Agent skill · software engineering · browser-use
remote-browser
Controls an isolated Browser Use Cloud browser from a sandboxed machine with the current Browser Use CLI.
Why this skill is useful
Adds specific commands for controlling a headless browser in a sandboxed environment that the AI wouldn't generate on its own.
What it needs
Requires browser-use installed locally. About 1k tokens when loaded. Last updated 2026-08-06. 108,113 stars on the source repository.
What this skill does
Remote Browser Use this skill when an agent runs on a machine without a usable local Chrome and needs an isolated browser. The current Browser Use CLI runs Python from stdin. Do not use the removed open, state, click, input, tab, cloud connect, or --connect commands. Check the CLI If setup fails, follow the current Browser Use skill. Start an isolated browser Authenticate once: Pick a short unique name. r7k2 below is only an example. Use the same name for every command in this browser: Each remote daemon is a separate Browser Use Cloud browser. Use a different name for each parallel task. Remote browsers can bill until they stop or time out. Inspect and interact Helpers are pre-imported. Keep multi-step work in one heredoc when practical. Useful helpers: Navigate: newtab(url), gotourl(url), waitforload() Inspect: pageinfo(), js(code), cdp(method, ...) Interact: clickatxy(x, y), typetext(text), fillinput(selector, text), presskey(key), scroll(x, y) Tabs: listtabs(), switchtab(target), closetab(target) Files and proof: capturescreenshot(), waitforelement(selector) Prefer the accessibility tree for element discovery: Use a targeted js(...) query when the accessibility tree lacks the element. Verify each action with pageinfo(), a focused DOM check, or a screenshot. Stop the browser When the work is done, stop the exact named browser: Do not leave an unused remote browser running.
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills browser-use/remote-browser