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...
sales-tiktok-marketing
by johnnyscalezTikTok marketing strategy — organic growth, paid ads, content creation, influencer campaigns, algorithm optimization, and performance measurement. Covers organic profile growth (content strategy, posting cadence, trending audio, algorithm mechanics), TikTok Ads (campaign objectives, creative formats, targeting, Spark Ads, bidding), UGC and content creation (native formats, hooks, trending concepts), influencer strategy on TikTok (creator tiers, campaign types, ROI measurement), TikTok Shop integration, and performance metrics (CPM, CPC, ROAS, EMV). Use when your TikTok videos aren't getting views, TikTok ads are spending but not converting, your profile growth has stalled, you're unsure what content to post on TikTok, you can't tell if TikTok campaigns are actually driving revenue, or you're debating whether to hire an agency for TikTok. Do NOT use for platform-specific agency help (use /sales-houseofmarketers or /sales-cloutboost), general influencer marketing across platforms (use /sales-influencer-marketin
sales-media-relations
by johnnyscalezMedia relations and PR outreach strategy across platforms — journalist databases, media list building, pitch writing, media outreach sequences, press coverage tracking, and earned media measurement. Covers platform comparison (Meltwater, Cision, Muck Rack, Prowly, Agility PR, BuzzStream), journalist research (beat coverage, recent articles, social profiles), media list building (segmentation, tiering, contact verification), pitch writing (subject lines, personalization, angles, timing), outreach sequences (initial pitch, follow-ups, exclusives, embargoes), coverage tracking (clip reports, reach, AVE alternatives, message pull-through), and PR measurement (earned media value, share of voice, sentiment). Use when journalists aren't responding to pitches, unsure which reporters cover your beat, press outreach isn't landing coverage, can't measure PR impact, or don't know which media database to pick. Do NOT use for platform-specific config (use /sales-meltwater), influencer outreach (use /sales-influencer-market
sales-marketplace-payouts
by johnnyscalezMarketplace payouts strategy — selecting and operating the payment infrastructure that pays 1099 supply workers, sellers, drivers, hosts, and creators on a two-sided marketplace. Covers Stripe Connect (Standard / Express / Custom), PayPal Hyperwallet, Adyen for Platforms, Trolley, Tipalti, Routable, dots.dev, Branch, Nium, Wise Business, and Tremendous — when to pick each, the connected-account vs custodial trade-off, KYC and onboarding burden, daily-vs-weekly-vs-on-demand pay schedules, multi-currency, tax form generation (1099-K, 1099-NEC, W-9, W-8), and the 1099-misclassification risk that worker payment design carries. Use when deciding between Stripe Connect Standard vs Express vs Custom for a 1099 cleaning marketplace, comparing Hyperwallet vs Trolley for multi-country payouts, the supply side is churning because payouts arrive too slowly, can't decide whether to use a per-payout API (Trolley, Routable) or a full marketplace stack (Stripe Connect, Adyen for Platforms), need on-demand pay to compete on s
sales-hypefy
by johnnyscalezHypefy platform help — AI-native influencer marketing with zero-subscription, pay-per-campaign pricing. Covers AI campaign setup (brief generation from product description, geography, and budget), influencer discovery (3K+ vetted internal database, 12M+ external on Instagram and TikTok), automated outreach and hiring (proposals, terms, coordination), content review and approval before publishing, influencer payments (multi-currency, milestone-based, compliance), performance dashboard (reach, engagement, ROI), and built-in calculators (Budget, ROI, Engagement, CPM, CTR). Use when Hypefy campaign setup isn't clear, unsure if Hypefy is the right platform for your budget, pricing model feels confusing, creator payments aren't going through, content approval workflow is stuck, or campaign metrics don't look right. Do NOT use for influencer strategy across platforms (use /sales-influencer-marketing), ad campaign strategy (use /sales-retargeting), email marketing to subscribers (use /sales-email-marketing), or affil
sales-note-taker
by johnnyscalezSales meeting note-taker and conversation-intelligence strategy — platform selection (Fathom, Fireflies, Avoma, Gong, Otter, Fellow, Grain, Sembly, Read.ai, MeetGeek, Jamie, Krisp, Colibri, Cluely, Jamy, Wave, tl;dv, Claap, Tactiq, Granola, Hedy, Omi, Bluedot, Lindy, Notta, Rilla, Siro, Plaud, Speakwise, Sybill, Winn.ai, Sonnet, Supernormal, VoiceToNotes, Sonix, Outdoo, Jiminny, Enthu.AI, Demodesk, Clari Copilot, Salesken, Cresta, Balto, Observe.AI, Oliv, Weflow, Noota, Dialpad, Modjo, Verbit, Temi, Char, Amical, Handy, IRIS Clarity, Soz AI, Shadow, HappyScribe, Circleback, monday Notetaker, Memoro, MinutesLink, Voicenotes, Letterly, Cleft Notes, Coconote, HyNote AI, Backtrack, Superpowered, Noted, People.ai/Backstory, Scribbl, Audionotes, Bubbles, KUDO, Interprefy, Transync AI, Rimo, Liznr, Meeting.ai, KaraX.ai, reason8, NoteWave) plus backend API integration for auto-downloading transcripts into CRM, data warehouse, Slack, or internal tools. Use when choosing an AI note-taker, comparing pricing or features,
sales-hypeauditor
by johnnyscalezHypeAuditor platform help — AI-powered influencer marketing with Influencer Discovery (223.6M+ profiles across Instagram, TikTok, YouTube, X, Twitch, Snapchat), Analytics Reports (35+ metrics, AQS scoring), Fraud Detection (53 patterns, 95%+ accuracy), My Network IRM (CRM), Campaign Management (tracking, content approval, payments, product seeding), Market Analysis (competitor monitoring, benchmarks), Recruitment API, and ecommerce integrations (Shopify, WooCommerce, Magento). Covers Discovery API, Reports API, Campaign Management API, Lists Management API, Market Analysis API, Suggester API, and Gmail sync. Use when HypeAuditor searches aren't surfacing the right creators, audience data looks suspicious, unsure if an influencer has fake followers, campaign tracking isn't capturing results, API integration isn't returning data, ecommerce sales aren't attributing to influencers, or unsure which HypeAuditor plan fits your needs. Do NOT use for influencer strategy across platforms (use /sales-influencer-marketin
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.