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...
track-my-renewals
by gethoustonStop getting surprised by auto-renewals. I scan your contracts and any connected drive for renewal dates, notice windows, and auto-renew language, then maintain a living renewal calendar grouped by lead-time tier so you always know what's next. I also produce a quarterly digest with negotiation candidates and anything past the cancel window.
evaluate-a-candidate
by gethoustonScore a candidate against an open role - paste a resume or share a LinkedIn URL and I give you a rubric score, the evidence behind it, red flags, and what to probe in interviews. Branches on `source`: `resume` or `linkedin`.
capture-my-call-notes
by gethoustonTurn a transcript or recording into structured notes: agenda actual versus intended, attendees, pains in their words, decisions, action items split internal versus external, and the next step. I match the call to the right lead, update their dossier, and only sync to your CRM with your nod.
check-my-sales-tax-nexus
by gethoustonSee where you owe sales tax. I total revenue and transaction counts per US state from Stripe (or QuickBooks / Xero / invoices as fallback), compare each state's totals against its economic-nexus threshold for the quarter and trailing 12 months, pinpoint the month each crossed state was triggered, and flag physical-nexus states (W-2 employees, offices, inventory / FBA). I rank exposure highest-dollar first and call out the closest pre-crossing states as early warnings. I prep — you register and remit through Avalara, TaxJar, or the state portal directly.
check-my-sales
by gethoustonGet a read on how your sales motion is actually doing. Pick what you need: a Monday rollup across every domain, a cross-call synthesis with playbook edits, a win-loss pattern read, a deep read on a single discovery call, or a pipeline snapshot with the leakiest stage. Every read ends with a concrete next move, not a dashboard.
prep-a-meeting
by gethoustonPrep me for a meeting in the shape that fits: a one-page call prep with the right questions for the deal's weakest qualification pillar, or an account review pack with shipped outcomes, usage trend, risks, and renewal runway. Both pull from your playbook and the deal or customer history - no generic templates.
brief-me-for-today
by gethoustonWake up with a one-screen brief: today's meetings, drafts waiting on your sign-off, the top three moves I'd make today, and your watch list of stalled deals or red customers. Calendar is the anchor; I never invent meetings.
manage-my-crm
by gethoustonRun the CRM action you need: a hygiene sweep that diffs dupes and stage mismatches without mutating, a natural-language read-only query, a routing pass that assigns GREEN, nurtures YELLOW, and drops RED, or a follow-up task pushed to your task tool. I never mutate without your per-row approval.
plan-a-trip
by gethoustonGet a trip pack drafted so you can travel without dropping the rest of your week. I assemble a trip summary, an itinerary with flight and hotel search criteria, and a packing checklist adapted to the destination and trip type. Tell me where and when; I draft, you book.
set-up-my-people-info
by gethoustonTell me how you do HR - values, leveling (IC and manager, L1-L5), comp bands, review-cycle rhythm, policy canon, escalation rules, voice, and hard nos - so I can give you sharp drafts and answers. This is the foundation doc every other people Action reads first.
track-compliance-deadlines
by gethoustonKeep a living people-compliance calendar - I-9 / W-4 status, visa renewals, vesting cliffs, review-cycle dates, policy-refresh cadence. I scan your HR system, update the calendar in place, and nudge you before things expire.
brief-me
by gethoustonGet the brief you need to walk into your day or your meeting prepared. Pick what you need: a daily roll-up of your inbox, calendar, chat, and recent docs into today's plan; a deep attendee pre-read for an upcoming meeting with agenda and likely asks; or post-meeting notes that turn a transcript into decisions, owners, and follow-ups.
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.