agent-browser

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

Updated Mar 10, 2026
One-click install
npx skills add https://github.com/erguotou520/myclaw --skill agent-browser-erguotou520
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/erguotou520/myclaw/tree/main/container/skills/agent-browser
Command: npx skills add https://github.com/erguotou520/myclaw --skill agent-browser-erguotou520

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the friction of manually navigating websites by letting an AI inspect pages, interact with controls, capture screenshots, and extract information directly from the browser.

Core Features & Use Cases

  • Web Navigation: Open pages, move backward and forward, reload, and manage browser sessions for multi-step workflows.
  • Interactive Task Execution: Click, type, fill forms, select options, upload files, and handle checkboxes or other page controls.
  • Page Inspection and Extraction: Read accessibility trees, query text or attributes, collect page data, and verify results after navigation changes.
  • Testing and Research: Use it for web app QA, content review, screenshot capture, PDF export, and structured data gathering from live sites.

Quick Start

Use the agent-browser skill to open the target website, inspect the interactive elements, and complete the required browsing task by clicking, filling, or extracting data as needed.

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 navigation and form filling for multi-step workflows?

Automate web navigation and form filling by using command-driven instructions to open pages, click controls, type text, and manage browser sessions. The skill interacts with page elements directly, handling multi-step workflows reliably across interactive websites.

Can I extract structured data from live websites using browser automation?

Extract structured data from live websites by reading accessibility trees and querying text or attributes after navigation. The skill collects page data and verifies results, enabling content review and structured data gathering from interactive sites.

What is the best way to capture screenshots and export PDFs during web testing?

Capture screenshots and export PDFs during web testing by driving the browser to target pages and issuing snapshot commands. The skill automates page inspection, allowing you to verify visual results and gather content from live web applications.

Do I need any external browser extensions to handle interactive page controls?

No external browser extensions are required to handle interactive page controls. The skill uses ref-based interactions and session state handling to click, type, select options, upload files, and manage checkboxes directly within the automation workflow.

Does web automation work for QA testing across interactive web apps?

Web automation works for QA testing across interactive web apps by inspecting accessibility trees, executing interactive tasks, and verifying page changes. The skill supports web app QA, content review, and structured data gathering from live sites.

What are the limitations of using command-driven browser automation for web interaction?

Command-driven browser automation for web interaction requires explicit ref-based interactions and session state handling to complete tasks reliably. It depends on navigating elements via accessibility trees, so pages without proper structure may pose challenges for data extraction.