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...
job-changes
by sachacoldiqJob change signal tracking for B2B outbound. Use when the user asks about job change signals, champion tracking, new role outreach, vendor amnesty period, Clay job change monitoring, or days 14-45 engagement window. Do NOT use for general hiring signals (use hiring skill) or company-level events (use company-events skill).
josh-braun-copywriting
by sachacoldiqJosh Braun's 5 cold email writing principles plus personalization best practices. Use when refining email copy, improving message quality, or reviewing outreach for common mistakes.
qualify-accounts
by sachacoldiqQualify and score target accounts using ICP scoring matrices, ABM tier assignment, intent data layering, and lookalike building. Use when user asks about "qualify accounts", "score accounts", "ABM tiers", "account-based marketing", "intent data", "lookalike accounts", "prioritize accounts", "tier 1 accounts", "account scoring". Do NOT use for initial ICP definition (use define-icp) or finding contacts at accounts (use find-contacts).
linkedin-content
by sachacoldiqExpert LinkedIn organic content strategist for B2B founders and GTM leaders. Use when the user asks about LinkedIn posting strategy, LinkedIn algorithm, LinkedIn hooks, LinkedIn carousels, LinkedIn content writing, LinkedIn profile optimization, LinkedIn engagement strategy, LinkedIn newsletter, LinkedIn comment strategy, or growing a LinkedIn audience. Also triggers on "LinkedIn post", "LinkedIn content", "LinkedIn hook", "LinkedIn algorithm", "LinkedIn carousel", "LinkedIn profile", "LinkedIn engagement", "LinkedIn reach", "LinkedIn followers", "LinkedIn headline", "LinkedIn banner", "write a LinkedIn post", "LinkedIn strategy". Do NOT use for LinkedIn Ads (use linkedin-ads skill) or LinkedIn outbound messaging/cold outreach sequences (use cold-email skill).
email-waterfall
by sachacoldiqSet up email waterfall enrichment in Clay for maximum coverage. Use when the user asks about finding work emails, email enrichment, email waterfall setup, provider ordering, email coverage optimization, conditional runs for email, bounce rates, or email validation. Triggers on "find emails", "email waterfall", "email coverage", "email discovery", "work email", "email provider", "bounce rate". Do NOT use for phone enrichment, company-only enrichment without email needs, or general CRM email questions.
cold-call-scripts
by sachacoldiq1-minute cold call script (5 steps) and no-show phone script. Use when training SDRs on calls, building call frameworks, or handling common phone scenarios.
company-enrichment
by sachacoldiqEnrich company data in Clay with firmographics, technographics, revenue, headcount, and industry. Use when the user asks about company enrichment, firmographic data, tech stack detection, company revenue, employee count, industry classification, or company research workflows. Triggers on "company data", "firmographics", "technographics", "company enrichment", "revenue data", "headcount", "tech stack", "company research", "industry data". Do NOT use for people/contact enrichment, email finding, or phone number discovery.
debugging
by sachacoldiqTroubleshoot Clay workflow issues, fix common mistakes, resolve auto-update problems, and stop credit waste. Use when the user reports something not working in Clay, credits being wasted, auto-update issues, wrong enrichment results, empty columns, or workflow errors. Triggers on "not working", "error", "troubleshoot", "debug", "credits wasted", "auto-update issue", "Clay problem", "wrong results", "fix my workflow", "common mistakes", "empty results", "credits burning". Do NOT use for building new workflows from scratch, learning Clay basics, or pricing questions.
phone-enrichment
by sachacoldiqSet up phone number waterfall enrichment in Clay for direct dials and mobile numbers. Use when the user asks about finding phone numbers, phone waterfall, mobile numbers, direct dials, phone enrichment, or calling prospects. Triggers on "phone numbers", "mobile numbers", "phone waterfall", "direct dial", "phone enrichment", "cell phone", "find phone", "calling list". Do NOT use for email enrichment, company data, or general contact discovery without phone-specific needs.
table-setup
by sachacoldiqCreate and configure Clay tables, choose column types, import data, and set up auto-update. Use when the user asks about creating a Clay table, choosing column types, importing data (CSV, CRM, LinkedIn), setting up views and filters, configuring auto-update, using the Chrome extension, or organizing workbooks. Triggers on "create table", "table setup", "column types", "data import", "auto-update", "Clay table", "workbook", "views", "filters", "CSV import", "Chrome extension", "Clip to Clay". Do NOT use for enrichment-specific questions, scoring, or formula writing.
btl-messaging
by sachacoldiqWrites cold emails targeted at Managers and Individual Contributors (Below-the-Line). Use when the user asks to "email a manager", "email an IC", "email an end user", "below the line", "BTL messaging", "operational email", or targets someone with a Manager/Specialist/Analyst/Coordinator title. Also triggers on "tactical messaging", "user-level email", "bottom-up outreach", "champion building email". Do NOT use for emails targeting VP/C-Level/Directors (use atl-messaging), general email writing without a specified persona, or deliverability questions.
copywriting
by sachacoldiqCold email copywriting frameworks, principles, and sequence structure. Use when the user asks about email copywriting frameworks, cold email writing rules, email sequence structure, email variations, e-commerce cold email, copy testing, A/B testing email copy, or needs named frameworks (Do the Math, Short Trigger, Pattern Interrupt, etc.). Triggers on "copywriting framework", "email framework", "Do the Math", "Short Trigger", "Pattern Interrupt", "email variations", "email structure", "copy principles", "e-com cold email", "ecommerce outreach", "email copy rules", "how to write cold email", "copy testing". Do NOT use for personalization at scale (use personalization) or subject lines only (use subject-lines).
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.