agent-browser

Automate browser navigation, form filling, screenshots, and data extraction.

1|Updated Oct 22, 2025
One-click install
npx skills add https://github.com/vojtechmares/mares.cz --skill agent-browser-vojtechmares
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/vojtechmares/mares.cz/tree/main/.claude/skills/agent-browser
Command: npx skills add https://github.com/vojtechmares/mares.cz --skill agent-browser-vojtechmares

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates complex browser interactions, streamlining tasks like web testing, data scraping, and form submission.

Core Features & Use Cases

  • Web Navigation: Open, close, and navigate between web pages.
  • Element Interaction: Click, fill forms, check/uncheck, select dropdowns, and more using semantic locators or element references.
  • Data Extraction: Retrieve text, HTML, attributes, and other element properties.
  • Screenshots & Recording: Capture screenshots or record video of browser sessions.
  • Use Case: Automate the process of logging into a web application, filling out a complex form, and submitting it, then taking a screenshot of the confirmation page.

Quick Start

Use the agent-browser skill to open the URL 'https://example.com' and then click on the element with the text 'Submit'.

Frequently Asked Questions about agent-browser

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

FAQPage Schema
How do I automate web form filling and submission?

Automate web form filling by navigating to the target URL, locating input elements via semantic locators or refs, entering data, and triggering the submit action to streamline repetitive data entry tasks.

Can I take screenshots and record video of web application testing sessions?

Yes, you can capture screenshots or record video of web testing sessions to visually document automated browser interactions, verify UI states, and confirm form submission results.

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

Data extraction from web pages is handled by retrieving text, HTML, and element attributes after navigating to the target site, allowing you to reliably scrape and collect information using semantic locators.

Does browser automation support navigating websites and managing sessions?

Browser automation supports opening, closing, and navigating between web pages, along with session management. You can use it to interact with web applications, handle multi-step workflows, and extract information.

How do I click elements and interact with dropdowns during web testing?

You click elements and interact with dropdowns during web testing by using semantic locators or element references, allowing precise interaction with web page components for automated navigation and form completion.