What problem does it solve?
This skill solves the difficulty of programmatically interacting with complex, dynamic web pages that require browser-level control, such as clicking elements, taking screenshots, or extracting accessibility trees, without the overhead of heavy automation frameworks.
Core Features & Use Cases
- Browser Interaction: Perform clicks, text input, and navigation directly on open Chrome tabs.
- Data Extraction: Capture full accessibility trees or specific HTML elements for analysis.
- Visual Capture: Take high-resolution screenshots of the current viewport with automatic coordinate mapping.
- Use Case: Use this to automate data collection from a web dashboard that requires login or complex state, or to debug UI elements by inspecting the accessibility tree.
Quick Start
Use the chrome-cdp skill to take a screenshot of the page with target ID 6BE827FA and save it to the current directory.