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...
kidswear-photography-master-github
by fancyai-officialProfessional kidswear photography generation system. Receives a white-background kidswear image, sequentially asks for model characteristics (gender/type/age group), recommends 6 matching scenes, and generates five 3:4 vertical commercial blockbuster shots using a 4-layer prompt structure. Use this skill when the user mentions "generate kidswear model images", "change kidswear background", "kidswear try-on effect", "kidswear commercial shots", or directly uploads a kidswear image requesting a model/scene generation.
icon-designer
by fancyai-officialDesign with a legendary fashion icon — Coco Chanel, Alexander McQueen, Giorgio Armani, Valentino Garavani, Christian Dior, or Yves Saint Laurent. User selects a designer, describes their need, and the icon designs through their signature philosophy. Output is 3-angle on-model imagery (front, side, back). Use when the user wants to design with a fashion legend, mentions icon designer, legendary designer, design with Chanel/McQueen/Armani/Valentino/Dior/YSL, or wants garment design from a specific iconic fashion house perspective.
fashion-campaign-director
by fancyai-officialAI Creative Crew — a full production team (Creative Director, Photographer, Stylist, Hair & Makeup Artist, Casting Director, Set Designer) that analyzes apparel or lookbook inputs and produces a fashion campaign scaled to input volume (1–3 inputs → 6 images; 4+ inputs → 9 images). Each crew member contributes their own expertise and references, creating productive creative tension. Presents 3 treatments as pitches, then executes the selected direction with visual cohesion. Use when the user uploads garment photos, lookbook images, or collection assets and wants a professional campaign produced — or mentions fashion campaign, creative direction, campaign production, editorial shoot, or lookbook campaign.
beauty-photography-master
by fancyai-officialUse this skill whenever the user uploads a perfume or beauty product photo and wants luxury advertising campaign images or short video ads. It covers product identification, creative direction, prompt construction, parallel campaign image generation, visual QA, curation, iteration, and optional video ad generation. Triggers on perfume ad photography, beauty campaign, fragrance creative direction, product shoot styling, bottle photography, cosmetic ad, luxury brand campaign, , , , , or any request to turn a product photo into a premium ad image or short ad video.
beverage-photography-master-github
by fancyai-officialBeverage commercial photography expert. Given a product image, automatically analyzes product → selects aesthetic style → builds Prompts → batch generates 5 × 4K images (dynamic splash / macro close-up / lifestyle narrative / still life atmosphere / creative concept) → compresses and saves locally with real-time preview. Use when the user mentions "beverage shoot", "product photography", "commercial photography", "help me shoot", or uploads a beverage product image.
ecom-shoe-image-shotlist-github
by fancyai-officialFootwear e-commerce photography expert. Given a white-background shoe image, automatically analyzes product (compress_product_img.py → Read tool → LLM vision) → selects scene from professional scene library → generates 6 advertising-quality hero images in 2-batch parallel pipeline (batch 1 baseline model → batch 2 remaining 5 images) using three-step pattern (submit → poll → download/upload to CDN) covering on-feet full-body shots, on-feet close-ups, and lifestyle still-life shots → optional video generation for 5 images with highlight reel. Use when the user mentions "shoe photography", "e-commerce hero image", "product shot", or uploads a shoe product image.
appliance-skill
by fancyai-officialAnalyzes small appliance product features and generates high-end commercial photography. Use when the user uploads a product image, describes a small appliance, wants to generate commercial photography, create e-commerce hero images, or brand posters. Trigger words: small appliances, product photography, commercial photo, generate image, e-commerce hero, product poster, headphones, hair dryer, air fryer, rice cooker, robot vacuum, smartwatch, neck fan, etc.
editorial-fashion-six
by fancyai-officialSix fixed 3:4 editorial fashion storyboard images from the same SKU's multi-angle white-background product photos. Covers brand ID, layered non-flat scenes (reference-scenes), styling (reference-outfit), poses (reference-pose-vocabulary), optional web research, triple-choice, hero-image anchoring, HTTP nano-banana generation, and per-frame QC with targeted regeneration only; bright natural daylight; do not paste full prompts in chat. Use for six editorial, magazine, or mood shots, lookbook storyboards, or nano-banana synced generation for one garment. Triggers include requests for six frames, six editorial images, storyboard six, magazine-style, nano banana image gen. Do not use for eight-slot global PDP or marketplace detail-page matrices—use ecommerce-fashion-workflow instead.
street-style-photographer
by fancyai-officialYou are a street style photographer in the spirit of The Impression and Vogue street style coverage. Use when the user provides garment, outfit, or model images and wants candid fashion week street style photos, editorial street snaps, or city-based fashion photography concepts.
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.