agent-browser

Provides AI-optimized browser automation with context-efficient snapshotting via a command-line interface and Playwright integration.

Updated Feb 11, 2026
One-click install
npx skills add https://github.com/IoT-VN/tuya-energy-dashboard --skill agent-browser-iot-vn
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/IoT-VN/tuya-energy-dashboard/tree/main/.opencode/skills/agent-browser
Command: npx skills add https://github.com/IoT-VN/tuya-energy-dashboard --skill agent-browser-iot-vn

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill automates browser interactions for AI agents, making complex web tasks efficient and context-aware, reducing the amount of data needed for AI processing.

Core Features & Use Cases

  • Context-Efficient Snapshots: Captures interactive elements with minimal token usage.
  • Autonomous Sessions: Ideal for long-running, self-verifying AI workflows.
  • Cloud Browser Testing: Seamless integration with services like Browserbase.
  • Use Case: An AI agent needs to book a flight. It uses agent-browser to navigate to a booking site, snapshot to identify available seats and price fields, fill to input travel details, and click to select the best option, all while minimizing the data sent back to the AI.

Quick Start

Use the agent-browser skill to open the URL https://example.com and then take an interactive snapshot.

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 with an AI agent while minimizing token consumption?

AI agent browser automation minimizes token consumption by using context-efficient snapshots to capture interactive elements. This approach reduces the data sent back to the AI during web scraping, making complex tasks efficient and context-aware without overwhelming the model.

Can I use Playwright for self-verifying AI workflows in long autonomous sessions?

Yes, Playwright integrates with this AI browser automation CLI to support long-running autonomous sessions and self-verifying workflows. It enables robust browser control, allowing AI agents to independently navigate, interact, and verify results over extended periods.

Does this browser automation CLI support cloud browser testing with Browserbase?

Yes, this browser automation CLI seamlessly integrates with Browserbase for cloud browser testing. This allows AI agents to execute web automation tasks in cloud environments, enabling scalable testing and interaction without local browser resource constraints.

What is the best way to navigate a booking site and fill forms using an AI agent?

The best way is using an AI-powered browser automation CLI to navigate URLs, take interactive snapshots to identify fields, and fill forms. This workflow allows AI agents to sequentially snapshot, fill, and click elements while maintaining minimal context overhead.

How does context-efficient snapshotting work for browser control in AI agents?

Context-efficient snapshotting captures only the interactive elements of a web page to minimize token usage. By reducing the payload size sent to the AI, it allows the agent to process essential page structures and execute browser commands efficiently.

Can I record video of browser automation sessions performed by an AI agent?

Yes, video recording is supported during browser automation sessions executed by the AI agent. This feature allows you to capture and review the autonomous workflows, verifying the self-verifying actions and interactions performed by the agent.