steel-browser

Automate cloud browser sessions with Steel.dev and Playwright.

Updated Mar 4, 2026
One-click install
npx skills add https://github.com/velamints2/clawbot-lab --skill steel-browser
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: steel-browser
Source: https://github.com/velamints2/clawbot-lab/tree/main/skills/steel-browser
Command: npx skills add https://github.com/velamints2/clawbot-lab --skill steel-browser

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires steel-sdk, playwright, and includes scripts (resource) components.

What problem does it solve?

Cloud browser automation and management to perform web tasks efficiently without local browser setup.

Core Features & Use Cases

  • Create and manage cloud browser sessions with proxy and CAPTCHA support.
  • Navigate, interact with pages using Playwright selectors (CSS/text/aria), take screenshots, and scrape content.
  • Build browser automation loops for AI agents, QA, and data collection from web sources.

Quick Start

Start a Steel browser session and begin automating web tasks using Playwright selectors.

Frequently Asked Questions about steel-browser

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
What is cloud browser automation and when do I need it for web scraping?

Cloud browser automation runs remote browser sessions to execute web scraping and interaction tasks without local setup. You need it when scaling data collection, QA testing, or AI agent loops that require proxy and CAPTCHA support.

How do I automate web tasks using Playwright selectors in a cloud browser?

You automate web tasks by creating a remote session via Steel.dev and driving it with Playwright selectors. Use CSS, text, or aria selectors to navigate pages, interact with elements, take screenshots, and scrape content during automation loops.

Do I need a Steel API key to run browser automation loops remotely?

Yes, you need a STEEL_API_KEY to authenticate and manage remote cloud browser sessions. The Steel SDK uses this key to provision environments, configure proxies, and handle CAPTCHA challenges before executing Playwright automation loops.

Can I use Playwright CSS and text selectors to scrape content from Steel cloud sessions?

Yes, Playwright CSS, text, and aria selectors work directly within Steel cloud sessions. You connect Playwright to the remote browser instance to navigate pages, extract targeted content, and build automated data collection workflows.

What is the difference between local Playwright automation and Steel cloud browser sessions?

Local Playwright runs browsers on your machine, while Steel cloud browser sessions execute remotely via the Steel SDK. Cloud sessions offer built-in proxy rotation and CAPTCHA support, making them better suited for scalable web scraping and AI automation loops.