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...
design-overdrive
by stuffbucketPushes interfaces past conventional limits with technically ambitious implementations — shaders, spring physics, scroll-driven reveals, 60fps animations. Use when the user wants to wow, impress, go all-out, or make something that feels extraordinary.
tauri-updater-signing-keys
by stuffbucketUse when managing the Tauri v2 updater's Ed25519 signing keypair — generating it with `bunx tauri signer generate -w ~/.tauri/myapp.key`, embedding the public key in `tauri.conf.json` `plugins.updater.pubkey`, wiring `TAURI_SIGNING_PRIVATE_KEY` + `TAURI_SIGNING_PRIVATE_KEY_PASSWORD` into CI secrets without committing them, and understanding the rotation constraint (old clients can never validate a new public key, so a "rotation" actually means shipping a new app version first with the new key trusted, then phasing the old one out). Pairs with [[tauri-updater]] for the broader plugin setup and [[tauri-bundling]] for OS code signing (a separate signature).
tauri-sidecar
by stuffbucketUse when bundling an external binary (Go/Rust/Python/Node) with a Tauri v2 app and running it as a sidecar process — including target-triple naming, externalBin config, shell:allow-execute permissions, stdin/stdout piping, and lifecycle (kill on app exit).
npm-trusted-publishing
by stuffbucketPublish npm packages from GitHub Actions using OIDC trusted publishing with provenance. USE FOR: setting up npm publish workflows, debugging 404/401/403 errors on npm publish, configuring --provenance, fixing 'not in this registry' errors. DO NOT USE FOR: general npm usage, installing packages, or non-GitHub CI.
ghostty-config
by stuffbucketConfigure and optimize Ghostty terminal for any machine. Use when setting up Ghostty from scratch, changing fonts/themes/keybinds, optimizing for AI coding workflows, validating config, provisioning Ghostty for a team, troubleshooting Ghostty rendering or keybind issues, handling Ghostty upgrades, or fixing SSH terminfo problems.
pages-publish-vite
by stuffbucketMonitors the GitHub Actions deployment workflow and reports the live GitHub Pages URL. Polls the workflow run status via the GitHub API, fetches Pages info, then follows curl redirects from the canonical Pages URL to discover the actual served URL. Handles GHE environments where Pages may redirect to a codespace-style randomised subdomain. USE FOR: the final step of the Pages deployment pipeline; confirming deployment succeeded; discovering the actual live URL on GHE.
tauri-sidecar-node-sidecar
by stuffbucketUse when embedding a Node.js, Bun, or Deno program as a sidecar in a Tauri v2 app — picking the right single-binary compiler (`bun build --compile` / `@yao-pkg/pkg` / `deno compile` / `nexe`), naming the output for `externalBin`, running the dev loop without compiling each iteration (Vite UI on :1420 + `bun run dev` proxy on :4142 — the pattern this repo uses), the HTTP-server-as-sidecar model with capability-free localhost, the stdin/stdout pipe alternative, and making sure the child exits with the app.
skill-eval-loop
by stuffbucketRun the observe-analyze-iterate loop on promptfoo evals for a skill collection. Promptfoo-specific — assumes promptfoo is installed, tests live in YAML, and results are in the standard SQLite DB at ~/.promptfoo/promptfoo.db. Use when the user has a promptfoo eval suite and wants to diagnose failures, fix them, and re-run targeted tests. Triggers on phrases like "eval failed", "analyze the promptfoo eval", "iterate on skills", or any request to improve skills based on promptfoo output.
tauri-sidecar-lifecycle
by stuffbucketUse when managing the lifetime of a sidecar child in a Tauri v2 app — stashing `CommandChild` in `Mutex`Option...`` managed state, draining `CommandEvent::{Stdout,Stderr,Terminated,Error}` on a `tokio::spawn` receiver, supervised restart-on-crash with exponential backoff, killing on `RunEvent::ExitRequested` (and the Windows `taskkill /T /F /PID` escalation when grandchildren survive), choosing graceful SIGTERM vs immediate SIGKILL, and HTTP health-check polling against the sidecar's port.
colima-docker-setup
by stuffbucketSet up Docker, docker compose, and docker buildx on macOS using Colima. Use when Docker Desktop is not available, Colima needs install or config, docker compose v2 plugin is missing, x86_64 emulation via Rosetta is needed on Apple Silicon, or diagnosing socket errors and slow x64 containers.
tauri-setup-prerequisites
by stuffbucketUse when installing Tauri v2 system prerequisites on a specific OS (Linux distro, macOS, Windows, Windows Server), debugging "webkit2gtk not found" / "WebView2 missing" / "link.exe not found" / broken Xcode CLT, or preparing Android/iOS targets. Pairs with the broader `tauri-setup` skill for end-to-end scaffolding.
tauri-debug-test-webdriver-e2e
by stuffbucketUse when adding end-to-end tests to a Tauri v2 app via WebDriver — installing `tauri-driver` (cargo install), the Linux `WebKitWebDriver` + `xvfb-run` headless setup, the Windows `msedgedriver` version-must-match-Edge dance via `msedgedriver-tool`, the macOS-desktop gap (no WKWebView driver), WebdriverIO vs Selenium config (`capabilities: [{ 'tauri:options': { application } }]`, port 4444), spawning `tauri-driver` from `beforeSession`/`before` and killing it on shutdown, and the GitHub Actions matrix that runs the suite headless on `ubuntu-latest` + `windows-latest`.
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.