Skip to content
Browserbase Browser Automation

Browserbase Browser Automation Skill

by Browserbase browserbase/skills

Browserbase's official skill for driving a real browser from an agent via the browse CLI - navigate, snapshot, fill forms and click, locally or in a cloud session.

GitHub Docs
Development
Added to Onei
MIT

Install

Install with the skills CLI

One command for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf and dozens of other agents. Needs Node.js; the skill is fetched straight from browserbase/skills.

$ npx skills add browserbase/skills --skill browser

Run it in a terminal. The CLI finds the agents installed on your machine, asks which ones to add the skill to, and whether to install it into the folder you ran it from or for all your projects.

Other ways to install

  1. Open the skill on GitHub and download the folder that holds its SKILL.md.
  2. Put it at ~/.claude/skills/browser/, where Claude Code picks it up in every project.

No scripts or references next to it? Saving the SKILL.md alone as ~/.claude/skills/browser/SKILL.md works too.

Using another agent? Its personal skills folder
Codex
~/.agents/skills/
Cursor
~/.cursor/skills/
GitHub Copilot
~/.copilot/skills/
Gemini CLI
~/.gemini/skills/
Windsurf
~/.codeium/windsurf/skills/
OpenCode
~/.config/opencode/skills/
Open folder on GitHub

About

  • Navigate, snapshot, click and fill forms through the browse CLI
  • Local Chrome mode and remote Browserbase cloud sessions
  • CAPTCHA solving, residential proxies and Verified browsers on remote
  • CDP event tailing and session management
  • Prefers structured snapshots over screenshots to save context
  • Setup verification, mode comparison and troubleshooting

This skill teaches an agent to operate a browser through Browserbase's browse CLI: navigating pages, reading page state, interacting with elements, and managing sessions - in plain language rather than hand-written Playwright.

What it covers
  • Setup check - verifying the CLI is present before attempting anything, so failures are diagnosed instead of retried blindly.
  • Local versus remote - local mode drives Chrome or Chromium on your own machine; remote mode runs a Browserbase cloud session with Browserbase Identity, Verified browsers, automatic CAPTCHA solving and residential proxies. The skill includes a comparison table and explicit guidance on when each is the right choice, plus how to switch.
  • Commands - navigation, page state, interaction, CDP event tailing and session management, with a typical end-to-end workflow.
  • Snapshot over screenshot - the skill steers the agent toward structured page snapshots rather than images, which is both cheaper in context and more reliable to act on.
  • Best practices and troubleshooting for the failures that actually occur in browser automation.
Requirements

The browse CLI (npm install -g browse). Remote Browserbase sessions need BROWSERBASE_API_KEY; local mode just needs Chrome or Chromium installed. The skill declares Bash as its only allowed tool.

Where it fits

One of a large Browserbase collection that also covers serverless browser functions, full DevTools-protocol tracing, turning observed HTTP traffic into an OpenAPI spec, self-improving automation loops, domain-allowlisted safe browsing for Claude Agent SDK agents, cookie syncing from local Chrome, session-free fetch and search, adversarial UI testing, and research workflows built on the Browserbase Search API.

Install with npx skills add browserbase/skills, or add the marketplace in Claude Code and install the browse plugin. MIT licensed.

Try it

Once installed, ask your agent something like:

Log into this dashboard and extract the last 30 days of invoices as CSV.

SKILL.md

The instructions your agent loads, as published by Browserbase.

SKILL.md
name
browser
description
Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications. Supports remote Browserbase sessions with Browserbase Identity, Verified browsers, automatic CAPTCHA solving, and residential proxies — ideal for protected websites and JavaScript-heavy pages.
compatibility
Requires the browse CLI (`npm install -g browse`). Remote Browserbase sessions need `BROWSERBASE_API_KEY`. Local mode uses Chrome/Chromium on your machine.
license
MIT
allowed-tools
Bash
metadata
openclaw: requires: bins: - browse install: - kind: node package: "browse" bins: [browse] homepage: https://github.com/browserbase/skills

Browser Automation

Automate browser interactions using the browse CLI with Claude.

Setup check

Before running any browser commands, verify the CLI is available:

which browse || npm install -g browse
Environment Selection (Local vs Remote)

The CLI supports explicit per-command environment flags. If you do nothing, the next session defaults to Browserbase when BROWSERBASE_API_KEY is set and to local otherwise.

Local mode
  • browse open <url> --local starts a clean isolated local browser
  • browse open <url> --auto-connect attaches to an already-running debuggable Chrome; use --local when no debuggable Chrome is available
  • browse open <url> --cdp <port|url> attaches to a specific CDP target
  • Best for: development, localhost, trusted sites, and reproducible runs
Remote mode (Browserbase)
  • browse open <url> --remote starts a Browserbase session
  • Without a local flag, Browserbase is also the default when BROWSERBASE_API_KEY is set
  • Provides: Browserbase Identity, Verified browsers, automatic CAPTCHA solving, residential proxies, session persistence
  • Use remote mode when: the target site has bot detection, CAPTCHAs, IP rate limiting, Cloudflare protection, or requires geo-specific access
  • Get credentials at https://browserbase.com/settings
When to choose which
  • Repeatable local testing / clean state: browse open <url> --local
  • Reuse your local login/cookies: browse open <url> --auto-connect
  • Simple browsing (docs, wikis, public APIs): local mode is fine
  • Protected sites (login walls, CAPTCHAs, anti-scraping): use remote mode
  • If local mode fails with bot detection or access denied: switch to remote mode
Commands

Most driver commands work across local, remote, and CDP sessions after the daemon starts.

Navigation
browse open <url>                        # Go to URL
browse open <url> --local                # Go to URL in a clean local browser
browse open <url> --remote               # Go to URL in a Browserbase session
browse reload                            # Reload current page
browse back                              # Go back in history
browse forward                           # Go forward in history
Page state (prefer snapshot over screenshot)
browse snapshot                          # Get accessibility tree with element refs (fast, structured)
browse screenshot --path <path>          # Take visual screenshot (slow, uses vision tokens)
browse get url                           # Get current URL
browse get title                         # Get page title
browse get text <selector>               # Get text content (use "body" for all text)
browse get html <selector>               # Get HTML content of element
browse get markdown [selector]           # Get page content as markdown (defaults to body)
browse get value <selector>              # Get form field value

Use browse snapshot as your default for understanding page state — it returns the accessibility tree with element refs you can use to interact. Only use browse screenshot when you need visual context (layout, images, debugging).

Interaction
browse click <ref>                       # Click element by ref from snapshot (e.g., @0-5)
browse type <text>                       # Type text into focused element
browse fill <selector> <value>           # Fill input; add --press-enter if Enter is needed
browse select <selector> <values...>     # Select dropdown option(s)
browse upload <selector> <files...>      # Upload file(s) to <input type="file">
browse press <key>                       # Press key (Enter, Tab, Escape, Cmd+A, etc.)
browse mouse drag <fromX> <fromY> <toX> <toY>  # Drag from one point to another
browse mouse scroll <x> <y> <deltaX> <deltaY>  # Scroll at coordinates
browse highlight <selector>              # Highlight element on page
browse is visible <selector>             # Check if element is visible
browse is checked <selector>             # Check if element is checked
browse wait <type> [arg]                 # Wait for: load, selector, timeout
CDP event tailing
browse cdp <url|port>                    # Stream CDP events as NDJSON from any target
browse cdp 9222                          # Attach to local Chrome on port 9222
browse cdp ws://localhost:9222/devtools/browser/...  # Full WebSocket URL
browse cdp <url> --domain Network        # Only Network events
browse cdp <url> --domain Network --domain Console  # Multiple domains
browse cdp <url> --pretty                # Human-readable output
browse cdp <url> > events.jsonl          # Pipe to file
browse cdp <url> | jq '.method'          # Filter with jq

The cdp command connects directly to any Chrome DevTools Protocol target and streams events. It does not use the daemon — it's a standalone, long-running process. Press Ctrl+C to stop. Default domains: Network, Console, Runtime, Log, Page.

Session management
browse stop                              # Stop the browser daemon
browse status                            # Check daemon status and resolved mode
browse tab list                          # List all open tabs
browse tab switch <index-or-target-id>   # Switch to tab by index or target ID
browse tab close [index-or-target-id]    # Close tab
Typical workflow

If the environment matters, put --local, --remote, --auto-connect, or --cdp <port|url> on the first browser command.

  1. browse open <url> --local or browse open <url> --remote — navigate to the page
  2. browse snapshot — read the accessibility tree to understand page structure and get element refs
  3. browse click <ref> / browse type <text> / browse fill <selector> <value> — interact using refs from snapshot
  4. browse snapshot — confirm the action worked
  5. Repeat 3-4 as needed
  6. browse stop — close the browser when done
Quick Example
browse open https://example.com
browse snapshot                          # see page structure + element refs
browse click @0-5                        # click element with ref 0-5
browse get title
browse stop
Mode Comparison
FeatureLocalBrowserbase
SpeedFasterSlightly slower
SetupChrome requiredAPI key required
Reuse existing local cookiesWith browse open <url> --auto-connectN/A
Verified browserNoYes (Browserbase Verified browser via Identity)
CAPTCHA solvingNoYes (automatic reCAPTCHA/hCaptcha)
Residential proxiesNoYes (201 countries, geo-targeting)
Session persistenceNoYes (cookies/auth persist via contexts)
Best forDevelopment/simple pagesProtected sites, Browserbase Identity + Verified access, production scraping
Best Practices
  1. Choose the local strategy deliberately: use browse open <url> --local for clean state, browse open <url> --auto-connect for existing local credentials, and browse open <url> --remote for protected sites
  2. Always `browse open` first before interacting
  3. Use `browse snapshot` to check page state — it's fast and gives you element refs
  4. Only screenshot when visual context is needed (layout checks, images, debugging)
  5. Use refs from snapshot to click/interact — e.g., browse click @0-5
  6. `browse stop` when done to clean up the browser session and clear the env override
Troubleshooting
  • "No active page": Run browse stop, then check browse status. If it still says running, kill the zombie daemon with pkill -f "browse.*daemon", then retry browse open
  • Chrome not found: Install Chrome, use browse open <url> --auto-connect if you already have a debuggable Chrome running, or switch to browse open <url> --remote
  • Action fails: Run browse snapshot to see available elements and their refs
  • Browserbase fails: Verify API key is set
Switching to Remote Mode

Switch to remote when you detect: CAPTCHAs (reCAPTCHA, hCaptcha, Turnstile), bot detection pages ("Checking your browser..."), HTTP 403/429, empty pages on sites that should have content, or the user asks for it.

Don't switch for simple sites (docs, wikis, public APIs, localhost).

browse open <url> --local          # clean isolated local browser
browse open <url> --auto-connect   # attach to existing debuggable Chrome
browse open <url> --remote         # Browserbase session

Mode flags are applied when a session starts. After browse stop, the next start falls back to env-var-based auto detection. Use browse status to inspect the resolved mode and target while the daemon is running.

For detailed examples, see [EXAMPLES.md](EXAMPLES.md).
For API reference, see [REFERENCE.md](REFERENCE.md).

Install

Related Skills

See all Browserbase Browser Automation alternatives

Skill: Playwright CLI

by Microsoft

Featured

Microsoft's official Playwright skill — drives a real browser from the command line using accessibility snapshots and element refs, and plans, generates and heals Playwright tests.

DevelopmentTesting & QA

Skill: Firecrawl Build: Scrape

by Firecrawl

Integrate Firecrawl's /scrape endpoint into product code — turn a known URL into markdown, HTML, links, metadata or screenshots, with sensible defaults baked in.

Development
Browse all skills →