agent-browser

Automate browser interactions for testing, form filling, and data extraction.

2|Updated Jan 21, 2026
One-click install
npx skills add https://github.com/roderik/mpe --skill agent-browser-roderik
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/roderik/mpe/tree/main/.agents/skills/agent-browser
Command: npx skills add https://github.com/roderik/mpe --skill agent-browser-roderik

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates browser interactions for testing, form filling, screenshots, and data extraction. It helps reduce manual QA time by scripting repetitive web tasks.

Core Features & Use Cases

  • Navigate to URLs with agent-browser open <url> to automate sessions.
  • Snapshot interactive elements with agent-browser snapshot -i to obtain element refs like @e1, @e2.
  • Interact with page elements using refs (click, fill, type) and capture results (screenshots, text).
  • Use cases include automated form submission, UI testing, and data collection across websites.

Quick Start

Use the agent-browser to open a URL, snapshot, and perform actions with element refs, for example: agent-browser open https://example.com agent-browser snapshot -i agent-browser click @e1 agent-browser get text @e1

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 interactions for web testing and form filling?

Automate browser interactions by scripting repetitive web tasks like form filling and UI testing. You can navigate to URLs, snapshot interactive elements, and interact with pages using element refs to reduce manual QA time.

How do I extract interactive elements and click them during web automation?

To extract interactive elements during web automation, use the snapshot command to obtain element refs like @e1 or @e2. You can then use these refs to click, fill, or type into specific page elements reliably.

Can I take screenshots while automating browser tasks via CLI?

Yes, you can capture screenshots while automating browser tasks via CLI. After navigating to a URL and interacting with elements using refs, capture visual results to validate web app behavior across sites.

Do I need a specific environment to run browser automation scripts?

You need a Bash-based environment with standard CLI tooling to run browser automation commands. No additional dependencies or components are required, as the scripts rely on standard command-line execution.

What is the best way to validate web app behavior across multiple sites?

The best way to validate web app behavior is by scripting automated sessions. Open URLs, snapshot interactive elements to get refs, perform actions like clicking or typing, and capture screenshots or text to verify results.

Why use element refs instead of standard selectors for web automation?

Element refs provide a reliable way to interact with page elements during web automation. By snapshotting interactive elements to obtain refs like @e1, you ensure consistent targeting for clicking, filling, and typing actions.