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...
vendor-skill-extract
by bondigoo-adminInstall a third-party service like Pika or Higgsfield, extract its published Claude Code skills, and save them into bondigoo's own repo as owned, committed, curated skills. Use when the user says "extract skills from <service>", "add <vendor> skills", "install <vendor> like we did Pika", "find more connectors like Pika and pull their skills", "vendor in <repo>'s skills", or wants to grow the owned third-party skill library. Wraps the Vercel-Labs `skills` CLI (`npx skills add`) with bondigoo's ownership, curation, and provenance rules. NOT for authoring a brand-new bondigoo-native skill from scratch (use the native .claude/skills convention) and NOT for connecting an MCP that ships no skills repo.
iphone-short-spotlight
by bondigoo-adminUse when the user asks to build, fork, or extend a SHORT (5-9s) 2D phone-plus-text "Feature Spotlight" social post for a bondigoo feature. Trigger phrases include "create a feature spotlight for X", "short iphone feature video", "5-8 second phone video for [feature]", "spotlight for [feature]", "iphone short spotlight for [feature]", "extend the C1 / coach-go-online spotlight", "build the 2D phone+text post for [feature]", "make the parameterized feature post", "add a feature spotlight to the library". This is the SHORT 2D social spotlight (a crisp straight-on iPhone playing the real product flow plus an eyebrow/headline/4-bullet text block, 4 layouts x 3 formats = 12 comps per feature). It is the 2D sibling of the 24s 3D hero reel - distinct from it. The skill packages the founder-approved C1 "coach-go-online" recipe (parameterized FeatureSpotlight composition, a per-feature data row + frame-based mockDriver, a beat-router that composes the REAL un-edited product mocks, the cinematic-takeover that heroes the
funnel-reel-creation
by bondigoo-adminfunnel-reel-creation workflow
youtube-video
by bondigoo-adminUse when making a bondigoo YouTube video (a long-form 16:9 explainer or a 9:16 Short), or when recording / looking up our YouTube video-creation decisions. Trigger phrases include "make a youtube video", "youtube explainer for X", "produce a long-form / Short for the channel", "build the was-ist-coaching video", "record our youtube decisions". This skill is the current-truth decisions + guidelines spine for the channel; it links the publishing plan and sits on top of it. As of 2026-06-04 the decisions are: motion-graphics spine (ExplainerMotion), Gemini-TTS voiceover, standard de-DE German for YouTube reach, no sfx - and this supersedes the earlier-same-day production-concept doc wherever they disagree (see the Current-truth overrides table).
blog-to-youtube-short
by bondigoo-adminUse when turning an existing bondigoo blog post into a 9:16 YouTube Short - distill the article's single highest-value insight into a ~25-32s narrated short in our house cinematic style, with a YouTube description that links back to the article, drafted into the Social Studio for the founder to approve and native-schedule. Trigger phrases include "make a youtube short from a blog post", "turn this article into a short", "blog to youtube short", "shortsify the blog", "auto-pick a blog post and make a short", "blog-to-youtube-short". This is the YouTube sibling of `linkedin-post` (read blog -> produce one channel asset). It DELEGATES the video build to `video-short-9x16`, the copy distillation to the `linkedin-post` heuristic + `humanizer-de`, the voiceover to `youtube-voiceover.sh`, and the publish to the Social Studio + `scripts/yt-social.mjs`. NOT for building a short from scratch with no source article (use `video-short-9x16`), NOT for the big-animated-metaphor short (use `youtube-shorts`), NOT for product-
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.