desktop-click

Click desktop UI elements or screen coordinates with configurable mouse buttons.

2.0k|267|Updated Jan 30, 2026
One-click install
npx skills add https://github.com/openakita/openakita --skill desktop-click
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: desktop-click
Source: https://github.com/openakita/openakita/tree/main/skills/system/desktop-click
Command: npx skills add https://github.com/openakita/openakita --skill desktop-click

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill allows for programmatic interaction with desktop applications and elements, automating tasks that would typically require manual mouse clicks.

Core Features & Use Cases

  • Element Clicking: Clicks buttons, icons, menu items, or other UI elements based on their description or name.
  • Coordinate Clicking: Clicks at specific X, Y coordinates on the screen.
  • Button Specification: Supports left, right, and middle mouse buttons.
  • Double Click: Can perform double-click actions.
  • Find Methods: Offers 'auto', 'uia' (UIAutomation), and 'vision' (visual recognition) for locating elements.
  • Use Case: Automatically click the "Save" button in a software application, or click a specific point on the screen to open a context menu.

Quick Start

Click the 'Save' button on the desktop.

Frequently Asked Questions about desktop-click

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

FAQPage Schema
How do I automate clicking a desktop UI button or screen coordinate?

To automate clicking a desktop UI button or screen coordinate, you can programmatically target elements by their description, name, or specific X/Y coordinates. This approach supports single, double, and various mouse button actions for task automation.

What methods are available for locating desktop elements during UI automation?

For locating desktop elements during UI automation, you can use 'auto', 'uia' (UIAutomation), or 'vision' (visual recognition) find methods. These options provide robust element identification for interacting with application interfaces.

Can I perform right-click or middle-click actions on desktop applications?

Yes, you can perform right-click or middle-click actions on desktop applications. The interaction supports left, right, and middle mouse buttons, allowing you to trigger context menus and other specific application functions programmatically.

Does UI automation support visual recognition for elements without UIAutomation metadata?

Yes, UI automation supports visual recognition via the 'vision' find method. This allows you to interact with elements that lack standard UIAutomation metadata by identifying them visually on the desktop instead.

What is the best way to click a specific point on the screen to open a context menu?

The best way to click a specific point on the screen to open a context menu is by using coordinate clicking with right mouse button specification. This programmatically targets the exact X/Y screen location to trigger the desired menu.

How do I double click desktop icons or files programmatically?

To double click desktop icons or files programmatically, you use the element clicking function with the double click option enabled. You can target the icon by its description or name using UIAutomation or visual recognition methods.