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...
go-to-market-strategy
by stefanoskarakasisAssigns launch tier (T1–T4) and generates a complete GTM strategy brief with positioning angles, channel strategy, success metrics, and competitive context. Self-learns from past launches stored in the brain. Trigger on: "what tier is this launch", "GTM strategy for", "help me scope this", "how should we launch", "what channels for this launch", "is this a T1 or T2", "plan my launch", "launch strategy for", or any request to scope, tier, or build a GTM plan for a product, feature, pricing change, or market expansion.
hs-interview-summary
by stefanoskarakasisA self-improving customer interview synthesis engine for PMMs, Product Managers, and UX Researchers. Transforms raw transcripts into structured discovery outputs anchored in JTBD theory, with signal-level pattern detection, confidence scoring, and a compounding learning loop. Trigger on: "summarize interview", "process transcript", "interview summary", "what did customers say", "synthesize discovery", "interview debrief", "JTBD analysis", "customer insight", "research synthesis", or any request to process, structure, or extract meaning from a customer or prospect interview.
hs-product-requirement-doc
by stefanoskarakasisBuilds, guides, and co-writes a complete HubSpot Product Requirements Document (PRD) with an embedded Solution Story. Use this skill whenever a user mentions PRD, product requirements, solution story, feature spec, GTM brief, launch plan, product brief, user stories, feature rollout, announcement level, or asks for help writing up a product idea, feature, or initiative. Also trigger when a PM or PMM asks how to structure a product document, align on messaging, define success metrics, or plan a feature launch — even if they don't use the word "PRD". This skill produces two tangible outputs: (1) a standalone Solution Story for PMM-led communications, and (2) a full collaborative PRD for PM + PMM.
hs-pre-mortem
by stefanoskarakasisA self-improving pre-mortem risk engine for PMMs running cross-functional risk analysis on any strategic project. Covers: PRD, product launch, pricing change, new marketing channel, GTM pivot, new market entry. Run by a PMM facilitating cross-functional teams. Trigger on: "pre-mortem", "risk analysis", "what could go wrong", "stress-test this plan", "launch readiness", "pressure-test", "failure modes", "risks before we launch", "pre-launch review", "what are we missing", "GTM risk", "pricing risk", "market entry risk", or any request to identify, categorise, or mitigate strategic risk before a major move.
hs-prioritization-frameworks
by stefanoskarakasisGTM-native prioritization reference for PMMs — 9 frameworks with formulas, PMM interpretation layer, and launch tier output logic (T1–T4). Use when selecting a prioritization method, scoring strategic projects, triaging a launch backlog, or deciding how much GTM weight a product or initiative deserves. Trigger on: "how do I prioritize this", "should this be a big launch", "what tier is this", "help me score these initiatives", "RICE vs ICE", "prioritization framework", "launch backlog", "what gets GTM investment", "how do I decide what to launch first", or any request to rank, score, or tier product or GTM initiatives.
hs-retro
by stefanoskarakasisFacilitate a structured GTM retrospective for cross-functional squads (Eng, Design, PM, PMM) — anchored to OKRs and launch outcomes, with a self-improving knowledge loop that compounds across every session. Use when running a post-launch retro, GTM cycle review, sprint retrospective with a PMM lens, or any cross-functional debrief where you need decisions, not just discussion. Trigger on: "retro", "retrospective", "post-launch review", "what went wrong", "GTM debrief", "sprint review", "what should we do differently", "our last launch", "debrief this launch", "what did we learn", or any request to reflect on a completed GTM cycle or product initiative.
hs-stakeholder-maps
by stefanoskarakasisPMM stakeholder intelligence engine. Builds a political map — not a grid — that tells you who can kill your launch, who can champion it, and exactly what to say to each. Trigger on: "stakeholder map", "who do I need to align", "stakeholder plan", "who can block this", "executive alignment", "cross-functional buy-in", "who owns what", "communication plan", "stakeholder communication", "launch alignment", "who do I brief", "who needs to know", "internal enablement", "build my stakeholder map", or any request to map, engage, or align stakeholders around a GTM initiative, launch, or campaign.
hs-gaccs-brief
by stefanoskarakasisBuilds, pressure-tests, and outputs a complete GACCS Brief (Goals, Audience, Creative, Channels, Stakeholders) for any marketing, GTM, or enablement project. Use this skill whenever a Product Marketer, PMM, or GTM Enablement person mentions a campaign, launch, content piece, event, enablement asset, or any marketing project — even if they say "I need to write a brief", "help me think through this campaign", "I'm planning a launch", "what's the best way to structure this project", or "where do I even start with this". Also trigger when someone pastes a brain dump of marketing context and needs it structured. The skill auto-detects whether to run in Conversational mode (idea-first) or Brain-dump mode (context-first), and challenges weak sections inline with adversarial callouts before generating the final brief.
hs-privacy-policy
by stefanoskarakasisDraft a jurisdiction-aware privacy policy for any digital product — use this skill whenever a PMM or Product Manager needs to create, update, audit, or review data protection documentation, asks about GDPR, CCPA, or UK GDPR obligations, mentions "privacy policy", "cookie policy", "data retention", "right to be forgotten", "data processing agreement", or asks what their product needs to comply with applicable privacy law.
hs-pmm-resume
by stefanoskarakasisResume reviewer and tailoring engine for Product Marketing Managers (IC to VP, including AI PMM roles). Takes baseline resume + job description → dissects JD → ranks bullets by impact fit → rebuilds complete resume in one pass. Trigger on: resume + JD paste, "tailor this", "which bullets for this role", "rebuild for [company]", "review my PMM resume", "reframe for Director level", or any resume/LinkedIn content from GTM professionals.
hs-writing-assistant
by stefanoskarakasisA writing coach and messaging strategist for B2B tech teams. Use this skill whenever someone wants to rewrite, sharpen, draft, or pressure-test any written communication: Slack messages, internal emails, async updates, decision memos, PRDs, one-pagers, homepage copy, ads, email campaigns, or positioning documents. Trigger on phrases like: "rewrite this", "sharpen this", "help me say this better", "draft a message", "is this landing?", "why isn't this converting?", "make this more human", "review my copy", "this feels flat", "help me write to my CEO", "write a Slack update", "turn this into an email", or any request involving internal or external written communication in a tech or B2B context.
hs-positioning-messaging
by stefanoskarakasisUse for any positioning or messaging task — positioning statement, messaging hierarchy, homepage copy, sales persona cards, competitive deck, messaging audit, value proposition, tagline, elevator pitch, or when the user says "we sound like everyone else," "our messaging isn't landing," "sales can't explain what we do," or mentions April Dunford, Emily Kramer, or Obviously Awesome; runs the full Dunford sequence across five output modes (BUILD / AUDIT / FLETCH / SALES-ENABLEMENT / HOMEPAGE) with Pawel Huryn's self-improving memory loop. Parses attached screenshots and images before asking any questions, refuses briefs without a named primary persona and at least three alternatives including status quo, and blocks output until a 7-point self-verification gate passes.
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.