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...
business-model-canvas
by qa-amanUse when the user says "map out our business model", "business model canvas", "how does our business work", "what are our key resources", "define our value proposition", "revenue model design", "cost structure", "who are our key partners", "lean canvas", "business model design", "how do we make money", or wants to document, stress-test, or redesign how [your startup] creates, delivers, and captures value.
customer-discovery
by qa-amanUse when the user says "run customer discovery", "help me interview customers", "write customer interview questions", "validate my assumption", "talk to users", "synthesize customer interviews", "what are my customers saying", "user research for my startup", "mom test interview", "are we solving a real problem", or wants to extract real insight from conversations with potential or existing customers.
hypothesis-framing
by qa-amanWrite or refine a research hypothesis. Use when the user says "write a hypothesis", "frame my hypothesis", "is my hypothesis testable", "null and alternative hypothesis", "research hypothesis", "refine my hypothesis", "hypothesis statement", "H0 and H1", "operationalize my hypothesis", "turn my research question into a hypothesis", or needs to convert a research question or intuition into a falsifiable, testable hypothesis with clear variables and predictions - even if they don't explicitly say "hypothesis".
tax-position-memo
by qa-amanWrite a technical tax position memo that documents a tax filing position with authorities, facts, analysis, and conclusion. Use when a tax professional says "write a tax memo", "document this tax position", "research memo for the partner", "we need to support this deduction", "document the tax treatment", "write up the authority for this position", "technical memo on [tax issue]", "MLTN analysis", "reasonable basis memo", "document the IRC section that supports this", or needs to formally document a tax conclusion. Also trigger when someone has a tax question that needs a written conclusion backed by legal authority - even if they don't use the words "tax memo" or "tax position".
karpathy-guidelines
by qa-amanBehavioral guardrails against the six most common LLM coding failure modes. Apply on every coding task: writing, editing, reviewing, or refactoring.
kpi-review
by qa-amanReview marketing KPIs and produce an executive summary with insights, anomalies, and recommended actions using the Storytelling with Data framework (Cole Nussbaumer Knaflic). Every review starts with a Big Idea - one sentence capturing the insight, its implication, and why it matters. Use when the user asks for a KPI review, monthly metrics review, marketing dashboard review, "review last month's numbers", quarterly review, performance review, or wants to analyze marketing data. Reads kpis.md and any uploaded data files.
uat-plan
by qa-amanGenerate a User Acceptance Testing plan with scenarios and sign-off criteria. Use when the user says "UAT plan", "acceptance testing", "user testing plan", "how do we test this with users", "test scenarios for business validation", "sign-off criteria", "go/no-go for release", "acceptance test cases", "validate with stakeholders" - even if they don't explicitly say "UAT".
qbr-deck
by qa-amanBuild a structured Quarterly Business Review deck for a customer account. Use when user says "QBR", "quarterly business review", "prep my QBR", "build the deck", "renewal prep", "executive check-in", "90-day review", or "customer business review" - even if they don't use the acronym. Applies to CSMs preparing for executive-level customer meetings focused on value delivered, health, and next quarter alignment.
11-star-framework
by qa-amanRate any product, feature, or experience on the 11-star scale (Brian Chesky's Airbnb thought experiment). Use when user says "rate this experience", "11-star", "star rating", "experience audit", "how good is this", "experience rating", "product audit", "quality assessment", or wants to evaluate product quality and identify improvement paths. Also trigger when user wants to benchmark a feature, assess where a product stands, or map out what "great" looks like - even if they don't explicitly say "11-star".
expansion-discovery
by qa-amanIdentify expansion signals and structure upsell or cross-sell conversations using land-and-expand and Net Revenue Retention principles. Use when user says "upsell", "expansion", "cross-sell", "grow the account", "increase ARR", "find expansion opportunities", "NRR improvement", "upgrade conversation", "add-on", "renewal and expand", or "land and expand" - even if they don't say "expansion discovery" explicitly. Applies to CSMs managing account growth or CS teams building expansion playbooks.
onboarding-plan
by qa-amanDesign a 100-day customer onboarding plan with phase gates based on Never Lose a Customer Again by Joey Coleman. Use when user says "onboarding plan", "new customer onboarding", "customer kickoff", "first 90 days", "activation plan", "customer launch plan", "new customer journey", or "implementation plan" - even if they don't say "100 days" explicitly. Applies to CSMs designing structured onboarding programs that move customers from signed contract to full adoption.
fundraising-email
by qa-amanUse when the user says "write a cold email to investors", "investor outreach email", "how do I cold email a VC", "fundraising cold outreach", "email to angel investor", "reach out to investors", "get a meeting with investors", "intro email for fundraising", "follow up with investor", "warm intro email", or wants to draft any outbound investor communication to generate a first meeting or advance a fundraising conversation.
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.