computer-use

Control headless Linux desktop GUIs via Xvfb, XFCE, and VNC.

61|11|Updated Feb 4, 2026
One-click install
npx skills add https://github.com/viralcode/openwhale --skill computer-use-viralcode
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: computer-use
Source: https://github.com/viralcode/openwhale/tree/main/skills/computer-use
Command: npx skills add https://github.com/viralcode/openwhale --skill computer-use-viralcode

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires xvfb, xfce4, xfce4-terminal, xdotool, scrot, imagemagick, dbus-x11, x11vnc, novnc, websockify, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill enables full graphical desktop control for headless Linux servers and VPS instances, allowing you to interact with GUI applications as if you had a physical monitor connected.

Core Features & Use Cases

  • Virtual Display: Creates a virtual Xvfb display with an XFCE desktop environment.
  • GUI Automation: Supports 17 standard actions including screenshots, mouse clicks, keyboard input, and scrolling.
  • Live Remote Viewing: Provides flicker-free VNC setup for real-time desktop monitoring via a web browser or VNC client.
  • Use Case: Remotely install and configure a desktop application on a cloud server, interact with its graphical interface, and capture screenshots of the process.

Quick Start

Run the setup script to install and configure the virtual display and VNC server.

Frequently Asked Questions about computer-use

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

FAQPage Schema
How do I run GUI automation on a headless Linux server?

You can run GUI automation on a headless Linux server by creating a virtual Xvfb display with an XFCE desktop environment. This setup supports 17 standard actions including mouse clicks, keyboard input, and scrolling.

What is the best way to control a remote desktop on a VPS instance?

The best way to control a remote desktop on a VPS instance is using a virtual display combined with a VNC server. This allows you to interact with graphical applications and perform live remote viewing through a web browser.

Can I view my XFCE desktop environment live in a browser?

Yes, you can view your XFCE desktop environment live in a browser. The setup provides a flicker-free VNC server accessible via web browsers using noVNC and websockify for real-time monitoring.

Do I need a physical monitor to use GUI applications on a cloud server?

No, you do not need a physical monitor to use GUI applications on a cloud server. Xvfb creates a virtual display that allows you to interact with graphical interfaces and capture screenshots remotely.

Does this remote desktop setup work with any LLM?

Yes, the remote desktop setup works with any LLM for model-agnostic operation. It integrates with large language models to execute standard GUI automation actions on your virtual display.

What are the limitations of using Xvfb for GUI automation?

A limitation of using Xvfb for GUI automation is that it requires specific dependencies like xdotool and scrot. You must install these components and configure dbus-x11 to ensure standard actions like screenshots work properly.