Generates weekly plans (Mon-Fri activities) and tracks cumulative findings.
startup-intake
by DojoCodingLabsAI intake interview structured to produce a `startup-profile.md` artifact compatible schema-wise with DojoOS Launchpad Startup Profile. Use when the user asks "startup intake", "startup profile", "onboard my startup", "create startup profile", "AI intake", "/startup-intake". Produces a structured profile covering problem, customer, solution, team, stage, traction, and funding needs — ready for co-founder matching, investor matching, and demo day prep in subsequent skills (or DojoOS Launchpad).
feature-to-spike
by DojoCodingLabsTransforms methodology learnings from dog-food sessions of launchpad-toolkit into Linear SPIKE issues formatted for William Ugalde (DojoOS Launchpad owner). This is the plugin's DIFFERENTIATOR — the piece that makes launchpad-toolkit a "methodology laboratory" not just a founder tool. Use when the user asks "propose spike", "generate spike", "feature to spike", "productize this", "send to William", "/feature-to-spike".
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.