Browser Automation & Web Scraping

关于

This skill empowers Claude to interact directly with the web by managing a background browser daemon for sophisticated automation. It enables advanced capabilities such as navigating complex site architectures, extracting structured data, filling out forms, and testing web applications in real-time. By utilizing named 'browsing contexts,' the skill maintains a persistent history across multiple tabs, allowing for parallel research and orchestrated multi-step workflows that can be precisely managed through a high-level planning and delegation model.

主要功能

• Interactive web form filling and complex UI navigation
• Real-time web application testing and state verification
• Smart orchestration with sub-agent delegation for single-page tasks
• Automated data extraction and web scraping from dynamic pages
• 1 GitHub stars
• Persistent multi-tab browsing contexts with full action history

使用场景

• Conducting multi-source online research and summarizing data across tabs
• Scraping detailed product information and pricing from e-commerce platforms
• Automating repetitive administrative tasks on internal web dashboards