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...
site-community-page
by RyanRealtyScaffolds or updates the canonical per-resort-community landing page at /lp/<community>/ on ryan-realty.com. This is the Tier 2 page in the four-tier search-authority stack (city -> community -> subdivision -> listing) and is the right producer for master-planned resort communities like Tetherow, Pronghorn / Juniper Preserve, Broken Top, Sunriver, Caldera Springs, Crosswater, Brasada Ranch, Black Butte Ranch, Eagle Crest, Aspen Lakes, Vandevert Ranch, NW Crossing-as-master-planned, Tree Farm, and River's Edge. Use this skill when Matt says "build me the Pronghorn page", "create the Sunriver community landing page", "we need a Broken Top resort LP", "set up the Caldera Springs page", or any time a resort or master-planned community needs its own search-authority landing page. Use this skill (NOT site-neighborhood-page) any time the community has its own HOA, master plan, golf course or ranked amenity, multiple sub-neighborhoods, or a recognizable resort brand. The skill outputs a Next.js dynamic route at app/l
marketing-brain-inbox
by RyanRealtyInbound-email entry point for the marketing brain. Polls the dedicated agent-facing inbox at marketing@ryan-realty.com every 2 minutes, parses each message via Anthropic Haiku, dispatches the matching producer (or routes unparseable mail to comms:matt_alert), and replies to the sender with a voice-validated confirmation. Use this skill when reasoning about how inbound email becomes a brain action, how to extend the allowlist, how to add a new action_type to the parser, or how to diagnose a stuck inbox event.
ig-single-post
by RyanRealtyCanonical renderer for Ryan Realty single-image Instagram + Facebook feed posts at 1080×1350. Handles the S1–S10 template catalog: S1 Just Listed, S2 Just Sold, S3 Open House, S4 Coming Soon, S5 Price Improvement, S6 Featured Listing of the Week, S7 Agent Intro, S8 Brag Stat, S9 Press Feature, S10 Market Data Card. Payload-discriminated by `template` field. Enforces brand typography (Amboqia display, Geist body, Azo Sans Medium accent), data accuracy, voice rules, and the #RyanRealtyBend hashtag rule. Use whenever Matt asks for "a single IG post", "just listed post", "sold post", "coming soon post", "open house post", "price reduction post", "brag stat post", "press post", "market card", or "agent intro post". For multi-slide carousels use instagram-carousel. For static print/digital flyers use flyer-design.
marketing-brain-generate-briefs
by RyanRealtyThe synthesis layer of the marketing brain. Gathers signals from all four audits plus diagnose, competitor intel, and platform trends. Synthesizes ranked opportunities. Maps each opportunity to 0-N content briefs validated against the Ryan Realty voice. Persists to content_briefs and marketing_decisions. Core logic in lib/marketing-brain/generate-briefs.ts. HTTP trigger at /api/marketing-brain/generate-briefs.
site-city-page
by RyanRealtyScaffolds or updates the city-level landing page at /lp/<city>/ on ryan-realty.com. This is the Tier 1 (top) page in the four-tier search- authority stack (city → community → subdivision → listing). The right producer for Bend, Sisters, Redmond, La Pine, Sunriver-as-a-place, Tumalo, Terrebonne, and Madras as wide-funnel city LPs. Use this skill when Matt says "build the Bend page", "create the /lp/bend/ landing page", "make the city pages for Central Oregon", or any time a Central Oregon city or town needs its own search-authority landing page above the resort-community tier. Use this skill (NOT site-community-page or site-neighborhood-page) any time the subject is a whole municipality with a city government, taxing authority, school district mention, and a city-wide MLS dataset, not a master-planned resort community. The skill outputs a Next.js dynamic route at app/lp/[city]/page.tsx with ISR 6h. The page is the broadest of the four tiers --EMDASH-- it lists every resort community + neighborhood inside the c
marketing-brain-run
by RyanRealtyTop-level marketing brain invocation. Runs the weekly cycle, dispatches all generated action items to their assigned producers in parallel, surfaces drafts for review. Use when Matt says "run the brain", "run the marketing brain", "marketing brain please", "what should we make this week", "/marketing-brain", "brain please", "brain run", "weekly brain", or any equivalent.
viral-playbook
by RyanRealtyWhat is actually working RIGHT NOW (2026) on short-form social for real estate, local-lifestyle, and AI-native content — the "what to make and why" layer. Per-platform format cheat sheet (IG Reels, TikTok, YouTube Shorts + long-form, Facebook, LinkedIn), the current hook/hold rules, winning vs dead formats, a copy-ready hook library, audio strategy, and the AI-slop line. Load this BEFORE deciding what a piece of content should be, so we make things people save and share instead of algorithmically-invisible listing tours. Pairs with tool-mastery (the how-to-build layer).
blog-post
by RyanRealtyGenerate and publish SEO-optimized long-form blog posts on Ryan Realty's AgentFire WordPress site at ryan-realty.com. full schema markup, embedded YouTube video, internal cross-links, image alt text, and the WP REST API publish path. Use this skill whenever the user requests a blog post, says "write a blog post for [topic]", "publish to the blog", "draft a blog post about [city/neighborhood/listing]", "post this to ryan-realty.com", or asks for written long-form content destined for the website. Use this skill ALWAYS when the monthly-market-report-orchestrator routes deliverable #3. Do NOT use this skill for social-media captions, email newsletters, or video-script copy. those have their own skills. The blog at ryan-realty.com is AgentFire-hosted WordPress (NOT Vercel). this is the only blog destination.
tools-registry-agentfire-wordpress
by RyanRealtyUse this skill when a task involves "WordPress REST API", "AgentFire blog", "ryan-realty.com blog", "publish blog post", "wp-json", "WordPress Application Password", "AGENTFIRE_WP_USER", "AGENTFIRE_WP_APP_PASSWORD", "featured_media", "blog-post producer", "POST /wp/v2/posts", or any task that creates, updates, or queries blog posts on the Ryan Realty WordPress installation hosted by AgentFire at ryan-realty.com.
ryan-realty
by RyanRealtyRyan Realty brand system — Bend, Oregon real estate. Two registers — heritage Americana (blue lab mascot "Jax", navy engraving-style illustrations, "It's About Relationships" tagline, yard signs/postcards) and modern web (shadcn/ui radix-nova + Geist + navy
ryan-realty-brand-voice
by RyanRealtyEnforce Ryan Realty brand voice on every piece of marketing content before publish. Use when generating, reviewing, or validating any content for publication including blog posts, social posts on any platform, email, ad copy, listing copy, video voiceover scripts, video on-screen text, flyers, signage, or website copy. Validates against the five voice attributes (trustworthy, honest, knowledgeable, professional, dependable), banned punctuation/words/phrases, and Matt Ryan's canonical writing corpus. Mandatory load for the marketing brain and any subagent generating Ryan Realty content.
comparable-grid
by RyanRealtyProduces a branded comparable-sales grid image (3x2 or 3x3 layout) showing recent closed sales used as comps for a listing or CMA. Each cell shows a property photo, address, close price, square footage, price-per-sqft, and close date. Use when Matt asks for "comparable grid", "comp grid", "show me the comps as a visual", "comp photos for the CMA", "build the comp grid for this listing", or when the CMA producer delegates this action. All data pulls live from Supabase listings table per §0 Data Accuracy rules.
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.