agent-browser

Automate browser navigation, form filling, data extraction, and screenshot capture.

41|3|Updated Jan 2, 2026
One-click install
npx skills add https://github.com/tdimino/claude-code-minoan --skill agent-browser-tdimino
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/tdimino/claude-code-minoan/tree/main/skills/integration-automation/agent-browser
Command: npx skills add https://github.com/tdimino/claude-code-minoan --skill agent-browser-tdimino

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates repetitive browser tasks, saving time on web testing, data collection, and form interactions.

Core Features & Use Cases

  • Web Navigation: Open URLs, go back/forward, reload pages.
  • Element Interaction: Click, fill forms, type, check/uncheck, select options.
  • Data Extraction: Get text, HTML, attributes, and structured data from web pages.
  • Screenshots & PDF: Capture full-page or element-specific screenshots, save pages as PDFs.
  • Use Case: Automatically fill out a complex online application form, take screenshots at each step, and save the final page as a PDF for your records.

Quick Start

Use the agent-browser skill to open the URL https://example.com and take a full-page screenshot named output.png.

Frequently Asked Questions about agent-browser

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

FAQPage Schema
What is browser automation for web testing and data extraction?

Browser automation programmatically controls web pages to perform navigation, form filling, data extraction, and screenshot capture. It automates repetitive web tasks like content scraping and complex web application testing using CSS selectors and semantic locators for precise element targeting.

How do I automate form filling and take screenshots across web pages?

You can automate form filling by using element interaction features to click, type, and select options, then capture full-page or element-specific screenshots. This workflow supports automatically filling out complex online application forms and saving the final page as a PDF for your records.

Can I extract structured data and HTML attributes from web pages using CSS selectors?

Yes, data extraction features allow you to get text, HTML, attributes, and structured data from web pages. The automation utilizes CSS selectors and semantic locators to precisely target and extract the specific elements you need from various web pages.

What's the best way to capture full-page screenshots and save web pages as PDFs?

The best way to capture full-page screenshots and save web pages as PDFs is through automated browser navigation. After opening a URL, the automation can capture full-page or element-specific screenshots and directly save the loaded pages as PDF files.

Does browser automation work for complex web application testing without dependencies?

Yes, this browser automation supports complex web application testing with no dependencies. It handles web navigation, element interaction like checking/uncheck options, and structured data extraction across various web pages independently.