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...
evolution-agent
by heath-gtmThe AI-native capstone. Watches QA Agent's audit + reads implicit feedback (emoji reactions, click-through, outcome attribution) + explicit feedback (👍/👎, structured reasons) — then generates pull requests to heath-gtm/Skill-Builder + LOCKED_DESIGN.md that evolve the system — tightens scoring rubrics, updates trigger phrases, amends lock-ins, proposes new workflows when usage patterns suggest them, retires unused analysts. Closes the loop QA Agent surfaces. Heath approves PR → system mutates itself. Trigger on "evolve the system", "apply this week's QA recommendations", "PR the scoring update", "amend lock-in
qa-agent
by heath-gtmThe 7th analyst — the meta-analyst. Monitors every other analyst's audit log + feedback queue, surfaces scoring blind spots, CRM hygiene gaps, enrichment gaps, workflow drift, and Daily Drop engagement decline. Generates weekly QA report (HTML) + Slack digest (Sundays, DMs Heath) + improvement recommendations. First stepping stone of AI-native GTM — every override, every missing CRM field, every enrichment miss becomes a training signal. Use to ask "what's broken in the system?", "show me CRM hygiene issues", "is the Daily Drop working?", "are scoring models drifting?", "what should we coach on this week?". Trigger on "run QA", "weekly QA report", "system health check", "where are our scoring blind spots?", "show me coaching priorities from data", "audit our workflow performance", "Daily Drop engagement check", "where's the system getting things wrong?", or any system-level health / improvement / feedback-loop question. Also fires automatically Sundays 7pm CT.
amplitude-analyst
by heath-gtmYour product usage analyst. Connect Amplitude — turns any "how are they using us?" question into a product engagement read: 11-capability adoption rubric, 12-week trend analysis, new user signals, Ghost-Active detection, Aero False-Negative detection, power-user identification, WAU/DAU at gp:domain grain. Use when a rep needs a single account's product story, finds expansion signals, surfaces new signups at customer accounts, or validates an Aero score. Trigger on "how is {account} using us?", "is {domain} active?", "find power users at {company}", "who signed up at customer accounts this week?", "is Aero right about {account}?", "is {account} ghost-active?", "what capabilities have they not adopted?", "show me onboarding gaps", "find product-qualified leads", "are they an Aero false negative?", or any product engagement question. Also fire when a CSM preps a QBR or a rep gets a meeting from a free account.
amplitude-event-taxonomy
by heath-gtmCanonical Amplitude event + capability reference for Mixmax — the single source of truth for which events mean what, how they roll up into the 11 product capabilities at gp:domain grain, and how events→groups→adoption-tier produce the product-engagement narrative. Load FIRST on any Amplitude / product-usage question. Defines the Mixmax prod project (130895), gp:domain grain, universal filters, the Tier 1/2/3 event registry with traps, the 11-capability rubric and its raw-event mapping, adoption tiers (Power/Established/Emerging/Dormant/Untouched/Never-adopted), the 12-week trend classifier, Ghost-Active + Aero-False-Negative detectors, the conversion funnel + aha moments, and paid productIds. Trigger on Amplitude, product usage, product engagement, events, event taxonomy, 'what event should I use', 'is this event reliable', gp:domain, 11-capability rubric, adoption tier, ghost active, Aero false negative, WAU, DAU, activation, aha moment, signups, conversion to paid, or any product-analytics question.
strike-zone-analyst
by heath-gtmMixmax's funnel + PQA diagnostic engine and funnel-leak analyst. Connect Salesforce + Amplitude (+ optional Octave, Common Room, FullEnrich, Mixmax). Three modes: (1) FUNNEL DIAGNOSIS finds leaky conversion gates by channel (Inbound/Outbound/Product) with per-stage leakage, dollarized leverage points, and cohort velocity; (2) SPRINT PLANNING multi-source-enriches PQAs into a ranked backlog with verified buying committees; (3) SCORING AUDIT finds where Aero is failing. Trigger on 'strike zone math', 'funnel diagnosis', 'diagnose the funnel', 'where are we leaking', 'why is [channel] underperforming', 'conversion by channel', 'show rate is dropping', 'meeting-to-SQL conversion', 'should we reallocate budget', "what's our funnel velocity", 'PQA sprint planning', 'score our PQAs', 'is Aero missing accounts', 'find missed ICPs', 'audit the scoring model', or any channel-level cohort-conversion, PQA prioritization, or scoring-gap question. Also fire after the Aero dashboard when the user asks 'now what'.
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.