agent-browser

Automate web browser navigation, form interaction, and data extraction via CLI.

Updated Feb 16, 2026
One-click install
npx skills add https://github.com/michaeljabbour/amplifier-bundle-letsgo --skill agent-browser-michaeljabbour
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/michaeljabbour/amplifier-bundle-letsgo/tree/main/skills/agent-browser
Command: npx skills add https://github.com/michaeljabbour/amplifier-bundle-letsgo --skill agent-browser-michaeljabbour

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates repetitive tasks on the web, such as filling forms, navigating websites, and extracting data, saving you time and reducing manual errors.

Core Features & Use Cases

  • Web Navigation: Open, close, and navigate between web pages.
  • Form Interaction: Fill text fields, select dropdowns, click buttons, and submit forms.
  • Data Extraction: Scrape text, HTML, or specific element attributes from web pages.
  • Screenshots & PDFs: Capture full-page screenshots or generate PDFs of web content.
  • Session Management: Maintain state across sessions for authenticated browsing.
  • Use Case: Automate the process of logging into a web application, filling out a report, and downloading the generated PDF.

Quick Start

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

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 navigation for repetitive tasks?

You can automate web form filling and navigation by using a command-line interface for browser automation, enabling programmatic control over web pages to interact with text fields, dropdowns, and buttons to reduce manual errors.

What is the best way to scrape specific data and capture screenshots from web pages?

The best way to scrape data and capture screenshots is through browser automation that extracts text, HTML, or element attributes and generates full-page screenshots or PDFs of the target web content.

Can I maintain authenticated sessions across multiple web automation tasks?

Yes, you can maintain state across sessions for authenticated browsing, allowing you to execute workflows like logging into a web application and downloading a generated PDF without repeated authentication.

Does browser automation support proxy configurations and video recording?

Browser automation supports proxy configurations and video recording to ensure deterministic web task execution, allowing you to route traffic and capture task playback for testing or review.

How do I extract HTML or text content from specific web page elements?

You extract HTML or text content by issuing navigation commands to open the target web page and using the data extraction features to scrape specific element attributes from the loaded content.

What are the limitations of using a command-line interface for web automation?

Using a command-line interface for web automation requires programmatic control knowledge and does not inherently handle dynamic anti-scraping mechanisms, making it best suited for deterministic task execution rather than interactive browsing.