agent-browser

Automate browser tasks via CLI for navigation, form filling, and data capture.

Updated Dec 19, 2025
One-click install
npx skills add https://github.com/juanjaragavi/topfinanzas-us-next --skill agent-browser-juanjaragavi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/juanjaragavi/topfinanzas-us-next/tree/main/.agents/skills/agent-browser
Command: npx skills add https://github.com/juanjaragavi/topfinanzas-us-next --skill agent-browser-juanjaragavi

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Automate repetitive browser tasks for AI agents by providing a CLI to open websites, interact with pages, fill forms, click elements, and capture data.

Core Features & Use Cases

  • Navigate and render pages, snapshot DOM structure with element refs, and perform scripted interactions.
  • Support deterministic flows for testing web apps, data extraction, login automation, and content capture.
  • Re-snapshot after navigation or dynamic content changes to maintain valid element refs and state.

Quick Start

Open a URL with agent-browser open, snapshot the page with agent-browser snapshot -i, then interact using commands like fill and click to automate tasks.

Frequently Asked Questions about agent-browser

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate browser tasks for AI agents without writing complex scripts?

Browser automation for AI agents is handled through a CLI that opens websites, snapshots DOM elements, fills forms, and clicks elements. You navigate to a URL, snapshot the page, then issue interaction commands to automate data extraction and web app testing.

What is the best way to extract web data using headless browser automation?

Web data extraction is achieved by navigating to a URL and snapshotting the DOM structure with element refs. You re-snapshot after dynamic content changes to maintain valid element references and capture the updated page state.

Does browser automation support multi-session isolation for testing different logins?

Multi-session isolation is supported for browser automation. It allows you to maintain separate recorded states across different sessions, enabling concurrent login automation and isolated web app testing without cross-session interference.

How do I interact with dynamic web forms during automated web scraping?

Automated web scraping handles dynamic forms by using fill and click commands after taking a DOM snapshot. You re-snapshot the page after navigation or content changes to ensure the element references remain valid for interaction.

Can I run automated browser tasks in both headless and headed modes?

Automated browser tasks operate under both headless and headed modes. This supports deterministic testing flows and login automation while allowing recorded state management across multi-session environments.

When should I re-snapshot a page during browser automation?

Re-snapshotting during browser automation is necessary after page navigation or dynamic content changes. It updates the DOM structure and element refs, ensuring subsequent fill and click commands target valid page elements.