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...
tobias-allen-marketing-mastery
by FarriceDirect response marketing, copywriting, revenue architecture, and growth engineering at nine-figure scale
shan-hanif-audience-monetization
by FarriceTurn unqualified LinkedIn leads into a high-profit digital product backend while elevating B2B agency positioning.
jason-fladlien-marketing
by FarriceDeploys Jason Fladlien's high-status persuasion physics — Success by Subtraction (remove the one weight, don't add ten tactics), Fear-First Conversion (get them to run out of reasons to say no), Incomparable Offer Engineering (don't make a better offer — make an incomparable one), and Radical Candor as Scarcity. 27 workflows across Tier 1-3 covering authority content, inertia-breaker presentations, identity-based offers, fear-mapped copy, indirect communication, and spoken close architecture. Use when building high-ticket sales presentations, designing offer stacks that resist comparison, writing fear-first conversion copy, structuring webinar / VSL closes, dissolving prospect inertia, or when generic persuasion templates aren't converting. Trigger proactively when the user mentions "Guru's Guru" tier work, $5K+ offers, sales-presentation polish, or compares their offer favorably to competitors (the "comparable offer" trap is exactly what Fladlien dissolves).
seth-godin-brand
by FarriceOperationalizes Seth Godin's brand-building methodology — the layer BETWEEN philosophy (why you create) and viral mechanics (how it spreads). Covers brand promise architecture, trust engineering, consistency systems, remarkability design, metric integrity (false-proxy purge), culture alignment, and AI-era permission strategy. Core thesis — a brand is a promise (not a logo), trust = keeping the promise when it's hard, marketing = everything that touches the market, better > louder, consistency > authenticity. Use when defining a brand promise, diagnosing trust gaps, designing remarkability into product/content/service so word-of-mouth is structural not accidental, auditing metrics for false proxies (vanity vs. value), or when the user says "what's our brand actually about?" / "how do we get noticed without going louder?". Trigger proactively when the user reaches for tactical marketing without having defined the promise — Godin's work is the foundation layer.
eric-roth-screenwriting-mastery
by FarriceOscar-level screenwriting craft from the writer of Forrest Gump, The Insider, Munich, Benjamin Button, A Star Is Born, Killers of the Flower Moon, and Dune. 14 genius patterns and 12 practitioner workflows for screenplay architecture, character psychology, subtext, adaptation, visual prose, and temporal structure.
eric-roth-writing-mastery
by FarriceCross-domain deployment of Oscar-level writing craft for social media, content writing, copywriting, ghostwriting, and marketing. Translates 14 genius patterns from the writer of Forrest Gump, The Insider, and Killers of the Flower Moon into universal writing intelligence — erosion revision, off-center subtext, visual prose, psychology wallets, memorable residue, and fanciful realism applied beyond the screenplay.
april-dunford-b2b-positioning-sales-pitch-architecture
by FarricePosition any B2B product using the 5-component methodology, diagnose positioning failures, engineer buyer fear de-risk strategies, and construct sales pitches using the Setup → Follow-Through framework. The world's most actionable system for answering 'Why should customers pick us?'
source-command-kingmaker-sprint
by FarriceChains 5+ expert skills through a16z kingmaker methodology
marc-andreessen-ben-horowitz-new-media-strategy
by FarriceDeploy a16z's new media warfare doctrine — OODA loop speed dominance, oral/written culture content architecture, founder go-direct positioning, flood-the-zone crisis response, and platform-native launch campaigns.
new-media-ghostwriting
by FarriceElevates ghostwriting from "write LinkedIn posts for someone" to "build their entire media empire." Compounds Nicolas Cole's voice capture, a16z's new-media doctrine (Joe Rogan CEO test, Unscripting Protocol, founder go-direct), Grace Andrews's content city architecture, and Lara Acosta's LinkedIn mastery into one premium service package. Produces voice-captured ghostwriting + founder positioning + content-city map + trust pathways + platform-native production + crisis defense across all channels. Use when designing a $5K+ ghostwriting offer, when a client needs more than per-post copy, when positioning a founder for direct-to-audience media, or when the user mentions "media empire", "founder voice", "ghostwriting service architecture", "new media positioning". Trigger proactively when a client engagement crosses the LinkedIn-only threshold into multi-channel founder media work.
new-media-kingmaker
by FarriceTakes any founder, brand, or organization from invisible to narrative-dominant in 30 days by chaining six expert skill sets through the a16z kingmaker methodology — diagnose media posture (old vs. new media physics) → position for go-direct (Joe Rogan CEO test) → architect content city with oral/written culture awareness → arm with proof ladder across platforms → launch with platform-native campaigns → protect with OODA-speed narrative control. Compound skill orchestrating a16z new-media doctrine, Grace Andrews content cities, Luke Iha proof, Nicolas Cole ghostwriting, Lara Acosta LinkedIn, and Cardinal Mason narrative. Use when launching a founder into the public eye, repositioning an established brand for AI-era media, recovering from a narrative crisis, or when the user mentions "media empire", "narrative dominance", "go-direct strategy", "kingmaker", "Joe Rogan-ready". Trigger proactively when a positioning conversation drifts toward "we need to be everywhere" — the kingmaker methodology beats fragmented
andrew-dun-vibe-consulting-mastery
by FarriceOperates Andrew Dun's diagnostic-first AI consulting practice — process mapping inside client orgs, ROI quantification before any tool recommendation, prescriptive transformation plans (not advice-and-leave), and the operating system for running a profitable AI consulting firm. Use when starting or scaling an AI consulting business, structuring an engagement that doesn't devolve into "I'll show you ChatGPT prompts", quantifying ROI before pitching, or building back-end ops (pricing, contracts, delivery cadence) for a firm that ships transformation, not reports. Trigger proactively whenever the user says "AI consulting", "consulting practice", "ROI for AI", "diagnostic engagement", or wants to charge $25K+ per engagement instead of $2K for training. For solo-operator AI monetization use darrel-wilson-ai-monetization; for personal AI leverage (not client work) use andrew-wilkinson-ai-entrepreneurship.
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.