browser-use

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the agent needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information.

The browser-use skill teaches your agent the Browser Use CLI. The CLI runs Python in the browser to do actions online. The agent can connect to your real Chrome, preserving logins, or to a Browser Use cloud browser.

Install

Install or upgrade browser-use with `uv tool install --python 3.12 --upgrade --force 'browser-use @ git+https://github.com/browser-use/browser-use.git'`, run `browser-use skill install`, and connect it to my browser. Follow https://github.com/browser-use/browser-use if setup or connection fails.

Links

skills.sh

Source