agent-browser

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

Updated Nov 16, 2025
One-click install
npx skills add https://github.com/yanhao98/h-devcontainer --skill agent-browser-yanhao98
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/yanhao98/h-devcontainer/tree/main/.agents/skills/agent-browser
Command: npx skills add https://github.com/yanhao98/h-devcontainer --skill agent-browser-yanhao98

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates complex browser interactions, making it easy to navigate websites, fill forms, extract data, and test web applications programmatically, saving significant manual effort and time.

Core Features & Use Cases

  • Web Navigation: Open URLs, navigate back/forward, and manage tabs.
  • Form Interaction: Fill text fields, select dropdowns, check boxes, and submit forms.
  • Data Extraction: Scrape text content, element attributes, and structured data.
  • Screenshots & PDFs: Capture full-page screenshots or save pages as PDFs.
  • Authentication: Handle logins, manage sessions, and use saved authentication states.
  • Use Case: Automate the process of logging into a web application, filling out a multi-step form, and then extracting the confirmation details into a structured report.

Quick Start

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

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 scraping and form filling with a headless browser?

You can automate web scraping and form filling by using this Skill's command-line interface to navigate URLs, interact with text fields, select dropdowns, and extract structured data programmatically. It supports Chrome and Chromium via CDP for automated browser interactions.

Can I use browser automation to capture full-page screenshots and save pages as PDFs?

Yes, browser automation allows you to capture full-page screenshots and save web pages as PDFs. The Skill provides specific commands to programmatically generate visual captures of websites for testing or archival purposes.

Does this browser automation tool support session management and authentication handling?

Yes, it supports session management and authentication handling. You can manage logins, maintain sessions, and use saved authentication states to access protected pages during automated web navigation and data extraction.

What is the best way to handle multi-step web form submissions and extract confirmation details?

The best way to handle multi-step web form submissions is to use this Skill to automate logging in, filling out sequential form fields, and then extracting the final confirmation details into a structured report, saving manual effort.

How does visual diffing work with automated browser screenshots?

Visual diffing works by comparing automated browser screenshots captured during web navigation. This feature helps detect visual changes in web applications by analyzing full-page screenshots taken programmatically across different sessions.