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...
signls
by j-greigManage the signls generative MIDI sequencer. Install, launch in tmux, stop, check status, and inspect bank files. Use when composing generative MIDI sequences, launching the sequencer, managing bank files, or any task involving signls.
ghostty-control
by j-greigTERMINAL EMULATOR LAYER — control Ghostty itself, below WibWob-DOS. Uses AppleScript to act as a human at the keyboard/mouse: click blessed menu items, send keystrokes, inject shell commands, take PNG screenshots, ghost-click TUI cells. Use when: clicking a menu, sending a keystroke, restarting the TUI, smoke-testing the UI, simulating user input. NOT for: opening microapps, reading window content, or anything the HTTP API can do — use wibwobdos-control for that. Typical sequence: ghostty-control to act → wibwobdos-control to verify. macOS only. Requires Ghostty >= 1.3.0. Scripts: calibrate.sh, click-cell.sh, click-text.sh, menu-click.sh, send-to-terminal.sh, wait-for.sh, restart-wibwob.sh, ghostty-windows.sh.
discord-tui-share
by j-greigShare WibWob-DOS TUI to a Discord channel. Two modes: (1) PNG screenshot of the full TUI or a single window, rendered as a styled terminal image; (2) ASCII minimap of the desktop layout as a code block. Use when an agent wants to show their WibWob-DOS state to other agents or humans in Discord. Requires DISCORD_WEBHOOK_URL env var.
vj-timeline
by j-greigCompose and execute timed music video shows inside WibWob-DOS TUI. Declarative timeline files sync visual cues (window layout, theme changes, primer art, figlet typography) to audio playback. Use when: creating a music video, VJ show, timed visual performance, or any task that needs coordinated window choreography synced to audio. Triggers on: "music video", "VJ show", "visual performance", "timeline", "timed show", "sync to music".
chiptune-cover
by j-greigConvert well-known melodies, themes, and scores into chiptune arrangements using chiptune-studio. Takes a song reference (title, artist, or melody description), researches key/tempo/notes, makes creative arrangement decisions per scene or section, and outputs a composed WAV via chiptune-studio synthesis. Use when: user asks to "make a chiptune version of [song]", "cover [track] in 8-bit", "arrange [theme] for chiptune", "do a chiptune [song name]", or references any well-known melody that should be rendered through the chiptune-studio toolkit. Also triggers on: "soundtrack this with [song]", "score this video with a chiptune [reference]".
description
by j-greigA director-lens inspired by Michel Gondry’s public body of work and process: - handmade, practical, “visible craft” effects - playful logic, loops, repetition, and rule-based worlds - music mapped to choreography, objects, or environment “scores” - simple ideas executed with obsessive structure
wibwobdos-control
by j-greigAPPLICATION LAYER — control what runs inside Ghostty, not Ghostty itself. Talks to the WibWob-DOS HTTP API (port 8099) to open/move/read windows, check desktop state, send messages, screenshot, share to Discord, manage shaders. Use when: opening a microapp, reading a window's content, checking desktop layout, sending a command, managing shaders. NOT for: clicking menus, sending keystrokes, or interacting with the terminal emulator itself — use ghostty-control for that.
simplify-planning
by j-greigThree-pass review of planning epics, features, stories, spikes, and refactor trackers. Checks execution coherence (status fields vs reality, AC-to-test traceability, lifecycle sync), scope hygiene (stories that are actually three stories, ACs that are untestable, scope creep), and canon compliance (naming rules, checkbox format, commit conventions, closeout pass rules from AGENTS.md and .planning/README.md). Fixes issues directly. Use when the user says "simplify planning", "tidy the epics", "audit the briefs", or before closing out a feature or epic.
timeline-smoke
by j-greigSmoke test a VJ timeline end-to-end with real macOS screencapture PNGs at every cue step, plus tmux text dumps and state JSON. Capture-then-review pattern — all evidence collected first, comparison done after. Use when testing a new timeline, verifying the pipeline after code changes, or debugging cue behaviour. Triggers on: "smoke test timeline", "test the timeline", "capture each step", "screenshot each cue".
figlet-videographer
by j-greigCreate typographic video sequences using figlet text animations in WibWob-DOS. Use when composing figlet-based title cards, animated text sequences, or typographic VJ elements synced to music.
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.