Agent Skills
Instruction packs that give your AI agent know-how. Three different kinds — pick the right one below.
✦ Standalone skills2,933
Self-contained. Install one into any project and it works on its own — no other software needed.
🧰 Tool add-ons725
Come bundled with a specific tool and only work together with it — they teach your agent how to operate that tool.
napkin
✓★ 36,200by github
Browser-based visual whiteboard for sketching ideas and collaborating with Copilot through drawings and sticky notes. Opens an interactive canvas on the user's desktop where they can draw, sketch, and add sticky notes, then share back to Copilot via a "Share with Copilot" button Reads whiteboard content through PNG snapshots (visual interpretation of sketches, diagrams, and layout) and optional JSON clipboard data (precise text from sticky notes and labels) Designed for non-technical...
game-studio
✓★ 4,000by openai
Route early browser-game work. Use when the user needs stack selection and workflow planning across design, implementation, assets, and playtesting before…
browser-act-skill-forge
★ 3,600by browser-act
Explores websites via browser-act automation and packages discoveries into callable Skill packages (SKILL.md + scripts) — execute reliably and efficiently without re-exploration. Use when: user wants a reusable Skill for any website ('create/make/build a skill for X'), needs to understand a site's internal APIs ('what endpoint does X use', 'how does X load data'), or requires batch extraction at scale (hundreds+ records — forge a Skill first, then execute reliably). Differs from browser-act:...
wp-playground
★ 208by automattic
Use for WordPress Playground workflows: fast disposable WP instances in the browser or locally via @wp-playground/cli (server, run-blueprint, build-snapshot),…
chrome-extension
★ 157by samber
Comprehensive guide for building Chrome extensions with Manifest V3. Use this skill whenever the user mentions Chrome extension, browser extension, manifest.json, content script, service worker (in extension context), popup, side panel, chrome.runtime, chrome.tabs, chrome.storage, chrome.scripting, background script, MV3, Manifest V3, or any Chrome extension API. Also trigger when the user wants to inject scripts into web pages, communicate between page and background, bypass CSP from a...
droid-control
★ 90by factory-ai
Control terminal TUIs and web/Electron apps for testing, demos, QA, and computer-use tasks. Use when you need to automate a CLI, drive a browser, record a…
rivetkit-client-javascript
★ 16by rivet-dev
JavaScript client for connecting to Rivet Actors with stateless or stateful connections. Supports browser, Node.js, and Bun environments with automatic endpoint detection via environment variables or explicit configuration Offers two interaction modes: stateless action calls for independent requests and stateful connections with real-time event subscriptions Includes low-level HTTP and WebSocket access for actors implementing onRequest or onWebSocket handlers Provides compound array-based...
browser-automation
✓★ 5by browserbase
Automate web browser interactions using MCP tools. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots,…