agent-browser

Automate browser navigation, form submission, data extraction, and visual regression testing.

1|Updated Aug 1, 2020
One-click install
npx skills add https://github.com/JohannesKonings/JohannesKonings.github.io --skill agent-browser-johanneskonings
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/JohannesKonings/JohannesKonings.github.io/tree/main/.agents/skills/agent-browser
Command: npx skills add https://github.com/JohannesKonings/JohannesKonings.github.io --skill agent-browser-johanneskonings

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill eliminates the need for manual web interaction when AI agents need to navigate websites, fill forms, extract data, or test web applications, removing repetitive human effort from browser-based workflows.

Core Features & Use Cases

  • Full Browser Automation: Navigate pages, interact with elements via reference IDs, take screenshots, extract text and PDFs, and run visual regression tests.
  • Session & Auth Management: Save and reuse logged-in session state, handle OAuth, 2FA, and cookie-based authentication without repeated logins.
  • Use Case: For example, use it to automatically log into a SaaS dashboard, scrape product pricing data from multiple pages, and save a full-page PDF report of the results.

Quick Start

Use the agent-browser skill to navigate to your target website, fill out the required form with your provided details, and capture a screenshot of the resulting confirmation page.

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 for an AI agent?

To automate web browser interactions, this Skill enables AI agents to programmatically navigate pages, fill forms, and extract data using the agent-browser CLI tool. It handles element reference tracking and supports both headless and headed browser modes.

Can I scrape authenticated content without logging in every time?

Yes, you can scrape authenticated content without repeated logins by saving and reusing logged-in session state. The Skill manages session persistence, OAuth, 2FA, and cookie-based authentication for automated web scraping workflows.

How do I run automated visual regression testing for web applications?

You can run visual regression testing by using the Skill to navigate target web pages and capture screenshots programmatically. The agent-browser CLI tool executes browser commands to detect visual changes across web application testing sessions.

Does this browser automation tool support headless and headed modes?

Yes, browser automation supports both headless and headed modes. The Skill requires the agent-browser CLI tool to execute commands, allowing you to run workflows either visibly for debugging or invisibly for automated data extraction.

What is the best way to extract text and PDF data from web pages programmatically?

The best way to extract text and PDFs from web pages is using this Skill's full browser automation capabilities. The agent-browser CLI tool interacts with web elements via reference IDs to capture and save the resulting page data.

Can I automate repetitive cross-site form filling workflows with AI?

Yes, you can automate repetitive cross-site form filling workflows with AI agents. The Skill enables programmatic form submission by tracking element references, allowing agents to fill out and submit required forms across multiple target websites automatically.