Can I use this skill to test authenticated areas of a website?

Yes, the skill supports cookie and storage management, including the ability to save and load session states to a file (e.g., auth.json) to maintain login sessions across different runs.

Does it support visual debugging and recording?

Absolutely. You can take screenshots (standard or full-page), export pages as PDFs, and record .webm videos of your browser interactions to debug or document workflows.

How does agent-browser identify elements on a page?

It generates a snapshot of the page (accessibility tree) and assigns unique reference tags, such as @e1 or @e2, to interactive elements, allowing you to click or fill them without needing complex CSS selectors.

Can I mock API responses with agent-browser?

Yes, the 'network route' command allows you to intercept specific URLs to abort requests or provide mock JSON bodies, which is ideal for testing frontend behavior in isolation.

Browser Automation Agent

Name: Browser Automation Agent
Author: myk-org

bymyk-org

•

Browser Automation

Automates web browser interactions, testing, and data extraction through a comprehensive command-line interface.

The agent-browser skill empowers Claude to perform sophisticated web automation tasks, ranging from simple navigation and form filling to complex end-to-end testing and data extraction. By utilizing a robust reference-based system for element interaction, it allows for precise control over DOM elements without brittle selectors. The skill supports advanced features like session state management for authentication, network request interception for mocking, and visual debugging through screenshots and video recordings, making it an essential tool for developers and QA engineers working with modern web applications.

Key Features

011 GitHub stars

02Advanced visual debugging with full-page screenshots, PDF exports, and video recording.

03Support for complex interactions including drag-and-drop, file uploads, and iframe navigation.

04Comprehensive session management to save and load cookies and local storage states.

05Network layer control for intercepting requests, mocking API responses, and testing offline modes.

06Interactive element targeting using unique reference tags (@e1, @e2) from page snapshots.

Use Cases

01Automating repetitive administrative tasks like form submissions, report generation, and account setup.

02Automated end-to-end (E2E) testing of web applications to verify UI workflows and logic.

03Dynamic web scraping and data extraction from JavaScript-heavy websites and SPAs.

Key Features

011 GitHub stars

02Advanced visual debugging with full-page screenshots, PDF exports, and video recording.

03Support for complex interactions including drag-and-drop, file uploads, and iframe navigation.

04Comprehensive session management to save and load cookies and local storage states.

05Network layer control for intercepting requests, mocking API responses, and testing offline modes.

06Interactive element targeting using unique reference tags (@e1, @e2) from page snapshots.

Use Cases

01Automating repetitive administrative tasks like form submissions, report generation, and account setup.

02Automated end-to-end (E2E) testing of web applications to verify UI workflows and logic.

03Dynamic web scraping and data extraction from JavaScript-heavy websites and SPAs.