Think of a robot that can use a web browser just like you do. Browser automation gives computers the power to open sites, click buttons, and read text. People use it to test websites, gather data from the internet, or let AI agents interact with web pages.
Many automation scripts break easily. The key is using the right selectors and waiting strategies. This skill teaches you how to build reliable systems that run for years. It focuses on Playwright, the best tool for most jobs, and also covers Puppeteer when needed.
You will learn patterns that avoid common mistakes. No more random timeouts or fragile code. Instead, you let the browser do the waiting and find elements the way users see them. This makes your tests and scrapers stable and easy to maintain.
Global
mkdir -p ~/.claude/skills/browser-automationProject
mkdir -p .claude/skills/browser-automationSource Repository
Agent Browservercel-labs/agent-browser
Fast browser automation tool for AI agents to control any website
Develop Userscriptsxixu-me/skills
Build and debug browser userscripts for Tampermonkey and ScriptCat
Just Scrapescrapegraphai/just-scrape
Search, scrape, crawl, and monitor web pages with an easy command line tool
Browser Actbrowser-act/skills
AI agents use browser-act to automate web tasks like fetch forms screenshots and complex workflows
Firecrawlfirecrawl/cli
Search, scrape, and crawl websites with one simple command line tool
Playwright Climicrosoft/playwright-cli
Automate browser tasks and test web pages with simple terminal commands
Browser Usebrowser-use/browser-use
Automate web testing, form filling, and screenshots with simple CLI commands
Browser Act Skill Forgebrowser-act/skills
Explore any website once and create reusable skill packages forever