Skip to main content
skill CX Codex

browser · brightdata — Claude Code skill: what it does, how to install

This skill offloads local browser automation tasks to cloud infrastructure. It redirects traffic from drivers like Playwright, Puppeteer, or Selenium through a remote proxy server.

MIT 183 installs ★ 272 updated 2026-10-15

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add brightdata/skills --skill browser -a claude-code
Open on GitHub

What browser does

The skill automates the migration of local automation scripts to the Bright Data cloud. It updates driver launch parameters, replacing local addresses with remote WebSocket endpoints to bypass blocks, detection, and rate limits. Automation logic, including selectors and navigation sequences, remains untouched.

Operation requires an active account and a configured zone of type browser_api. The agent identifies connection parameters using bdata zones --json. Selenium scripts are routed through port 9515, while other drivers use 9222. Avoid site logins without prior KYC approval, as password submission is restricted by default.

The agent retrieves the BRIGHTDATA_API_KEY from the environment or CLI storage. If the key is missing or permissions are insufficient, the task is handed off to agent-onboarding for configuration.

What it helps with

  • run local automation scripts in the cloud
  • bypass IP blocks during scraping
  • configure remote browser control for Playwright
  • connect Puppeteer to cloud infrastructure

Example prompts for the agent

  • Switch my Playwright script to run on Bright Data cloud
  • Configure remote Selenium connection via Browser API
  • How do I route my existing automation script through a cloud zone?

How to install browser

1Skills CLI (Vercel)

npx skills add brightdata/skills --skill browser -a claude-code

2Manually: put the files in place

~/.claude/skills/browser/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/browser/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about browser

How to install browser in Claude Code?

Run npx skills add brightdata/skills --skill browser -a claude-code in your project terminal.

What does browser do?

It modifies the launch configuration of local automation drivers to route traffic through cloud servers, helping to avoid rate limits and site blocks.

What is needed to use browser?

You need the Bright Data CLI, a valid BRIGHTDATA_API_KEY, and a configured zone of type browser_api in your account.

Source text

SKILL.md · MIT
---
name: browser
description: 'Use when the user already has browser automation and wants it unblocked or run in the cloud: Playwright, Puppeteer, Selenium or another driver, a headless script that gets blocked, detected, or rate limited locally, or a computer-use AI that clicks by itself and needs somewhere to click. Also for asks that name CDP, connectOverCDP, browserWSEndpoint, a remote WebDriver, a websocket browser endpoint, or Browser API. Not for building the scraper for them (use scrape), not for one page as markdown, HTML, or a screenshot (use fetch), not for a search query (use search).'
---

# Bright Data - Browser

The user already wrote the automation. This skill changes the launch line so it runs on Bright Data's cloud browser instead of the local one, wires in the credentials that line needs, and runs it once to prove it connects. Their automation logic does not move.

## The one question

**Who does the clicking - your code, your AI model, or us?**

| Who clicks | Where it goes |
|---|---|
| Their code: Playwright, Puppeteer, or Selenium | Stay here. Point it at our cloud browser, nothing to rewrite. |
| Their computer-use model, the AI that clicks by itself | Stay here. Same swap, same endpoint. |
| The agent itself, step by step from a terminal | Stay here and drive `bdata browser`: `open`, `snapshot`, `click <ref>`, `type <ref>`, `close`, one command per action, no code to hold. Every subcommand is in `bdata browser --help`, and the `brightdata-cli` skill's `references/commands.md` has the session options. |
| Us | `scrape`. Scraper Studio does the clicking, and the user gets fields back instead of a driver to maintain. |

Ask it when the request names a framework, a technique, or an agent but leaves who drives the browser unstated. Ask it once, then act. A user holding working Playwright code and a blocked local browser never needs to hear about Scraper Studio.

## What the swap is

The local launch call becomes a remote connect call against a websocket:

```
wss://brd-customer-<CUSTOMER_ID>-zone-<ZONE>:<PASSWORD>@brd.superproxy.io:9222
```

Selenium is the one exception. It speaks WebDriver, not CDP, so it uses `https://` on port `9515` with the same credentials. Selectors, waits, navigation, screenshots and page logic all stay exactly as written.

The agent fills the three pieces itself, with free API reads and the key the user already has (`BRIGHTDATA_API_KEY`, else the CLI's stored login), never with placeholders left for the user. No key anywhere means the user is not set up: hand off to `agent-onboarding`, never ask for a key in chat. [references/connect.md](references/connect.md) has the lookup and the two ways to wire it.

## The zone

Find the Browser API zone by type, not by name, before writing the string:

```
bdata zones --json
```

Take the `name` of the entry whose `"type"` is `"browser_api"`, and use it wherever the connect string says `<ZONE>`. It is `cli_browser` after `bdata login`, `agent_browser_api` on an account made by agent registration, `mcp_browser` when the MCP server set the account up, and any name at all when a person created it by hand: read the type, then use whatever name it carries. This is one free read and it starts no session. If `bdata` is not recognized, the CLI is not installed or npm's global directory is not on PATH; both fixes live in the `agent-onboarding` skill's Install section.

No entry of that type at all is not a connect string to fix, but it is not an account problem yet either. The remedy, after the user agrees (it changes their account), is one free call, `POST https://api.brightdata.com/zone` with body `{"zone":{"name":"cli_browser","type":"browser_api"},"plan":{"type":"browser_api"}}`. `bdata browser open` creates one on demand too, but that starts a billable session, and it uses the name `cli_browser` unless given `--zone <name>` or `BRIGHTDATA_BROWSER_ZONE`, so on an account whose browser zone has another name, pass that name or it makes a second zone (with an agent-registration key it cannot create one and fails instead; pass `--zone agent_browser_api`). Do not reach for `bdata login` on a machine that is already logged in: it replaces the stored key. Escalate to `agent-onboarding` when the creation is refused with `kyc_required` or `business_account_required`, or on a permissions refusal (a key from agent registration, or a user without the Admin or Ops role, cannot create zones): the person then makes the zone in the Control Panel.

## The boundaries

Building the scraper belongs to `scrape`, and so does any ask where the user wants data and does not care what drives the browser. One page as markdown, HTML, or a screenshot belongs to `fetch`. Anything starting from a search query belongs to `search`. This skill is for a driver that already exists.

## Logging into sites

Typing passwords through Browser API is blocked by default. It needs KYC plus a compliance exception. Never promise a login flow before that is approved, and never retry into the block. The deep detail lives one skill over: open `agent-onboarding` and read the `references/auth.md` file inside it, which lists what needs KYC, what does not, and the approval path.

## Read next

- **Read [references/connect.md](references/connect.md) before writing the connect line** - the exact string, where the key and each of the three pieces come from, the two designs (endpoint in a secret, or looked up at run time) and when to pick which, and the Playwright edit end to end.
- **Read [references/errors.md](references/errors.md) the moment a connect attempt fails** - the 407 `client_100xx` codes and what each means, the Browser API auth codes, and the retry rule.

## Red flags - stop if you catch yourself doing one of these

- Offering Scraper Studio to a user who already has working driver code
- Rewriting their automation instead of changing the endpoint line
- Pointing Selenium at port 9222, or Playwright at 9515
- Printing, logging, or committing the assembled endpoint, which carries the password, or printing a connect error without redacting it
- Running `bdata zones info <zone>` in a terminal: it prints the zone password
- Leaving the user a variable to fill, or asking for a key, when the agent can read the stored key itself
- Retrying a 407 without reading which code came with it
- Sending the user to KYC before an error actually refused the connect
- Hardcoding or guessing a zone name instead of finding the `browser_api` zone by type
- Creating a zone without asking the user first

© brightdata · MIT · brightdata/skills

Similar skills

All skills for Automation and no-code: n8n, Zapier, Make →

browser by other authors comes first.

browser browserbase Automates browser navigation via the browse CLI. Useful for data extraction, filling forms, and navigating sites behind bot protection. CX Codex +1 6,100installs browser ruvnet Automates web browsers using agent-browser and accessibility snapshots. It cuts LLM context size by 93% using element references instead of full DOM trees. CX Codex +1 674installs browser stellarlinkco browser automates Chrome actions via Chrome DevTools Protocol without configuring an MCP server. Useful for taking screenshots, running scripts, and inspecting DOM nodes. CX Codex +1 202installs Browser Automation Claude Office Skills Browser Automation is a Claude Code skill that controls web pages through Puppeteer/Playwright. It covers scraping, browser-based tests, and repeatable web workflows. CX Codex +1 5,400installs adspower-antidetect-browser reason-machines adspower-antidetect-browser — a skill that gives your agent ready calls for creating, launching and stopping AdsPower browser profiles over the local API. CX Codex +1 822installs browser-automation sickn33 The browser-automation skill builds browser checks around observed UI state and explicit outcomes. Use it for UI workflows, timing failures, or authorised page-data collection. CX Codex +1 6,700installs lightpanda-browser reason-machines lightpanda-browser is a Claude Code skill for setting up Lightpanda for browser automation and web scraping. It activates for requests about Lightpanda, headless browsing, or CDP automation. CX Codex +1 1,600installs anti-detect-browser antibrow anti-detect-browser is a Claude Code skill that launches Chromium with a genuine device fingerprint through Playwright API. Each profile persists across runs for testing, scraping, and multi-account work. CX Codex +1 168,800installs safe-browser browserbase The skill builds a local browser agent whose only tool is safe_browser. Requests to hosts outside the allowlist fail at the CDP layer. CX Codex +1 1,800installs

From the same set14

The whole set →
scraper-builder scraper-builder takes you from "I want data from site X" to a working scraper: site analysis, Bright Data API choice, selectors, pagination. CX Codex +1 415installs design-mirror The design-mirror skill reads a website’s visual language and applies it to an existing codebase. Use it when a UI needs to follow a reference site’s look. CX Codex +1 353installs fetch fetch — a skill for Claude Code retrieves a web page as markdown, HTML, or a screenshot. Resolves bot challenges and 403 blocks using Bright Data Web Unlocker. CX Codex +1 186installs billing billing — a skill for Claude Code and Codex that checks Bright Data balance, inspects spend per zone, and estimates upcoming job costs. CX Codex +1 185installs brightdata-mcp The brightdata-mcp Claude Code skill explains how to connect Bright Data tools through MCP and choose which ones an agent can use. It activates during MCP client setup or tool-routing work. CX Codex +1 184installs instagram This Claude Code skill fetches Instagram profiles, posts, Reels, and comments as JSON. It activates for requests about account followers, post likes, or recent content. CX Codex +1 182installs datasets Identifies available pre-collected datasets in the marketplace to replace manual scraping. It triggers when a large generic corpus is requested. CX Codex +1 180installs brightdata-plugin brightdata-plugin is a Claude Code plugin that searches Google, collects web pages, and extracts structured data for agents working with live website information. ★ 272repo stars

Project sponsors

Companies that keep this analytics open