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...
gaps
by sureservermanUse when the user asks to find content gaps in their Obsidian vault, missing pages, topics that should have a dedicated note, or mentions "/obsidian-wiki:gaps". Trigger on "what's missing from my wiki", "find topics I should write up", "any gaps in my notes", or "entities I keep mentioning but don't have a page for".
amo-compliance-check
by sureservermanUse when checking a Firefox extension for addons.mozilla.org (AMO) submission compliance, before packaging or publishing a Firefox WebExtension. Trigger on "AMO rejected my addon", "prep this addon for mozilla", "check firefox extension for AMO", "is this extension signable", "will AMO accept this manifest".
mock-server-from-app-sources
by sureservermanUse when the user asks for a mock server, fake API, or stub backend based on an app's sources. Trigger on "make a mock server for this app", "I need a fake API for testing", "this app needs a backend for UI tests", or when an app requires login/REST/GraphQL and no mock exists yet.
game-feel-and-juice
by sureservermanUse when tuning the moment-to-moment responsiveness, "game feel", or "juice" of a game — input handling, controller feel, jump feel, hit feedback, screen shake, hitstop, easing curves, particle feedback, animation snappiness. Triggers on "improve game feel", "the jump feels off", "controller feels mushy", "tune the controller", "add juice", "the combat feels weak", "hits don't feel impactful", "input lag", "input feels delayed", "add coyote time", "add jump buffer", "add screen shake", "tune dead zones". Also triggers on `*controller*` / `*input*` / `*camera*` file edits in a game project. Grounded in Steve Swink (Game Feel) and platformer-feel best practices.
rust-coding
by sureservermanUse when authoring, scaffolding, refactoring, or reviewing Rust code. Triggers on greenfield requests like "create a Rust app", "new Rust project", "scaffold a Rust crate", "cargo new", "start a Rust library", "build a Rust binary that...", or any "in Rust" / "using Rust" request to build from scratch. Also triggers on `*.rs` edits, `Cargo.toml`/`Cargo.lock` changes, `unsafe` blocks, `async`/`tokio` code, FFI bindings (`extern "C"`, `#[repr(C)]`, cxx, bindgen), `serde` derives, `thiserror`/`anyhow` error enums, `clippy` warnings, borrow-checker errors (E0382, E0502, E0505, E0597, E0716), and edition 2024 migration. Also triggers on questions like "is this idiomatic Rust", "Arc or Rc", "thiserror or anyhow", "is this unsafe sound", "tokio deadlock".
engine-unreal
by sureservermanUse when authoring or reviewing Unreal Engine 5 projects — C++ gameplay code, Blueprints, GameMode, GameState, PlayerController, Pawn/Character, PlayerState, Subsystems, replication, .uproject configuration. Triggers on edits to `*.cpp`/`*.h` inheriting from `AActor`/`APawn`/`AGameModeBase`/`APlayerController`/`UGameInstance`, `*.uasset`, `*.umap`, `*.uproject`. Also on natural-language prompts like "Unreal gameplay framework", "GameMode vs GameState", "PlayerController vs PlayerState", "Blueprint vs C++", "Unreal Subsystem", "Unreal replication", "UE5 architecture review", "Pawn possession". Grounded in Epic's official Unreal Engine 5 documentation (dev.epicgames.com).
game-mechanics-design
by sureservermanUse when designing, balancing, or reviewing core game mechanics, the core game loop, compulsion loops, progression, or FTUE (first-time-user experience). Triggers on greenfield mechanic-design requests like "design a core loop", "design a mechanic", "what's the core loop here", "balance this", "design the onboarding", "design progression", "how should this game feel session to session", "design a roguelike loop", "design a survival loop", "design FTUE". Also triggers on review requests like "is this loop shallow", "does this mechanic have depth", "audit the onboarding flow", "why does this game feel grindy", "compulsion loop review". Grounded in Schell, Sylvester, and Nystrom.
build-readiness-check
by sureservermanUse to audit whether the current project is ready to be built and published by the three pipelines under `~/dev/infra/`: `utils` (Debian `.deb` via `pkgskel` + `reprepro`), `build-for-mac` (Rust → macOS `.pkg` via GitHub Actions), and `publish-images` (multi-arch Docker → DockerHub/GHCR/Quay/ GitLab/ECR). Read-only. Reports per pipeline whether the project is READY / PARTIAL / NOT-READY with the exact missing files or registration entries. Trigger on "is this project ready to publish", "check build readiness", "what's missing for the deb build", "audit my mac/ layout", "is this image registered with publish-images".
goodbye
by sureservermanFrontmatter name does not match the directory name — discovery breaks.
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.