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...
hypothesis-building
by extruct-aiGenerate testable pain hypotheses from the company context file (ICP, win cases, product knowledge) and user input. Fast, no API keys needed — pure reasoning. Outputs a hypothesis set with search angles that directly guide list-building queries. Sits between context-building and list-building. Triggers on: "build hypotheses", "hypothesis set", "pain hypotheses", "define hypotheses", "what pain points", "campaign angles", "search angles", "refine hypotheses".
list-enrichment
by extruct-aiAdd research-powered enrichment columns to Extruct company tables. Use when the user wants to add enrichment columns (e.g. funding, verticals, tech stack) to an existing Extruct table, run column configs from enrichment-design, or monitor enrichment progress. Triggers on: "enrich", "add column", "add data point", "research column", "enrich table", "enrichment", "add a field", "run enrichment", "monitor enrichment".
table-creation
by extruct-aiCreate an Extruct company table from user-provided data, upload rows, and optionally add enrichment columns. Handles the full flow: parse input (CSV, pasted list, or structured data), create or reuse a table, upload domains in batches, add agent columns, and trigger enrichment. Triggers on: "create table", "upload companies", "add to extruct", "new extruct table", "import companies", "upload list to extruct".
campaign-sending
by extruct-aiUpload finalized emails for sequencing and sending. Maps fields to lead schema, creates or finds campaigns, uploads leads with dedup, and provides a pre-send verification checklist. Triggers on: "upload to instantly", "run instantly", "send emails", "instantly campaign", "push to instantly", "start campaign", "load into instantly".
email-prompt-building
by extruct-aiDesign a cold-outreach email sequence as a FIXED TEMPLATE SET — real, human-approved copy with {{input_field}} placeholders and variant-routing rules. Reads the company context file and campaign research, explores angles, and commits to copy at design time. The output is rendered later by the email-generation skill via deterministic substitution — no per-row LLM. Triggers on: "cold email", "outreach prompt", "email campaign", "new vertical email", "draft email prompt", "email sequence", "email template".
post-engagers
by extruct-aiExtract people who engage (comment, react, repost) on a LinkedIn post, enrich their profile / email / company data, and land them in a local SQLite CRM (content.db → crm.db) as the source of truth. Extruct people-table upload is optional. Triggers on: "post engagers", "linkedin engagers", "who commented on", "who liked", "who reacted", "linkedin post engagers", "scrape post", "extract engagers", "post commenters".
email-verification
by extruct-aiValidate email addresses before campaign sending. Takes a contact CSV, validates each email via a verification provider, removes invalid/do_not_mail/abuse/unknown addresses, and optionally cleans them from sequencer campaigns. Outputs a verified CSV ready for campaign-sending. Fits between email-generation and campaign-sending in the pipeline. Triggers on: "verify emails", "validate emails", "email verification", "clean emails", "check emails before sending", "remove bad emails", "email hygiene".
context-building
by extruct-aiBuild and maintain a global company context file that all other GTM skills read from. Captures product info, voice rules, ICP, win cases, proof library, campaign history, hypotheses, and DNC lists. Supports four modes: create (new context), update (append to existing), call recording capture (extract signals from transcripts), and feedback loop (import campaign results). Triggers on: "company context", "update context", "build context", "ICP", "win cases", "campaign history", "call recording", "feedback loop", "DNC list".
competitor-monitoring
by extruct-aiSet up and run competitive intelligence monitoring. Discover competitors via user input, lookalike search, web research, or G2/review sites, then create an Extruct company table with research columns for blog, social media, news, key people, and business model tracking. Re-run columns to refresh monitoring data. Triggers on: "competitor monitoring", "track competitors", "competitive intelligence", "monitor competitors", "competitor analysis", "competitive landscape", "who are my competitors", "competitor tracking".
deal-intelligence
by extruct-aiDeal intelligence assistant that combines Attio CRM, Gmail, Granola, and Extruct AI signal monitoring to answer questions about deals, contacts, and pipeline. Supports deal analysis, pipeline review, contact lookup, activity timeline, and 3rd-party signal scanning for cooling/stale deals. Triggers on: "deal intel", "deal analysis", "pipeline review", "deal status", "what's happening with", "tell me about the deal", "deal intelligence", "next week", "weekly plan", "pipeline update", "deal signals", "stale deals".
key-account-plan
by extruct-aiCreate comprehensive Key Account Plans for clients/prospects. Use this skill whenever the user mentions 'account plan', 'key account', 'account planning', 'strategic account', 'client plan', 'customer success plan', or wants to create a structured plan for managing an important client relationship. Also trigger when users ask to 'plan for [company name]', 'review account strategy', 'prepare account review', or mention MEDDPICC/MEDDPIC analysis alongside client planning. This skill pulls data from Attio CRM (company records, contacts, deals, notes, emails, call recordings, MEDDPICC scores) and Google Drive, then produces a polished .docx Key Account Plan document and creates summary notes + tasks back in Attio. Even if the user just names a company and says something like 'let's do an account plan' or 'prepare for my QBR with [company]', use this skill.
meddpicc-post-call
by extruct-aiAuto-fill CRM and create follow-up tasks after a sales call using MEDDPICC methodology. Pulls meeting transcripts from Granola, scores the call against all 8 MEDDPICC dimensions, extracts competitor mentions, budget discussions, decision criteria, champion signals, and next steps — then writes everything to Attio (deal updates, notes, tasks). MANDATORY TRIGGERS: Use this skill whenever the user mentions "post-call", "after the call", "MEDDPICC", "score the call", "call review", "update CRM after call", "auto-fill CRM", "call analysis", "sales call review", "what did we miss on the call", "debrief the call", "log the call", or references analyzing a completed sales meeting. Also trigger when the user asks to extract competitor mentions, budget info, or decision criteria from a call transcript.
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.