How do I install the Browser Use skill?

Run npx skillmds@latest add marchatton/browser-use in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Browser Use safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: makes network calls, reads secrets. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Browser Use?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Browser Use free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Browser Use?

marchatton (@marchatton) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Browser Use by marchatton — Agent Skill

Name: Browser Use
Rating: 4.2 (5 reviews)
Author: marchatton

Browser Use

Fast, persistent browser automation via `browser-use` CLI (sessions persist across commands). Use for multi-step web workflows (open -> state -> click/input -> verify -> repeat). Supports chromium/headed, real Chrome (logged-in), and remote browser.

marchatton Updated Sep 22, 2026

File contents

browser-use

Purpose

Persistent browser session across commands.
Element index workflow: state -> act by index.

When

Need quick multi-step browser automation without writing Playwright.
Need reuse logged-in Chrome session (real browser mode).
Need parallel sessions (--session).

Install

# one-off
uvx "browser-use[cli]" open https://example.com

# permanent
uv pip install "browser-use[cli]"
browser-use install  # downloads Chromium/deps

Core Loop

browser-use open https://example.com
browser-use state                 # list elements w/ indices
browser-use click 5
browser-use input 3 "hello"
browser-use screenshot
browser-use state                 # verify + get next indices
browser-use close

Modes

browser-use --browser chromium open <url>              # default (headless)
browser-use --browser chromium --headed open <url>     # visible window
browser-use --browser real open <url>                  # your Chrome (cookies/login)
browser-use --browser remote open <url>                # cloud browser (API key)

Common Commands

browser-use open <url>
browser-use state [--json]
browser-use click <idx> | dblclick <idx> | rightclick <idx> | hover <idx>
browser-use input <idx> "text" | type "text"
browser-use scroll up|down [n]
browser-use screenshot
browser-use get <what>                                # read page/element info
browser-use back | switch | close-tab
browser-use cookies export <path> | cookies import <path>
browser-use profile list|create|update|delete
browser-use sessions
browser-use server status|logs|stop
browser-use close [--all]

Sessions

browser-use --session work open https://work.example.com
browser-use --session personal open https://personal.example.com
browser-use --session work state
browser-use close --all

Rules (agent-friendly)

Always run browser-use state before acting; indices change after navigation.
After each navigation/submit: re-run state (don’t reuse stale indices).
Prefer --headed while debugging.
Cleanup: browser-use close (or close --all) when done.

Remote Mode

Env: BROWSER_USE_API_KEY (or --api-key).

---name: browser-usedescription: Fast, persistent browser automation via `browser-use` CLI (sessions persist across commands). Use for multi-step web workflows (open -> state -> click/input -> verify -> repeat). Supports chromium/headed, real Chrome (logged-in), and remote browser.---# browser-use## Purpose- Persistent browser session across commands.- Element index workflow: `state` -> act by index.## When- Need quick multi-step browser automation without writing Playwright.- Need reuse logged-in Chrome session (real browser mode).- Need parallel sessions (`--session`).## Install```bash# one-offuvx "browser-use[cli]" open https://example.com# permanentuv pip install "browser-use[cli]"browser-use install # downloads Chromium/deps```## Core Loop```bashbrowser-use open https://example.combrowser-use state # list elements w/ indicesbrowser-use click 5browser-use input 3 "hello"browser-use screenshotbrowser-use state # verify + get next indicesbrowser-use close```## Modes```bashbrowser-use --browser chromium open <url> # default (headless)browser-use --browser chromium --headed open <url> # visible windowbrowser-use --browser real open <url> # your Chrome (cookies/login)browser-use --browser remote open <url> # cloud browser (API key)```## Common Commands```bashbrowser-use open <url>browser-use state [--json]browser-use click <idx> | dblclick <idx> | rightclick <idx> | hover <idx>browser-use input <idx> "text" | type "text"browser-use scroll up|down [n]browser-use screenshotbrowser-use get <what> # read page/element infobrowser-use back | switch | close-tabbrowser-use cookies export <path> | cookies import <path>browser-use profile list|create|update|deletebrowser-use sessionsbrowser-use server status|logs|stopbrowser-use close [--all]```## Sessions```bashbrowser-use --session work open https://work.example.combrowser-use --session personal open https://personal.example.combrowser-use --session work statebrowser-use close --all```## Rules (agent-friendly)- Always run `browser-use state` before acting; indices change after navigation.- After each navigation/submit: re-run `state` (don’t reuse stale indices).- Prefer `--headed` while debugging.- Cleanup: `browser-use close` (or `close --all`) when done.## Remote Mode- Env: `BROWSER_USE_API_KEY` (or `--api-key`).

Frequently asked questions