Install
openclaw skills install browser-automation-skillUse Browser Relay when the user wants to control a real signed-in Chrome or Chromium browser through the published browser-relay-cli package and unpacked Browser Relay extension. Trigger for tasks like opening pages, reusing tabs, clicking, typing, scrolling, searching, taking screenshots, reading visible page content, or handling DOM-hostile sites with screenshot-guided clicks. Do not use for CAPTCHA bypass, stealth scraping, or evasion of anti-bot systems.
openclaw skills install browser-automation-skillUse this skill when the user wants real browser control through the local Browser Relay runtime.
This skill is a thin wrapper around the published npm package:
browser-relay-clihttps://github.com/jasonCodeSpace/browser-relayUse npx, not a local repo path, unless the user explicitly wants development mode.
Quick checks:
npx browser-relay-cli version
npx browser-relay-cli extension-path
npx browser-relay-cli relay-start
Tell the user to:
chrome://extensionsDeveloper modeLoad unpackednpx browser-relay-cli extension-pathThen verify:
npx browser-relay-cli status
You want extensionConnected: true.
Prefer DOM-first commands:
npx browser-relay-cli list-tabs
npx browser-relay-cli create-tab https://example.com
npx browser-relay-cli click 123456 'button'
npx browser-relay-cli type 123456 'input[name=\"q\"]' 'browser relay'
npx browser-relay-cli press 123456 Enter
npx browser-relay-cli scroll 123456 800
For DOM-hostile pages, switch to hybrid mode:
screenshotdescribe-visibleclick-at or click-at-normRead references/commands.md when you need the compact command catalog.
.env files, or local private credentials in the skill folder