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...
worklog-sync
by cyanluna-gitSync kanban board tasks to EOB weekly worklogs. Reads completed/in-progress kanban cards, maps them to worklog projects, estimates hours from timestamps, aggregates by day, and submits via the EOB API.
kanban-batch-run
by cyanluna-gitRun multiple kanban tasks end-to-end in Rolling Wave order — refine each task based on the prior card's actual implementation, then implement, then verify, then refine the next. Use for epic-level batch execution. --big-bang flag disables rolling wave for simple independent tasks.
kanban-explore
by cyanluna-gitCodebase exploration skill for uncertain implementation direction. Deeply explores the codebase, produces a direction report, and creates phased kanban tasks. Use when you don't know exactly how to implement something. NOT for direct implementation.
kanban-gen-wiki
by cyanluna-git프로젝트의 전체 아키텍처, 목표, 주요 결정사항을 wiki/ 디렉토리에 합성하여 정리합니다. 첫 실행 시 전체 생성, update로 변경분 반영. 매 카드가 아닌 프로젝트 수준의 지식을 정리합니다.
kanban-heartbeat
by cyanluna-gitScan kanban boards for stagnant tasks and optionally mark them. Detects tasks with no agent activity for N days (default 3), outputs a markdown report table, and appends Heartbeat entries to agent_log unless --dry-run.
kanban-init
by cyanluna-gitInitialize the current project in local SQLite kanban. Creates ~/.claude/kanban-dbs/{project}.db and writes local config. Usage: /kanban-init or /kanban-init my-project-name. Run with /kanban-init.
kanban-local
by cyanluna-gitLocal markdown-file kanban for toy and personal projects. No server, no PostgreSQL, no auth — all state lives in KANBAN.md in the project root. Use for solo/small projects where the remote kanban board is overkill. Auto-trigger when KANBAN.md exists and user says "태스크 추가", "add task", "칸반 보여줘", "다음 할 일", "task list", or similar task-management phrases. Sub-commands: init, list, add, move, done, show, edit, refine, run, rm, stats.
kanban-refine
by cyanluna-gitRefine backlog requirements through structured user interview. Turns rough task descriptions into concrete, actionable requirements with goal, scope, acceptance criteria, and edge cases.
kanban-run
by cyanluna-gitRun the AI team pipeline for kanban tasks — orchestration loop with 6 agents (Planner, Critic, Builder, Shield, Inspector, Ranger), single-step execution, and code review. Use /kanban-run to execute tasks through the 7-column pipeline. AUTO-TRIGGER when: user says "implement task NNN" or any task ID + implement/build/do combination; or user confirms with "yes/ok/go/do it" after Claude proposes implementing a specific kanban task.
kanban
by cyanluna-gitManage project tasks in a local SQLite DB (~/.claude/kanban-dbs/{project}.db). Supports task CRUD (add, edit, move, remove), board viewing, session context persistence, and statistics. For pipeline orchestration use /kanban-run, for requirements refinement use /kanban-refine. Run /kanban-init first to create the local DB.
kanban-spec
by cyanluna-gitTurn vague intent into a precise, executable spec through 5 structured phases, then optionally create a kanban task. Use when starting something new that needs proper scoping before refinement. Complements /kanban-refine (which refines existing tasks).
project-kickstart
by cyanluna-gitFull project pipeline — SRS → Plan → Tasks + TDD → Rolling Wave Execute. Use when starting a new project or major feature from scratch. Default mode is Rolling Wave (implement one → verify → refine next → repeat). Use --big-bang for old all-upfront refine style.
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.