skills.rest
Heyo-Computer
Heyo-ComputerOFFICIAL
Explore all skills by this author →
GitHub

computer

Automate Wayland desktop interactions with window enumeration, screenshots, and input synthesis.

1|Updated Apr 27, 2026
Search Tags:#automation#testing#screenshot#wayland#desktop#input
One-click install
npx skills add https://github.com/Heyo-Computer/heyo-public --skill computer
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: computer
Source: https://github.com/Heyo-Computer/heyo-public/tree/main/plugins/computer/skills/computer
Command: npx skills add https://github.com/Heyo-Computer/heyo-public --skill computer

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This skill solves the bottleneck of manually verifying UI changes or driving desktop applications, allowing agents to perform end-to-end testing and visual confirmation on Wayland-based Linux systems.

Core Features & Use Cases

  • Visual Verification: Capture screenshots of specific monitors to confirm UI rendering and layout changes.
  • Input Synthesis: Programmatically drive keyboard and mouse input to interact with desktop applications or web browsers.
  • System Observation: Enumerate active windows and monitor configurations to ensure the environment is ready for automated tasks.

Quick Start

Use the computer skill to capture a screenshot of the primary monitor and list all open windows to verify the current desktop state.

Frequently Asked Questions about computer

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

FAQPage Schema
How do I automate Wayland desktop interactions for end-to-end testing?▼

You can automate Wayland desktop interactions by synthesizing keyboard or mouse input and capturing screenshots to verify UI changes. This skill drives desktop applications and web browsers programmatically for headless UI verification.

What is needed to capture screenshots and enumerate windows on a Wayland compositor?▼

Capturing screenshots and enumerating active windows requires a Wayland compositor with ext-foreign-toplevel-list-v1 support. You also need write access to /dev/uinput to synthesize keyboard and mouse input for automated workflows.

Can I use this to verify UI rendering changes in headless Linux environments?▼

Yes, you can verify UI rendering changes in headless Linux environments by capturing screenshots of specific monitors. This allows agents to perform visual confirmation of layout changes and ensure the desktop state is ready.

Does automating input synthesis require special permissions on Linux?▼

Automating input synthesis requires write access to the /dev/uinput device on your Linux system. This permission is necessary to programmatically drive keyboard and mouse interactions for desktop applications.

What is the best way to drive automated browser-based workflows on Wayland?▼

The best way to drive automated browser-based workflows on Wayland is to combine input synthesis with system observation. You can enumerate active windows, confirm the environment, and programmatically interact with the browser.

Why does Wayland desktop automation fail to list active windows?▼

Wayland desktop automation fails to list active windows if your compositor lacks ext-foreign-toplevel-list-v1 support. Ensuring this specific protocol extension is active is required to properly observe and enumerate windows.

Related Skills

Explore More Software Engineering Skills→
hafley66hafley66
1

linux-input-overlay-rust

Intercept Linux input events and render text overlays on X11 and Wayland.

Community
Advanced
sunfminsunfmin

autocraft

Coordinate a multi-agent workflow to implement, test, and verify UI journeys from a spec.md.

Community
Advanced
betaTridentbetaTrident

browser-qa

Automate visual regression testing and UI interaction verification for web applications.

Community
Advanced
benjaminshafiibenjaminshafii
10

telegram

Send Telegram messages to configured chats via the Bot API.

Community
Basic