381,784 Collected SKILL.md files

Explore AI Agent Skills & Claude Prompts

Discover open-source agent skills for Claude Code, Codex, ChatGPT, and any tool that uses SKILL.md.

search
expand_more
Active:
igptai
Showing 12 of 46 skills
igptai

purchase-order-tracker

by igptai
star 16

Tracks every purchase order referenced in email — what has been ordered, from which supplier, at what price, whether it has been confirmed, shipped, delivered, or invoiced. Use when a procurement manager wants a real-time view of all active POs without checking a separate system. Triggers on "purchase order status", "PO tracker", "what orders are outstanding", "order status", "has my order been confirmed", "purchase orders".

navigation main article SKILL.md
schedule Updated 1 month ago
igptai

client-preference-miner

by igptai
star 16

Extracts everything a client has expressed about their property preferences from email — must-haves, deal-breakers, nice-to-haves, budget signals, neighbourhood preferences, and reactions to properties seen — so the agent has a complete preference profile without relying on memory. Triggers on "client preferences", "what does the client want", "preference profile", "client wish list", "what have they said they want", "client requirements".

navigation main article SKILL.md
schedule Updated 1 month ago
igptai

commission-agreement-tracker

by igptai
star 16

Finds every commission agreement, referral fee arrangement, and co-brokerage split referenced in email — tracking the agreed rates, parties involved, conditions, and whether payment has been confirmed. Use when an agent or broker wants to ensure all commission arrangements are documented and no payments are missed. Triggers on "commission agreements", "referral fees", "co-brokerage splits", "commission tracker", "who do I owe a referral fee", "commission arrangements".

navigation main article SKILL.md
schedule Updated 1 month ago
igptai

deal-pipeline-tracker

by igptai
star 16

Tracks every active real estate deal from email — where each transaction stands, what the next step is, which parties are involved, and what is stalling. Use when a real estate agent or broker wants a full pipeline view without manually checking every thread. Triggers on "deal pipeline", "active deals", "transaction status", "where are my deals", "deal tracker", "pipeline overview".

navigation main article SKILL.md
schedule Updated 1 month ago
igptai

data-source-tracker

by igptai
star 16

Tracks every data access request, dataset agreement, data sharing arrangement, and data source dependency referenced in research email threads — what has been requested, what has been approved, what is still pending, and what data access could be blocking research progress. Use when a researcher wants to know the status of all their data access requests and agreements. Triggers on "data access requests", "dataset agreements", "data sharing status", "what data are we waiting for", "data access tracker", "research data pipeline".

navigation main article SKILL.md
schedule Updated 1 month ago
igptai

client-deliverable-tracker

by igptai
star 16

Tracks every deliverable committed to across active consulting engagements — what has been delivered, what is outstanding, what is overdue, and what feedback is still open. Use when a consultant or agency wants a full view of all client deliverable commitments without manually reviewing every thread. Triggers on "client deliverables", "what have I promised to deliver", "outstanding deliverables", "what is due to clients", "deliverable tracker", "what am I behind on".

navigation main article SKILL.md
schedule Updated 1 month ago
igptai

it-vendor-commitment-tracker

by igptai
star 16

Tracks every commitment made by IT vendors and managed service providers from email — support SLA promises, implementation timelines, patch delivery commitments, uptime guarantees, and training deliverables — surfacing those that are unverified or at risk of being missed. Use when an IT manager wants to hold technology vendors accountable to what they committed. Triggers on "IT vendor commitments", "what has the vendor promised", "vendor SLA commitments", "MSP commitments", "vendor accountability IT", "what support did they promise".

navigation main article SKILL.md
schedule Updated 1 month ago
igptai

client-feedback-collector

by igptai
star 16

Collects and structures all client feedback received across consulting engagements — formal feedback, informal reactions, satisfaction signals, and criticism — so the consultant has a consolidated view of how each client perceives the work. Use when a consultant wants to understand their client satisfaction landscape. Triggers on "client feedback", "what are clients saying about the work", "satisfaction signals", "collect feedback", "how happy are my clients", "client reactions".

navigation main article SKILL.md
schedule Updated 1 month ago
igptai

client-offer-history

by igptai
star 16

Reconstructs the complete offer history for a specific client from email — every offer made, at what price, on which property, what the outcome was, and what feedback was received. Use when an agent wants to brief a client on their offer history or prepare strategy for a new offer. Triggers on "client offer history", "what offers have we made", "offer history", "previous offers", "offer track record", "what happened with past offers".

navigation main article SKILL.md
schedule Updated 1 month ago
igptai

listing-expiry-tracker

by igptai
star 16

Finds every active listing agreement referenced in email and surfaces those approaching expiry — including the expiry date, notice requirements, and whether the seller has indicated intent to renew or withdraw. Use when an agent wants to proactively manage listing agreement renewals before they lapse. Triggers on "listing expiry", "listing agreements expiring", "listings coming up for renewal", "which listings are expiring", "listing renewal", "expiring listings".

navigation main article SKILL.md
schedule Updated 1 month ago
igptai

vendor-coordination-tracker

by igptai
star 16

Tracks every outstanding vendor coordination item across active transactions — inspectors, appraisers, contractors, title companies, lenders, and attorneys — surfacing what has been scheduled, what is pending, and what is blocking a transaction. Use when an agent wants to ensure all third-party coordination is on track across their deals. Triggers on "vendor coordination", "third party status", "what's pending with vendors", "inspector scheduler", "transaction vendor tracker", "who have I not heard back from".

navigation main article SKILL.md
schedule Updated 1 month ago
igptai

collaboration-commitment-tracker

by igptai
star 16

Tracks every commitment made across active research collaborations from email — data sharing promises, co-authorship agreements, analysis contributions, review commitments, and meeting obligations — surfacing those that are unmet or at risk. Use when a researcher wants to hold collaborators accountable and ensure their own commitments are on track. Triggers on "collaboration commitments", "what have collaborators promised", "co-author obligations", "research partnership commitments", "what am I on the hook for with collaborators", "collaboration tracker".

navigation main article SKILL.md
schedule Updated 1 month ago
Page 1 of 4

Browse Agent Skills by Occupation

23 major groups · 867 SOC occupations

Browse by Category

Explore agent skills organized by their primary use case

SKILLMD / CREATORS AND OCCUPATION CATEGORIES

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.

SEO KNOWLEDGE HUB & TECHNICAL OVERVIEW

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.

8 QUESTIONS

Frequently Asked Questions

A practical guide to agent skills: what they are, how to inspect them, and how SkillMD helps you explore the ecosystem.