Back to Directory
research
Agent Browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Installation
Run this in your terminal or add to your configuration:
# Clone into your skills directory
git clone ...About this Skill
Initial release: Automates browser interactions for web testing, automation, and data extraction.
- Supports navigation, form filling, clicks, snapshots, and page analysis.
- Provides commands for screenshots, PDF creation, video recording, and mouse control.
- Enables element interaction by references or semantic locators (role, text, label, etc.).
- Includes features for cookie/storage/session management, network interception, tab/window/frame control, and dialog handling.
- Offers flexible wait conditions and browser/device emulation options.
- Outputs results in JSON and supports both headless and headed browsing.