agent-browser

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

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/jokim1/clawrocket --skill agent-browser-jokim1
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/jokim1/clawrocket/tree/main/container/skills/agent-browser
Command: npx skills add https://github.com/jokim1/clawrocket --skill agent-browser-jokim1

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 interaction with web applications, data extraction, and form manipulation without manual intervention.

Core Features & Use Cases

  • Web Navigation: Open, close, reload, and navigate back/forward through web pages.
  • Element Interaction: Click, fill forms, type, hover, check/uncheck, and upload files using element references or semantic locators.
  • Data Extraction: Get element text, HTML, values, attributes, titles, URLs, and count elements.
  • Screenshots & PDF: Capture screenshots of full pages or specific elements, and save pages as PDFs.
  • Authentication: Save and load browser states for seamless login persistence.

Quick Start

Use the agent-browser skill to open the URL 'https://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 data extraction?

Automate web browser interactions by executing commands for navigation, form filling, and data extraction using element references or semantic locators. This allows manipulation of web pages and information extraction without manual intervention.

Can I capture screenshots and save web pages as PDFs during web automation?

Yes, web automation supports capturing screenshots of full pages or specific elements and saving pages as PDFs. These commands execute during browser manipulation to capture visual states of web applications.

How does browser state management handle authentication for web scraping?

Browser state management handles authentication by saving and loading browser states. This enables seamless login persistence, allowing automated web scraping and form interactions to maintain authenticated sessions across tasks.

What's the best way to locate elements for web automation tasks?

The best way to locate elements for web automation is using direct element references or semantic locators. This supports clicking, typing, hovering, and checking elements during navigation and data extraction processes.

Does web automation work for extracting text and HTML attributes from web pages?

Yes, web automation works for extracting element text, HTML, values, and attributes. It retrieves titles, URLs, and counts elements, enabling comprehensive data extraction from web pages during automated browser sessions.