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...
tend-pr
by paulchiuMaintain one open PR until merge or timeout: rebase onto main, diagnose CI/build failures, push fixes. Use for tend, caretake, babysit, shepherd, monitor, watch, keep alive, or keep green/mergeable.
translate-to-taiwan-chinese
by paulchiuTranslate text into Taiwan Traditional Chinese for a non-technical 70-year-old parent. Use when asked to translate or localise for a Taiwanese elder, 'for my mum/dad', '繁體中文', or '正體中文'.
branded-deck-builder
by paulchiuCreate polished branded decks, presentation slides, bento promo slides, and short shareable presentation videos in the me&u engineering visual style. Use when asked to make or modify a branded deck, PowerPoint, Google Slides-inspired presentation, executive/update deck, bento summary slide, Spotify Wrapped/Rewind-style animation, or team-shareable promo asset using the referenced me&u brand colors, typography, frosted tiles, and diagonal-background style.
bk-buildkite
by paulchiuQuery Buildkite builds, jobs, logs, pipelines, and agents via the bk CLI. Use when investigating CI failures, reading build logs, retrying builds, or any Buildkite interaction.
ast-grep
by paulchiuWrite ast-grep rules for structural code search using AST patterns. Use when searching for code patterns, language constructs, or queries beyond text search.
reviewing-candidates
by paulchiuAnalyses resumes and interview transcripts, then crafts professional recruiter feedback. Use when reviewing a candidate's resume, writing interview feedback, or drafting hiring decisions.
personal
by paulchiuRouter for personal-life tasks and tools. Use when asked to convert a workout/gym log into Dataview-compatible fitness logs; prepare Dad's monthly family money report from ANZ exports and journal details; archive monthly Obsidian vault items from Area/Projects to Archive (with attachments); audit current branch changes for AGENTS.md conformance and auto-fix violations; clean up stale Codex/ChatGPT desktop state (dead project picker entries, invalid env refs, obsolete worktrees); refine an aichat role prompt (committer, pr-writer, etc.) based on output feedback; or translate text into Taiwan Traditional Chinese for a non-technical 70-year-old parent ("for my mum/dad", "繁體中文", "正體中文").
nex
by paulchiuManage Nex terminal workflows with the nex CLI. Use when asked to split, create, close, move, rename, capture, or send to panes; manage workspaces, groups, layouts, file opening, or diffs; show Codex progress/status in Nex; broadcast a command to all panes in a group; or delegate work to live Nex panes using cxd/ccd agent aliases. Trigger phrases include "delegate to Nex pane", "Codex pane", "Claude pane", "ccd", "cxd", "split pane", "send to pane", "send to group", "broadcast to panes", "broadcast to <group>", "nex broadcast", "all panes in group", "capture pane", "open in Nex", "Nex indicator", or "Nex status".
review-code
by paulchiuEnd-to-end PR review: create a worktree, run a principal-engineer branch review, run a hostile adversarial second pass, optionally apply a persona focus-lens, optionally delegate an outside-view round to a Codex/cxd Nex pane, archive a decision doc to ~/dev/sandbox, and only post inline comments / approve / request changes when the user explicitly ticks actions. Use on `/review-code`, 'review this PR', 'review the branch', 'branch review', 'reviewing branch changes', 'adversarial review', 'hostile review', 'review as <name>', 'persona-based review', or when given a PR number/URL.
ebook-naming
by paulchiuRename epub files to match Paul's personal ebook naming convention. Use when asked to rename, organize, or clean up ebook files (epub or pdf). The convention for naming is: Title - Subtitle. LastName, FirstInitial. Year.ext (omit subtitle if none). No publisher, no hash IDs, no Anna's Archive labels.
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.