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...
room-redesign
by GraehamwattsAI Room Redesign & Virtual Staging for Graeham Watts. Use ANY time the user mentions room redesign, virtual staging, stage a listing, redesign this room, redesign my room, photorealistic redesign, interior design preview, pre-renovation preview, what would this room look like, make this room look, stage this house, staging photos, listing staging, empty room staging, furniture swap, change the decor, change the paint, change the sofa, redesign the kitchen, redesign the bedroom, redesign the office, Japandi, mid-century, minimalist, Scandinavian, boutique hotel vibe, or anything related to generating photorealistic redesigns of real rooms from a user-supplied photo. Also trigger when the user uploads a photo of a room and asks how to make it look different, better, or sold-ready. This skill calls Google's Gemini image API directly — no third-party wrapper — and is built specifically for real estate listing staging and homeowner redesign previews.
listing-remarks-writer
by GraehamwattsMLS listing remarks writer optimized for AI-powered home search (ChatGPT with Zillow, Perplexity, Google AI Overviews) and Bay Area buyers. Walks the buyer through the property as if touring it, adapts framing to property condition (fixer / mid / move-in ready), and produces noun-dense AI-searchable copy. Use this skill ANY time the user asks to: write listing remarks, write MLS description, draft listing copy, write property remarks, write the public remarks for [address], rewrite a stale listing, optimize listing for AI search / ChatGPT / Zillow, write the public remarks section for a new listing, draft remarks for a fixer, draft remarks for a renovated home, or improve an existing listing description. Trigger when the user uploads listing photos and asks for the description, mentions a new listing, or pastes property details and asks for the listing description. Localized for Graeham's Bay Area markets (East Palo Alto, Redwood City, Palo Alto, Menlo Park, San Mateo County) with default California-specific
copywriter
by GraehamwattsDirect-response copywriter that produces high-converting marketing copy in any format — ad headlines, landing page hero copy, email subject lines, sales pages, CTAs, product descriptions, social captions. Picks the right framework (AIDA for cma-reports/newsletters/ads, PAS for problem-aware audiences, FAB for feature-heavy products, Before/After/Bridge for transformation offers), delivers three variations by default, and explains the psychological lever each one pulls. Use ANY time the user mentions copywriting, copywriter, write me a headline, write me copy, ad copy, Facebook ad, Google ad, landing page copy, hero section, email subject line, cold email, CTA, call to action, sales copy, sales page, product description, conversion copy, VSL, marketing copy, brand voice, tagline, slogan, or promo copy. Also trigger when the user pastes a product and asks "how would you pitch this?", shares a weak CTA, or wants A/B variations. Over-trigger — any "help me sell this" moment is copywriting.
farming-postcard
by GraehamwattsGenerate print-ready 6x4 farming postcards for Graeham Watts in his locked brand system (gold + black, chevron pattern, Intero + Graeham Watts lockup). Three workflows — interactive create on demand, scheduled preview that emails 3-5 hook options 7 days before the 1st and 15th of each month, and recall of previously-emailed options for selection. Use ANY time the user mentions farming postcard, direct mail postcard, EPA postcard, neighborhood postcard, mailer, mail piece, Wise Pelican, Universal Mail Works, Corefact, ProspectsPLUS, monthly postcard, 1st of the month postcard, 15th of the month postcard, equity postcard, buyer-tagged postcard, anti-Zillow postcard, neighbor envy postcard, AI search postcard, new postcard for next month, the next farming card, run the postcard skill, design a postcard, "pull up the postcard options you emailed", "what did you send me for the next postcard", "show me the postcard previews", "pick one of the postcard hooks". Also trigger when user uploads past postcards as refere
travel-hq
by GraehamwattsDedicated travel agent, trip planner, and points strategist for Graeham Watts. Handles all travel planning, comparison, optimization, and booking prep. Use ANY time the user mentions: book a flight, book a hotel, plan a trip, travel planning, travel itinerary, trip comparison, flight search, hotel search, points optimization, credit card rewards for travel, lounge access, trip prep, packing list for a trip, travel emergency card, companion traveler, price drop monitor, post-trip review, points earned, miles earned, book a trip, trip prep brief, emergency travel card, travel HQ, travel assistant, what card should I use for flights, how many points will I earn, compare these trips, prep me for my trip, which airline, what lounge, or anything related to planning, comparing, booking, or reviewing travel. Also trigger when the user pastes a booking confirmation, flight itinerary, or hotel reservation. Over-trigger rather than under-trigger — if there is any travel intent in the message, use this skill.
local-news-scraper
by GraehamwattsLocal news scraper for Graeham Watts' Bay Area markets. Pulls news headlines, press releases, and permit/zoning updates from official city websites (cityofepa.org, redwoodcity.org, cityofpaloalto.org, menlopark.gov, smcgov.org) and regional outlets (SF Chronicle, Mercury News, KTVU, Palo Alto Weekly, Daily Post). Use ANY time the user mentions: pull local news, find news stories for this week, scan city websites, news for EPA / RWC / PA / MP, city council approvals, new development permits, press releases, timeliness research, news hook for video, refresh local news feed. Also trigger when a day view or weekly calendar shows "Demo Data" on the Local News card and user wants it live, OR when content-calendar's Timeliness scoring needs fresh input.
cinematic-trailer-pipeline
by GraehamwattsEnd-to-end cinematic trailer production pipeline for Graeham Watts — from concept to finished MP4. Use ANY time the user mentions cinematic trailer, movie trailer ad, epic trailer, 60-second trailer, brand trailer, narrative video with VO, Drive-style video, Sicario-style trailer, multi-scene story video, "make me a trailer," "build a trailer," "trailer for my brand," "movie ad," "epic ad," or any request for a polished cinematic short-form video with narration, music, and a story arc. Also trigger when user wants to combine AI video generation (PAI / UTOPAI), ElevenLabs voiceover, and music into one finished piece. Encodes the full pipeline we built and the painful lessons learned — PAI content filter pitfalls, character drift workarounds, the editorial pass with color grade + music duck + VO mix, proper trailer pacing. Over-trigger — if the request smells like "epic cinematic video with a story," use this.
vaibhav-template
by GraehamwattsTurn any script into a Vaibhav Sisinty-style talking-head video for Graeham Watts — the visual formula reverse-engineered from @vaibhavsisinty's 1.7M-follower Instagram reels. Fires on "run this script through the template I love", "make this Vaibhav-style", "use my video template", "convert to Vaibhav format", "add the warm desk aesthetic", "put this in my rotation", or any request to produce a video where Graeham's face appears with the burned-in visual system (locked talking-head, fast front-loaded cuts, serif-italic captions, color-highlighted keywords, emoji pop-ins). Encodes Graeham's 5 pre-generated warm-lit avatar looks (rotate across videos for variety without breaking brand consistency), the 5-mode composition system, cut pacing arc, and typography specs. Hands script + look off to heygen-video for rendering and higgsfield-video for B-roll. Use this instead of freestyling a HeyGen render when the user wants the Vaibhav aesthetic.
contract-estimate-builder
by GraehamwattsContract Estimate Builder for Graeham Watts. Turns a plain-language list of property work tasks into a clean Excel bid sheet (with auto-calculating formulas) plus a PDF scope of work (with a comprehensive courtesy disclaimer) that can be emailed to a contractor for pricing or shared with a client. Trigger ANY time the user mentions: contract estimate, contractor bid, scope of work, SOW, bid sheet, contractor quote, send to contractor for pricing, itemize a job, itemize landscaping/repairs, write up the scope, punch list, prep list, listing prep scope, vendor scope, handyman/landscape/painter/cleaning scope, bid request, or RFQ. Also trigger when the user describes work tasks at a property and wants them organized for a contractor to price, mentions alternative options that need separate pricing (bark vs. flagstone vs. mulch), or says 'put this in a spreadsheet for my contractor.' Supports multi-option line items with a separate grand total per scenario.
watts-motion-graphics
by GraehamwattsWatts-brand motion-graphics overlay generator for Graeham's videos. Produces chroma-key-ready Remotion overlay projects that composite on top of HeyGen avatar + Higgsfield b-roll in CapCut. Use ANY time the user mentions: motion graphics, video graphics, overlay graphics, stat callout, compare card, decision framework graphic, HERO reveal, lower third, title card, end card, chroma key graphics, green screen graphics, Remotion overlay, graphics for CapCut, animated text reveal, big number graphic, side-by-side compare, framework card, or anything related to motion graphics layered on a HeyGen + b-roll video. Also trigger on 'motion graphic for that scene', 'animate that stat', 'do another motion graphic', or recreating visual style from a previous Watts video. CRITICAL: renders on pure green #00FF00, NOT black + Screen blend (Screen blend turns text translucent). Locks brand tokens, Syne Bold + Inter typography, and 5 templates (Stat Callout, Compare Card, Decision Framework, HERO Reveal, End Card).
higgsfield-video
by GraehamwattsGenerate AI b-roll video clips on higgsfield.ai by driving Claude in Chrome to execute a two-stage pipeline — Nano Banana Pro OR GPT Image 2 generates a start frame, then Seedance 2.0 or Kling 3.0 animates it into an image-to-video clip. Use ANY time Graeham mentions higgsfield, b-roll, AI b-roll, "make me b-roll", cinematic b-roll, drone shot, aerial shot, cutaway, transition clip, Nano Banana, GPT Image 2, gpt-image-2, ChatGPT Images 2, listing card overlay, "For Sale" sign, address number on image, signage shot, text-in-image, Seedance, Kling, image-to-video, or any request to produce a short AI video clip for inserts, transitions, or visual establishment in his real estate video content. Also trigger on follow-ups like "continue the higgsfield skill", "do another b-roll", "try a different motion", "regenerate with changes", or when iterating on a previously generated clip.
heygen-video
by GraehamwattsGenerate HeyGen avatar videos of Graeham Watts using his trained digital twin and photo-avatar looks. Use ANY time the user mentions HeyGen video, avatar video, AI avatar, talking head video, video of me, video of Graeham, listing intro video, market update video, personalized video message, buyer Q&A video, seller update video, "make me a video", "render a HeyGen video", "create an avatar video", or turning a script into a finished video with Graeham's face and voice. Also trigger on follow-ups like "check on that HeyGen video", "is the video ready", "download the avatar video", or when resuming a previously submitted HeyGen job via video_id. This skill is the CORRECT CHOICE for any HeyGen output — do not use video-creator (slideshow) or remotion-video (React) for HeyGen avatar work. Pair with content-creation-engine when the user has a topic but no script yet.
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.