agent-browser

I'm sorry, I can't provide that information.

4|Updated Mar 19, 2026
One-click install
npx skills add https://github.com/ClubMediterranee/ai-core --skill agent-browser-clubmediterranee
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/ClubMediterranee/ai-core/tree/main/skills/agent-browser
Command: npx skills add https://github.com/ClubMediterranee/ai-core --skill agent-browser-clubmediterranee

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Browser automation is a bottleneck for AI agents that must interact with websites, fill forms, click elements, and verify content; this Skill provides a command-line interface to orchestrate reliable, repeatable browser actions.

Core Features & Use Cases

  • Comprehensive browser automation: open pages, navigate, fill forms, click, capture screenshots, extract data, and run tests.
  • Snapshot refs: compact element references (@e1, @e2) to drive interactions and minimize context.
  • Multi-session workflows: named sessions and state persistence for concurrent automations.
  • Data extraction & testing: capture text, titles, URLs, and run validations during automation.

Quick Start

Install agent-browser, open a URL, snapshot to capture refs, then interact using the refs to automate your first task.

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?

Automate browser tasks for AI agents by using a CLI to navigate pages, interact with elements, capture refs, take screenshots, and extract data. This enables reliable, repeatable actions for form filling, page verification, and end-to-end workflows.

How do I use snapshot refs to interact with web elements?

Snapshot refs provide compact element references like @e1 or @e2 to drive interactions and minimize context. You snapshot a page to capture these refs, then use them in subsequent commands to click, fill forms, or extract data efficiently.

Can I run multiple browser automation sessions concurrently?

Yes, multi-session workflows are supported using named sessions with the --session flag. This allows state persistence and concurrent automations, enabling you to manage multiple concurrent browser tasks simultaneously across different workflows.

Do I need a specific browser for CLI web automation?

Yes, CLI web automation requires a Chromium-based browser to function. It relies on this browser environment to open pages, execute navigation, interact with elements, capture screenshots, and run validations during your automation workflows.

What is the best way to extract data and run tests during browser automation?

The best way to extract data and run tests is using built-in commands to capture text, titles, URLs, and run validations. This integrates data extraction and visual testing directly within your end-to-end automation workflows.

How do I stream browser automation results to a dashboard?

You can stream browser automation results to a dashboard using the Skill's dedicated streaming commands. This allows you to monitor navigation, interactions, and network activities visually during single or multi-session workflows.