desktop-control

Automate mouse, keyboard, and window operations with OpenCV-based image matching.

2|Updated Mar 31, 2026
One-click install
npx skills add https://github.com/Wike-CHI/acquisition-agent --skill desktop-control-wike-chi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: desktop-control
Source: https://github.com/Wike-CHI/acquisition-agent/tree/main/skills/desktop-control
Command: npx skills add https://github.com/Wike-CHI/acquisition-agent --skill desktop-control-wike-chi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Desktop tasks that require precise mouse/keyboard actions, screen inspection, and window control are repetitive, fragile, and slow when done manually; this Skill automates those interactions to save time and reduce human error.

Core Features & Use Cases

  • Pixel-accurate input: absolute and relative mouse movement, clicks, drag-and-drop with smooth trajectories.
  • Keyboard automation & hotkeys: configurable typing speed, key hold/release, and multi-key shortcuts for fast workflows.
  • Screen & window operations: full/region screenshots, pixel color reads, OpenCV-backed image matching, multi-monitor support, and window activation.
  • Safety & controls: failsafe corner abort, approval prompts, bounds checking, and logging for auditable automation.
  • Use Cases: automated form filling, GUI testing, repetitive data-entry, screenshot-based verification, and autonomous small workflows via the AI agent.

Quick Start

Ask the agent: Draw a circle in Microsoft Paint and save the result as drawing_result.png.

Frequently Asked Questions about desktop-control

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

FAQPage Schema
How do I automate mouse clicks and keyboard typing for desktop GUI workflows?

Pixel-accurate mouse control and keyboard automation enable precise desktop GUI workflows by executing absolute and relative clicks, drag-and-drop trajectories, and configurable typing speeds. This approach supports multi-key shortcuts and key hold/release sequences for fast, repetitive UI task execution.

Can I find UI elements on screen using image recognition instead of fixed coordinates?

OpenCV-backed image matching locates UI elements on screen visually instead of relying on fixed coordinates. This enables dynamic interaction with buttons or fields through screenshot analysis, full and region captures, and pixel color reads for robust GUI automation.

How do I take a screenshot of a specific window or monitor region for verification?

Screenshot verification supports full screen, specific regions, and multi-monitor setups for visual verification of desktop workflows. You can capture window-specific screens, read pixel colors, and validate that UI elements rendered correctly during automated GUI testing and repetitive data-entry tasks.

Does this desktop automation tool support multi-monitor window management?

Multi-monitor support and window activation capabilities enable desktop automation across multiple displays. This allows targeting specific applications, managing window focus, and executing screen operations on the correct monitor during GUI-driven testing and autonomous workflow execution.

How do I prevent an automated desktop script from running out of control?

Failsafe corner abort, approval prompts, and bounds checking prevent automated desktop scripts from running out of control. These safety mechanisms, combined with detailed logging, ensure auditable automation and allow immediate intervention during unexpected behavior or repetitive UI task execution.