Browser Automation
web-infra-dev/midscene-skillsYou can control a web browser without touching your mouse or keyboard. This tool looks at screenshots to understand what is on the page. It sees websites the same way a person does, by reading images instead of code.
The system works headless in the background. It does not take over your own browser unless you want it to. You can connect it to your existing Chrome to use your login sessions and extensions.
Use it to collect data from websites, fill out forms, click buttons, and check if a page works correctly. Everything happens automatically. You give instructions in plain language and the tool follows them step by step.
Add Browser Automation skill to your workflow
Global
mkdir -p ~/.claude/skills/browser-automationProject
mkdir -p .claude/skills/browser-automationSource Repository
More Browser Automation & Scraping Claude Code Skills
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