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...
apple-music-control
by aladacControl Apple Music playback via osascript — play, pause, shuffle, search library, playlists, volume. Automatically pauses Spotify when starting Apple Music playback. <example> Context: User wants to play Apple Music user: "play something on Apple Music" </example> <example> Context: User wants a specific playlist user: "play my rock playlist on Apple Music" </example> <example> Context: User wants to search their library user: "find Metallica in Apple Music" </example> <example> Context: User asks what's playing user: "what's playing on Apple Music?" </example>
poster
by aladacGenerate a cinematic landscape poster — image on the left, styled text on the right. Dark military aesthetic: navy background (#080c12), orange accent (#e8872b), light text (#c8d4de). Uses DIN Condensed Bold for titles and DIN Alternate Bold for body text. <example> Context: User wants to create a poster from an image and text user: "Make a poster from this mech image with the Protocol 3 speech" assistant: "I'll use the poster skill to generate it." <commentary> Image + text poster generation — the poster skill handles layout, fonts, and color scheme. </commentary> </example> <example> Context: User provides paragraphs separately user: "Create a poster with these 3 paragraphs and this background image" assistant: "I'll use the poster skill with separate paragraph inputs." <commentary> Multiple paragraphs get proper spacing — use --p1 through --p4 flags. </commentary> </example>
android-adb
by aladacUse for Android device operations via ADB on the Moto G52. Accessible via WiFi (192.168.88.155:5555) or USB through junkpile. Screenshot capture, input automation, app management, file transfer, and device control. <example> Context: User wants a phone screenshot user: "take a screenshot of the moto" </example> <example> Context: User wants to install an app user: "install this APK on the phone" </example>
protocol-5-backup
by aladacVerify all Protocol 5 backup destinations in a single pass. Checks local storage, Documents, Git LFS, Google Drive (both accounts), Moto G52, 1Password, database health, and size anomalies across fuji and junkpile. <example> Context: User wants to check backup status user: "check the backups" </example> <example> Context: User asks about Protocol 5 user: "how are the Protocol 5 backups doing" </example> <example> Context: Daily verification user: "run backup verification" </example>
moto-kitty
by aladacStart, stop, and check status of the SERE Kitty X11 stack on the Moto G52. Manages the full launch sequence: Termux X11 server, Android X11 activity, Openbox WM, and Kitty terminal. <example> Context: User wants to start Kitty on the Moto user: "start kitty on the moto" </example> <example> Context: User wants to stop the SERE display user: "stop the moto display" </example> <example> Context: User wants to check if Kitty is running user: "is kitty running on the moto?" </example>
eve-local-reference
by aladacLook up EVE Online mission guides, combat anomalies, and escalation chains from local offline files. Covers 159 L4 missions (eve-survival) and 26 Guristas hisec combat sites (EVE Uni Wiki). <example> Context: User asks about a mission user: "look up Gone Berserk" </example> <example> Context: User asks about a combat anomaly user: "what's in a Guristas Den?" </example> <example> Context: User wants escalation info user: "show me the Guristas escalation chain" </example> <example> Context: User wants specific DED site user: "look up the 4/10 scout outpost" </example>
latex-cv-documents
by aladacBuild LaTeX CVs, cover letters, and generate skill pill images. Manages Adam's CV at ~/Projects/cv/ with pdflatex, ImageMagick pill generation, and fswatch auto-rebuild. <example> Context: User wants to build the CV user: "build my cv" </example> <example> Context: User wants to create a new skill pill user: "generate a pill for Terraform" </example> <example> Context: User wants to see the CV user: "open my cv" </example> <example> Context: User wants to build a cover letter user: "build the cover letter" </example>
google-calendar
by aladacManage Google Calendar events via gog CLI. Multi-account (chi@sazabi.pl, adam.ladachowski@gmail.com). Shortcuts for today, tomorrow, week. Use today-all/week-all for both accounts. <example> Context: User asks about their day user: "what's on my calendar today?" </example> <example> Context: User asks about the week user: "what does my week look like?" </example> <example> Context: User wants to create an event user: "add a meeting tomorrow at 2pm" </example> <example> Context: User searches for an event user: "when's the dentist appointment?" </example> <example> Context: User checks all accounts user: "anything on any calendar today?" </example>
code-rust-tooling
by aladacRust linting (clippy), formatting (rustfmt), type checking (cargo check), coverage (tarpaulin), and CI validation. <example> Context: User wants to set up linting user: "configure clippy pedantic for this project" </example> <example> Context: User needs to validate their project user: "run all checks on this rust project" </example>
dotfiles-management
by aladacManage dotfile symlinks and sync to GitHub. Links config files from ~/Projects/dotfiles/ to ~/, commits changes, pushes to GitHub, and pulls on junkpile to keep both machines in sync. <example> Context: User wants to check dotfile status user: "check my dotfiles" </example> <example> Context: User changed a config and wants to sync user: "sync dotfiles" </example> <example> Context: User wants to add a new config to management user: "add my tmux config to dotfiles" </example> <example> Context: User wants to fix broken symlinks user: "fix my dotfile links" </example>
job-scout
by aladacMulti-source job search aggregator. Scans Gmail, NoFluffJobs, Just Join IT, RubyOnRemote, HN Who's Hiring, and more for senior Ruby/Rails roles. Scores matches, tracks pipeline, manages watchlist. <example> Context: User wants to find new jobs user: "scout for jobs" </example> <example> Context: User wants to check email for recruiter messages user: "check my job inbox" </example> <example> Context: User wants to analyze a specific posting user: "review this job posting" </example> <example> Context: User wants a status update user: "job report" </example> <example> Context: User wants to score a job description user: "score this job against my criteria" </example> <example> Context: User wants to track a company user: "add Shopify to my job watchlist" </example>
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.