agent-browser

Automate browser interactions for web testing, form filling, and data extraction.

7|Updated Sep 27, 2022
One-click install
npx skills add https://github.com/vieitesss/.mac_config --skill agent-browser-vieitesss
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/vieitesss/.mac_config/tree/main/agents/skills/agent-browser
Command: npx skills add https://github.com/vieitesss/.mac_config --skill agent-browser-vieitesss

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates browser interactions for web testing, form filling, screenshots, and data extraction to accelerate QA, demos, and data gathering without manual, repetitive actions.

Core Features & Use Cases

  • Navigate to URLs and manage page context
  • Snapshot interactive elements and use refs to perform actions
  • Fill forms, click controls, and validate page responses
  • Take screenshots, record sessions, and extract data from pages
  • Support headless and headed runs for CI and demonstrations

Quick Start

Open a URL with agent-browser, snapshot elements, and perform a click or fill action using the element refs.

Frequently Asked Questions about agent-browser

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate browser testing and form filling without manual repetitive actions?

Automate browser testing using headless browser automation to navigate URLs, snapshot interactive elements, and fill forms via element refs. This replaces manual repetitive actions with repeatable automated interactions across dynamic pages for QA and data gathering.

What is the best way to extract data from dynamic web pages?

Extract data from dynamic pages by taking element snapshots to identify interactive controls, then navigating and capturing content. This browser automation approach handles dynamic page updates and supports repeatable data extraction workflows.

Does browser automation support headless mode for CI pipelines?

Yes, browser automation supports both headless and headed runs. Headless mode suits CI pipelines and automated testing, while headed mode is available for demonstrations and visual debugging of form interactions and page navigation.

How do I identify and interact with elements on a dynamic page for automated testing?

Identify elements on a dynamic page by taking a snapshot of interactive controls, which provides element refs. Use these refs to perform targeted actions like clicking controls or filling forms, ensuring accurate and repeatable test execution.

Can I record browser sessions and take screenshots during web testing?

Yes, you can take screenshots and record sessions during web testing. This functionality supports capturing visual evidence for demos, documenting form interactions, and validating page responses during automated browser workflows.

When should I use headed mode instead of headless for browser automation?

Use headed mode for demonstrations, visual debugging, or when observing form interactions and page navigation in real time. Use headless mode for CI pipelines, automated data extraction, and repeatable testing where visual output is unnecessary.