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...
qualify-leads
by Othmane-KhadriRun the GTM-OS 7-gate qualification pipeline over a batch of leads from a CSV, JSON, Notion DB, profile-visitors export, post-engagers export, or an existing SQLite result set. Writes per-lead pass/fail data back into SQLite and returns a result-set id you can hand to the campaign launcher. Use when the user says 'qualify these leads', 'score this lead list', 'run the qualification pipeline', 'check if these leads are a fit', or 'qualify the engagers'. Side-effecting — writes to the local SQLite db.
yalc-orientation
by Othmane-KhadriFirst-touch onboarding for someone who just opened the YALC repo. Triggers when the user pastes the repo URL `https://github.com/Othmane-Khadri/YALC-the-GTM-operating-system` (with or without trailing slash, with or without `.git`), or says any of: 'what is yalc', 'what is this', "let's start", "let's go", 'i just cloned this', 'how do i use this', 'got the repo', 'where do i begin', "i'm new to yalc". Introduces YALC, checks prerequisites, asks the user what they want to do, and routes to the right capability. Hands off to /setup if the environment isn't initialized.
fullenrich-content-engagers
by Othmane-KhadriUse when the user says "enrich people who engaged with this post", "qualify post engagers with FullEnrich", "scrape and enrich LinkedIn post {URL}", "engagers from this post into a CSV", "enrich this CSV of leads", "FullEnrich content engagers", or any variant indicating they want to convert a list of leads — either LinkedIn post likers/commenters scraped via Unipile, or a bring-your-own CSV — into ICP-qualified, enriched leads via FullEnrich v2 bulk enrichment with webhook callback delivery.
fullenrich-event-attendees
by Othmane-KhadriUse when the user says "enrich this LinkedIn event", "enrich attendees of this event", "enrich this attendees CSV", "scrape and enrich LinkedIn event {URL}", "FullEnrich event attendees", or any variant indicating they want to turn LinkedIn event attendees into an SDR-ready CSV with verified emails and mobile phones. Two input modes: (a) bring-your-own attendees CSV (PhantomBuster, Evaboot, Sales Navigator, manual paste), or (b) run a user-configured Apify actor against a LinkedIn event URL. Both converge on FullEnrich v2 bulk enrichment with webhook callback delivery.
fullenrich-network-activation
by Othmane-KhadriUse when the user says "activate co-founder network with FullEnrich", "enrich LinkedIn connections export", "qualify my LinkedIn connections CSV", "turn Connections.csv into a lead list", "FullEnrich network activation", or any variant indicating they want to convert a LinkedIn personal-network CSV export into ICP-qualified leads with FullEnrich-verified emails and phones. Reads the LinkedIn Data Export Connections.csv, applies an ICP filter, then enriches missing contact info via FullEnrich v2 with webhook callback delivery.
fullenrich-plg-reverse-lookup
by Othmane-KhadriUse when the user says "set up FullEnrich reverse lookup for trial signups", "PLG enrichment webhook", "identify free trial signups via FullEnrich", "reverse email lookup for these signups", "who are these emails", "deploy a hosted webhook for trial signups", or any variant indicating they want to identify the person and company behind a signup email. Two install paths: (a) CLI batch over a CSV/JSON of recent signups, (b) hosted webhook that receives signup events live, runs FullEnrich reverse lookup, and outputs the enriched record as a JSONL log plus an optional generic forward webhook the user wires to whatever downstream they run.
provider-builder
by Othmane-KhadriUse when a teammate wants to add a new vendor to YALC for an existing capability without shipping a release. Triggers include "add a new provider for X", "wire up [vendor] to YALC", "build an adapter for [vendor]", "I want to use [vendor] for [capability]", "add Apollo for icp-company-search", or any variant indicating they want to author a declarative YAML manifest under `~/.gtm-os/adapters/`. Converts a vendor name + capability id + docs URL into a registered, smoke-tested manifest in roughly five minutes.
research-prospect
by Othmane-KhadriRun ad-hoc web research on a prospect (company URL or person) — Firecrawl scrapes the marketing site, key pages (pricing, careers, blog), and surfaces a brief. Read-only. Use when the user says 'research this prospect', 'tell me about [company]', 'do a deep dive on [domain]', 'pull a brief on this lead', or 'crawl the marketing site for [name]'. Side-effecting on the Firecrawl side (API call), no local DB writes.
run-competitive-intel
by Othmane-KhadriPull competitive intelligence on a competitor — pricing, positioning, recent changes, customer stories — via the competitive-intel CLI. Use when the user says 'analyze this competitor', 'pull competitive intel on [company]', 'compare us to [competitor]', 'what's [company] doing differently', or 'audit [competitor] pricing'. Side-effecting — calls Firecrawl + Anthropic, writes to local cache.
run-doctor
by Othmane-KhadriRun the GTM-OS health check across all 5 diagnostic layers (environment, database, configuration, provider connectivity, runtime state). Use when the user says 'is YALC working', 'diagnose YALC', 'check YALC health', 'is everything configured', 'run the health check', or 'are my keys set up'. Read-only — never writes anything. Surfaces /keys/connect/<provider> URLs alongside any failed provider so the user has a one-click path to fix.
scrape-post-engagers
by Othmane-KhadriPull the audience that engaged with a LinkedIn post — likers (reactors) and commenters — via Unipile, dedupe across endpoints, and persist them as a result set ready for qualification or campaign launch. Use when the user says 'scrape engagers from this post', 'who liked this LinkedIn post', 'who commented on this LinkedIn post', 'pull engagers from this URL', or 'get the audience of this post'. Side-effecting — calls Unipile and writes to the local SQLite DB.
send-cold-email
by Othmane-KhadriSend a cold email campaign or single message via the configured email provider (Instantly by default), optionally pre-drafting the sequence. Use when the user says 'send a cold email to this list', 'fire the email sequence', 'launch the email campaign', 'send the drip sequence', or 'email these qualified leads'. Side-effecting — calls Instantly API and writes to local SQLite + Notion.
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.