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...
backend-builder
by kolatheeImplements the serverside half of an approved technical brief — APIs, services, config, CMS/flags, and serverside unit tests. Use when the user says backend builder, implement backend, serverside only, or explicitly asks not to touch frontend. Never edits clientside/UI paths assigned to frontend-builder. Runs after human-approved spec-writer brief. Git branch from latest default branch (git-branch-workflow).
frontend-builder
by kolatheeImplements the UI/clientside half of an approved technical brief — components, hooks, state, and colocated unit tests. Use when the user says frontend builder, implement frontend, clientside only, or explicitly asks not to touch backend. Never edits serverside paths assigned to backend-builder. Consumes backend handoff; does not invent APIs. Git branch per git-branch-workflow.
dc-migration
by kolatheeAdd or migrate an Agoda Cronos service's appsettings to any new data center (DC). Use when the user says "migrate to [DC]", "add [DC] DC", "create appsettings for new DC", "set up appsettings.<dc>.json", "onboard to a new data center", or names any DC like MY, SG, AS, AM, HK and wants a new config created. Covers the full end-to-end workflow: duplicate config, replace DC prefixes, verify URLs via Sourcegraph and Slack, fix discrepancies, and escalate unverified URLs with direct Slack channel links and evidence.
flashcard-correction
by kolatheeUse when the user wants to correct an English sentence they wrote or said. Identifies what's wrong, explains why, and provides improved alternatives across different tones. Saves to Obsidian spaced-repetition.
flashcard-translate
by kolatheeUse when the user wants to create a Thai-to-English translation practice flashcard from a Thai sentence they want to learn to say in English. Saves to Obsidian spaced-repetition.
invest-fund-switch
by kolatheeRecord a fund switch in the Invest sheet correctly — updating D, E, F, G columns for both sending and receiving funds without double-counting.
monitor-mr
by kolatheeMR health check for GitLab merge requests: dual-mode — comment-blocker path (fetch discussions + merge status, report, then auto-chain suggest-mr-comment-resolution for threads) or pipeline path (MUST poll in the same invocation until pipeline success/failed/canceled or 45–60 min timeout — never stop early with "monitor again" or option menus while CI is still running). Summarize findings and proposed plan; STOP until user confirms before CI fix, push, or starting step 09. Use when the user says monitor MR, monitor pipeline, watch pipeline, fix pipeline, babysit MR, or software-factory step 08. Alias: monitor-pipeline (legacy name).
mr-merge-readiness
by kolatheeRead-only merge readiness check for a GitLab MR: pipeline, blocking jobs, unresolved discussions, merge status, labels, and ticket artifacts. Use when the user asks ready to merge, merge readiness, can I merge, or MR status check. Not a software-factory step — use monitor-mr (08) in the factory. Does not fix code or post comments — routes fixes to monitor-mr, suggest-mr-comment-resolution, or resolve-merge-conflict.
trip-booking-documents
by kolatheeSet up or refresh a CupOb trip folder — five core notes (Bookings, Arrival & Emergency, Itinerary, Prep, Budget), References PDFs, Trip.com/Spark import, cross-links. Trip-data only on traveler pages (no Source log, Spark IDs, or agent edit history). Use for new trips, booking sync, PDF links, VJW/emergency pages. Day plan → trip-itinerary.
trip-itinerary
by kolatheeDay-by-day trip itinerary in CupOb Obsidian — activity tables, orange/yellow photo highlights, shot/clothes refs, maps links, day summaries. Use when editing the Itinerary note, adding places per day, or adjusting table layout. Not for Trip.com PDFs or bookings (use trip-booking-documents).
trip-travel-ready
by kolatheePre-travel readiness audit for CupOb trip folders — checks References PDFs, Bookings & Documents links, prep checklist open items, hotel/flight date alignment, and produces a go/no-go summary. Use when the user asks if they are ready to travel, recheck trip plans, pre-departure review, travel readiness, or final trip check before Japan/any trip.
create-zero-pay-booking
by kolatheeTest Agoda BWZP (Book With Zero Payment) on hkg.agoda.com via headed Playwright — setup search/hotel with PAYFLEX experiments, user clicks "Book With ₹0 payment", auto-fill lead guest after 5s. Use when the user asks to test BWZP, zero payment booking, Book With 0 payment, PAYFLEX-106-BWZP, or create a zero-pay booking on Agoda.
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.