Agent Browser
Automates web browser interactions, including navigation, form filling, data extraction, and visual testing.
Agent Browser is a comprehensive Claude Code skill designed for seamless web automation and browser control. It provides a robust set of commands for navigating URLs, interacting with DOM elements via unique references, and capturing high-quality media like screenshots, PDFs, and video recordings. This skill is ideal for developers needing to perform end-to-end testing, dynamic web scraping, or security audits, offering advanced features like network interception, session state persistence, and multi-tab management within a unified AI-driven workflow.
Key Features
01Session management with persistent cookie and localStorage support
02Network layer control for request interception, mocking, and routing
03Comprehensive interaction suite including click, fill, drag-and-drop, and file uploads
04Advanced media capture with full-page screenshots, PDF export, and video recording
05Interactive element selection using unique @ref shorthand IDs
06256 GitHub stars
Use Cases
01Automated end-to-end (E2E) testing for modern web applications
02Visual documentation generation and recorded workflow tutorials
03Dynamic data extraction and web scraping from JavaScript-heavy websites