agent-browser

Automates web browser interactions including navigation, form filling, data extraction, and screenshots.

17|3|Updated Feb 21, 2026
One-click install
npx skills add https://github.com/omniaura/omniclaw --skill agent-browser-omniaura
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/omniaura/omniclaw/tree/main/container/skills/agent-browser
Command: npx skills add https://github.com/omniaura/omniclaw --skill agent-browser-omniaura

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates web browsing tasks, allowing for research, interaction with web applications, data extraction, and form submission without manual intervention.

Core Features & Use Cases

  • Web Navigation: Open URLs, go back/forward, reload pages.
  • Element Interaction: Click, type, fill forms, select dropdowns, check/uncheck boxes.
  • Data Extraction: Get element text, HTML, values, attributes, page title, and URL.
  • Screenshots & PDF: Capture screenshots of pages or full pages, and save pages as PDFs.
  • Authentication: Save and load browser states for authenticated sessions.

Quick Start

Use the agent-browser skill to open the URL https://www.example.com.

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 browser interactions like form filling and navigation?

Web scraping is supported through data extraction features that retrieve element text, HTML, values, and attributes from web pages. You can automate the extraction of structured data by referencing specific elements on the page.

Can I save and load authenticated browser sessions for web automation?

Yes, you can save and load browser states for authenticated sessions. This session persistence feature allows you to maintain logged-in states across multiple automation runs without re-entering credentials.

How do I capture screenshots and save web pages as PDFs during browser automation?

During browser automation, you can capture screenshots of visible pages or full pages and save web pages as PDFs. These features allow you to document page states and archive web content for later analysis.

Does this browser automation approach work with dynamic web applications?

Yes, this approach works with dynamic web applications by using semantic locators and element referencing to interact with page components. It handles JavaScript-rendered content through direct browser interaction rather than static HTML parsing.

What is the best way to extract data from web pages that require login authentication?

The best way to extract data from authenticated pages is to save the browser state after logging in, then load that state in subsequent sessions. This preserves your authenticated session while you navigate and extract text, HTML, or attributes from protected content.