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...
pre-approval-email
by AStyer8345Drafts a congratulatory pre-approval email to a borrower via Outlook (Zapier). Adam uploads a pre-approval letter PDF — Claude extracts key fields and populates the hardcoded HTML template, then creates an Outlook draft for Adam to review and send. Use this skill whenever Adam says "pre-approval email", "send pre-approval", "draft pre-approval email", "pre-approval letter email", "borrower got approved", "got pre-approved — send them the email", or uploads a pre-approval letter PDF and wants to draft the borrower email. Also trigger on phrases like "pre-approval email for [name]", "send [name] their pre-approval email", "[name] is pre-approved send the email", or "preapproval email".
website-lead-followup
by AStyer8345Processes a new inbound lead from Adam's website (styermortgage.com) — creates a Salesforce contact with Lead Source: Web Lead, drafts a personalized follow-up email via Gmail that references the conversation, includes the loan application link, and lists the documents needed to get started. Use this skill whenever Adam provides a website lead — someone who filled out the contact form on his site and had an initial phone call. Trigger on phrases like: "website lead", "came in through the site", "web lead from [name]", "website inquiry", "they found me online", "came from the website", or any time Adam uploads a screenshot of a website form submission. This is a DIFFERENT workflow from the realtor referral intake — there is no referring agent, Lead Source is Web Lead, and the email is custom based on the phone conversation rather than a templated referral intro.
send-rate-update
by AStyer8345Paste mortgage rates into chat and send a rate update — publishes a rate page to the website and sends teaser emails via Mailchimp.
refi-analysis
by AStyer8345Builds a branded multi-page refinance analysis PDF for a borrower and drafts the accompanying email to send with it. Use this skill whenever Adam uploads an Initial Fees Worksheet (IFW) PDF from Arive and wants to present refinance options to a borrower. Also trigger on phrases like "build a refi analysis", "create a refi presentation", "refinance PDF for [name]", "put together options for [name]", "send [name] their refi options", or any time Adam is comparing two or more refinance scenarios for a client. Always use when both a Mortgage Coach screenshot and an IFW are provided together. The skill produces a polished PDF and a ready-to-send Outlook email draft.
contract-received
by AStyer8345Extracts all key fields from an executed purchase contract and generates three outputs: (1) A professional reply-all email to transaction parties (buyer's agent, listing agent, title, TCs) acknowledging contract receipt and confirming loan details, (2) A separate borrower welcome email introducing Adam and setting expectations, (3) An Arive data entry checklist with all extracted fields organized by section. Use this skill whenever Adam says "contract received", "new contract", "got a contract", uploads a purchase contract PDF, or forwards a contract email and wants to kick off the loan process. Trigger on any phrase like: "contract received — [name]", "new contract for [address]", "process this contract", "kick off [name] file", or when Adam uploads a TREC contract.
final-cd-email
by AStyer8345Generates and sends a fully populated Final Closing Disclosure (CD) email draft to Outlook via Zapier. Use this skill whenever Adam says "Final CD email" or "CD email" or attaches a Closing Disclosure PDF and asks to draft the closing email. Extracts 10 fields from the CD, populates the hardcoded HTML template, sends the draft to adam@thestyerteam.com via Outlook Drafts (Zapier), and outputs a pre-send checklist. Trigger on any phrase like: "Final CD email — [name]", "send CD email", "draft closing email", "CD is done, send the email".
new-application-received
by AStyer8345Processes a new loan application from start to finish — extracts borrower and referral info, creates Salesforce contacts with Adam's defaults, drafts a personalized intro email via Outlook (Zapier), and adds contacts to Apple Contacts without duplicates. Handles two scenarios: (1) Application already submitted — borrower has already applied, email acknowledges receipt, (2) Referral intro — borrower hasn't applied yet, email includes loan application link. Use this skill whenever Adam says "new app", "application received", "app came in", "got an application from [name]", "new borrower [name]", "process this application", "add this borrower", "[name] just applied", "set up [name] in the system", or any variation of receiving a new loan application or borrower lead. Also trigger when Adam uploads a loan application screenshot or PDF and wants to kick off the intake workflow. Even casual mentions like "[name] applied, referred by [agent]" or "Thomas sent me [name], app is in" should trigger this skill.
contract-received
by AStyer8345Extracts all key fields from an executed purchase contract and generates three outputs: (1) A professional reply-all email to transaction parties (buyer's agent, listing agent, title, TCs) acknowledging contract receipt and confirming loan details, (2) A separate borrower welcome email introducing Adam and setting expectations, (3) An Arive data entry checklist with all extracted fields organized by section. Use this skill whenever Adam says "contract received", "new contract", "got a contract", uploads a purchase contract PDF, or forwards a contract email and wants to kick off the loan process. Trigger on any phrase like: "contract received — [name]", "new contract for [address]", "process this contract", "kick off [name] file", or when Adam uploads a TREC contract.
referral-intro-email
by AStyer8345Generates a personalized referral introduction email to a new buyer lead and sends an Outlook draft via Zapier. Use this skill whenever Adam provides a new referral lead and wants to send an intro email. Extracts lead details (name, referral source, target area, price range, timeline) and populates the hardcoded HTML template, then creates an Outlook draft for Adam to review and send. Trigger on any phrase like: "send referral intro email", "draft intro to [name]", "email the referral from [agent]", "add them as a contact and send an email", or when Adam creates a new lead contact and asks to email them.
review-request-email
by AStyer8345Drafts and sends a post-closing review request email to a borrower via Outlook (Zapier). Adam provides the borrower's name and email address — Claude populates the hardcoded HTML template and creates an Outlook draft for Adam to review and send. Use this skill whenever Adam says "send review email", "review request for [name]", "ask [name] for a review", "request a review from [name]", "send [name] the review email", "closing is done — send the review email", "review request email", "post-closing email", "[name] closed — send review request", or any variation of asking a closed borrower for a Google or Zillow review. Even casual mentions like "[name] funded, shoot them the review ask" should trigger this skill.
weekly-rate-update
by AStyer8345Generate Adam Styer's weekly rate update for real estate agents — a text message version, website landing page content with the full rate table and market commentary, and a simple teaser email that drives agents to the website. Use this skill whenever Adam mentions "rate update", "rate text", "weekly rates", "send rates out", "rate sheet", "what are rates", or anything about sending current mortgage rate information to his agent partners. Even casual mentions like "rates moved this week, let me send something out" or "here are this week's rates" should trigger this skill. Always use it when Adam provides mortgage rate data and wants to distribute it to real estate agents.
weekly-newsletter
by AStyer8345Generate Adam Styer's content + teaser emails for his mortgage business. This skill creates website landing page content (borrower + realtor versions) and simple teaser emails that drive traffic to the website. Use this skill whenever Adam mentions "newsletter", "weekly email", "send out an email", "realtor email", "borrower email", "write this week's email", "content for the site", "send something out about [topic]", or anything about creating recurring content for his mortgage database. Even casual mentions like "I need to send something out about [topic]" should trigger this skill. Always use it for any recurring email/content creation for Adam's mortgage business.
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.