cmux-browser

Automate browser tasks in cmux webviews with clicks, fills, and snapshots.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/ever-oli/omni-ecosystem --skill cmux-browser
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: cmux-browser
Source: https://github.com/ever-oli/omni-ecosystem/tree/main/omni-desktop/skills/cmux-browser
Command: npx skills add https://github.com/ever-oli/omni-ecosystem --skill cmux-browser

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

cmux-browser automates end-user browser tasks inside cmux webviews to open sites, interact with pages, wait for state changes, and extract data from surfaces.

Core Features & Use Cases

  • Open and target a browser surface, verify navigation with get url, take snapshots, interact with elements via click, fill, type, or press, wait for state changes, and re-snapshot after DOM/navigation changes.
  • Use cases include end-to-end form automation, login flows, data extraction, and automated testing of web interfaces.

Quick Start

Open a surface, navigate to a URL, snapshot to collect refs, then perform actions like click or fill and re-snapshot as needed.

Frequently Asked Questions about cmux-browser

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

FAQPage Schema
How do I automate end-user browser tasks inside webviews?

Automate end-user browser tasks inside webviews by opening a browser surface, navigating to a URL, taking snapshots to collect refs, and performing actions like click, fill, type, or press.

What is surface isolation and why is it needed for browser automation?

Surface isolation separates browser automation contexts across surfaces, ensuring that tasks like login flows and data extraction run independently without session conflicts.

How do I keep browser automation refs stable after DOM changes?

Keep browser automation refs stable by managing the ref lifecycle and re-snapshotting surfaces after DOM or navigation state changes to capture updated element references.

What's the best way to wait for page load states during webview automation?

Wait for page load states during webview automation by applying wait patterns that pause execution until specific page loading or state change conditions are met.

Can I extract data from web interfaces using browser snapshots?

Extract data from web interfaces by taking snapshots to collect element refs, interacting with pages via actions, and re-snapshotting after DOM changes to capture the resulting data.

Do I need any external dependencies to run cmux browser automation?

No external dependencies are required; the skill operates independently to provide templates and references for navigating sites, performing actions, and waiting for load states.