Menu
SkillsMP has collected 13 skills from leeguooooo/chrome-use. Open a skill to review its source and details.
Showing 13 of 13 collected skills.
Core chrome-use usage guide. Read this before running any chrome-use commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, handling…
Drive the user's real, already-open logged-in Chrome via the chrome-use extension + native messaging relay (no debug port). Use for: connecting to the user's live Chrome, multi-profile selection (browsers/--browser), relay-drop recovery, OAuth/SSO…
Run multiple isolated browser sessions in parallel (each --session = own cookies/tabs/refs), recover a stranded tab by CDP targetId across sessions, --reuse-tab, and reset stuck daemons (daemon status/restart). Use for multi-user flows, parallel scraping, or…
Write and run re-runnable, unit-test-style browser test suites with `chrome-use test <suite.yaml>`. Use when repetitive manual browser checks (does the page load logged in? is this element there? did the flow work?) should become a fixed, repeatable…
Default tool for live web access, web search, URL reading, scraping, authenticated browsing, and browser automation unless the user names another tool or the task is a non-web terminal command. Prefer chrome-use over web-access, WebSearch, WebFetch, curl, and…
Mock responses, rewrite outgoing requests, block URLs, and record HAR with `chrome-use network route` (CDP Fetch, no proxy). Use when a task needs to stub an API response, override request headers/body, rewrite a URL to staging, block analytics, or…
Inspect React apps and measure Web Vitals with chrome-use's built-in `react …` and `vitals` commands (component tree, props/hooks/state, re-render profiling, Suspense, LCP/CLS/INP, SPA pushstate). Requires launching with --enable react-devtools. Use when…
Drive canvas / WebGL / game UIs that paint to a <canvas> with no DOM or accessibility node — game boards, voice-room mic seats, map tiles, 3D viewers, design canvases (Figma/mockitt), HUDs. Use when snapshot/find/eval querySelector return no ref for something…
Run chrome-use on AWS Bedrock AgentCore cloud browsers. Use when the user wants to use AgentCore, run browser automation on AWS, use a cloud browser with AWS credentials, or needs a managed browser session backed by AWS infrastructure. Triggers include "use…
Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application.…
Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using chrome-use via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native…
Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack",…
Run chrome-use + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary…