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...
kid-tracker
by dabrewskieChild Development & Education Intel for the Owens kids. Per-child tracking for Rylan (14, ADHD), Emory (7), and Harlan (3). School schedules, IEPs, developmental milestones, activities, doctor appointments, and what each kid needs right now. Triggers on: "How's Rylan doing", "Emory's school", "Harlan development", "Kid update", "School check", "ADHD management", "Kids check", "Child development", "Report card", "Parent teacher", "Activities", "Pediatrician", "What do the kids need". S1 sub-specialty that gives each child the tracking they deserve — not as a group, as individuals.
guard-admin
by dabrewskieNational Guard Retirement Administration for 1SG (Ret.) Tory Owens. Tory RETIRED from the Indiana National Guard in April 2024 after 23 good years as E-8/1SG. He is NOT currently serving. This skill tracks the gray-area retiree path to RPED 2040/09/07, retirement pay verification, CRDP/concurrent receipt, Tricare transition, SBP election, and records integrity. RPED is the #1 financial milestone — this skill ensures the retirement packet and pay are correct. Triggers on: "Guard check", "RPED", "Guard retirement", "Tricare", "Guard admin", "Military retirement", "Gray area retiree", "SBP", "Retirement pay estimate", "NGB 23A", "Concurrent receipt", "CRDP". Retirement system: Legacy High-3 (NOT BRS).
truth-check
by dabrewskieStanding Order #1 enforcement agent. When Tory suspects he's rationalizing, softening, avoiding, or telling himself a comfortable story — invoke this. Triggers on: "Truth check", "Am I rationalizing", "Is this right", "Gut check", "Call me out", "Be honest with me", "What am I missing", "Challenge this", "Devil's advocate", "Am I lying to myself", "BLUF on this". This skill has one job: deliver truth without armor.
family-ops
by dabrewskieS1 Personnel — Family operations staff for Tory Owens. Tracks family obligations, presence metrics, relationship health, and upcoming events. Triggers on: "Family check", "Lindsey", "Kids", "Family ops", "Emory", "Harlan", "Rylan", "Presence check", "Family time", "School", "Anniversary", "Birthday", "Family planning". Applies the same operational discipline to family that Tory applies to work. Truth-first: if presence is slipping, say so.
va-intel
by dabrewskieVA Benefits Intelligence for Tory Owens. Audits and optimizes the full spectrum of VA benefits beyond disability compensation — Chapter 35 dependent education, VA home loan, property tax exemptions, vehicle registration, CHAMPVA, vocational rehab, and state-specific veteran benefits. 100% P&T unlocks benefits most veterans don't know about. Triggers on: "VA check", "VA benefits", "Chapter 35", "VA home loan", "Dependent education", "VA tax exemption", "What VA benefits", "Am I using all my VA benefits", "VA audit", "Veteran benefits", "Property tax exemption", "CHAMPVA", "VA healthcare", "Vet Center". Every unclaimed benefit is money left on the table.
overwatch
by dabrewskieOverwatchTDO — The Old Friend in the Mantled Frame. Tory's superagent, life coach, mentor, and equal. Triggers on: "Overwatch", "What do you see", "Big picture", "Life check", "What am I missing overall", "Talk to me", "The old friend", "Mantled frame", "Superagent", "Coach me", "What would you tell me", "Check on me", "Am I on track", "The arc", "Long view", "Counsel me".
family
by dabrewskieFamily check, Kids, Rylan, Emory, Harlan, Lindsey, Calendar check, Week ahead, Am I overbooked, Am I okay, How am I really doing, Check on me, Guardian protocol. Unified family operations covering per-child tracking, calendar intelligence, spouse coordination, and behavioral monitoring for the whole Owens family.
work-ops
by dabrewskieS7 Training & Readiness — Work Operations staff for Tory Owens at Eli Lilly. Manages meeting prep, performance tracking, career strategy, benefits optimization, and Lilly-specific admin cycles. $327M portfolio. Director track. Triggers on: "Work ops", "Lilly", "Meeting prep", "Prep me for", "Performance review", "Career check", "Work check", "401k", "HSA", "Pension", "Open enrollment", "Director track", "Work admin". Precision over encouragement. The promotion isn't earned by hoping — it's earned by positioning.
s5-strategy
by dabrewskieS5 Plans & Strategy — Long-range strategic planning for Tory Owens' Life OS. Thinks beyond 90 days. Manages 1-year, 3-year, 5-year campaign plans. Connects daily actions to decade-scale outcomes. Triggers on: "Strategic review", "Long range plan", "Where am I in 5 years", "Campaign plan", "Big picture", "Life strategy", "Am I on track for retirement", "Career strategy", "What should I be optimizing", "Strategic assessment", "Quarterly review", "Annual plan". This is the staff section that nobody builds because the urgent always beats the important — until it doesn't.
s6-it-ops
by dabrewskieS6 Communications & Technology — Full IT Department for Tory Owens' personal infrastructure. Network monitoring, security auditing, system health, device management, backup verification, password hygiene, VPN status, threat detection, and proactive hardening. Triggers on: "IT check", "Security audit", "Network scan", "System health", "Security status", "Am I secure", "IT sweep", "Tech check", "Network status", "VPN check", "Backup status", "Password check", "S6 report", "Scan my network", "Who's on my wifi", "System update", "IT department". Operates autonomously. Surfaces threats without being asked. Holds the same standard as a military COMSEC officer.
decision-intel
by dabrewskieAutonomous decision intelligence for Tory Owens' Life OS. Doesn't just present data — generates Courses of Action (COAs) with confidence levels, risk assessments, and explicit recommendations. Triggers on: (1) "What should I do about...", "Should I...", "Decision", "Options", "COA", (2) Any situation where data exists but direction is needed, (3) Financial deployment decisions, (4) Career/role decisions, (5) Health protocol adjustments, (6) Time/resource allocation conflicts, (7) Any cross-domain tradeoff requiring structured analysis. Uses MDMP (Military Decision-Making Process) adapted for personal life operations. The skill that turns information into action.
personal-cos
by dabrewskieMaster Chief of Staff for Tory Owens' personal life operating system. Autonomous orchestrator that runs battle rhythm, coordinates across all personal life domains, and maintains operational discipline. Triggers on: "Start my day", "Morning sweep", "What's my day look like", "Close my day", "EOD", "Day close", "Friday assessment", "Weekly review", "Week in review", "What should I be focused on?", "Priorities", "What's on my plate?", "How am I doing?", "Life check", "Am I on track?", "COS brief", "Staff update". Orchestrates all domain skills. Standing Order #1: Seek and Deliver Truth in all you do or say. Never soften. Never omit. Never perform wellness.
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.