agent-browser

Control a browser via command line for navigation, form submission, and data extraction.

6|4|Updated Feb 27, 2026
One-click install
npx skills add https://github.com/kortix-ai/kortix-registry --skill agent-browser-kortix-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/kortix-ai/kortix-registry/tree/main/files/skills/agent-browser
Command: npx skills add https://github.com/kortix-ai/kortix-registry --skill agent-browser-kortix-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates browser interactions, allowing AI agents to navigate websites, fill forms, click buttons, extract data, and take screenshots, effectively performing tasks that would typically require human interaction with a web browser.

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: Extract text content, element attributes, and structured data from web pages.
  • Screenshots & PDF: Capture full-page screenshots or save pages as PDFs.
  • Use Case: An AI agent needs to book a flight. It uses agent-browser to open the airline's website, fill in the departure and arrival dates, select seats, and complete the booking process.

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 on dynamic web pages with a headless browser?

Automate web scraping on dynamic pages by using the headless browser to navigate URLs, execute JavaScript, and extract text content or element attributes programmatically. It supports session management to maintain state across multiple page loads.

Can I use browser automation to fill out and submit web forms automatically?

Yes, you can use browser automation to fill out and submit web forms automatically. This Skill programmatically interacts with text fields, selects dropdowns, checks boxes, and triggers form submissions on targeted websites.

What is the best way to capture full-page screenshots during web navigation testing?

The best way to capture full-page screenshots during web navigation testing is using a headless browser interface. This Skill enables you to open URLs and save full-page visual captures or PDFs of the rendered output for debugging.

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

Yes, this browser automation tool supports authentication persistence and session management. You can maintain login states across multiple web navigation tasks, allowing continuous interaction with secure areas without re-authenticating.

Are there advanced debugging features like video recording available for web automation scripts?

Advanced debugging features like video recording and performance profiling are available for web automation scripts. These tools help diagnose issues during dynamic web content interaction and form submission processes within your automated workflows.