desktop-cli

Automate Windows desktop UI interactions and data entry via CLI.

Updated Jan 12, 2026
One-click install
npx skills add https://github.com/akiselev/desktop-cli --skill desktop-cli
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: desktop-cli
Source: https://github.com/akiselev/desktop-cli/tree/main
Command: npx skills add https://github.com/akiselev/desktop-cli --skill desktop-cli

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Windows desktop automation is tedious and error-prone when done manually; this CLI enables reliable, repeatable UI interactions without coding.

Core Features & Use Cases

  • LLM-optimized command surface for discovering and controlling desktop applications
  • Robust window targeting with smart disambiguation when multiple windows match
  • Rich actions including click, type, keys, scroll, and UI tree dump + compact summaries

Quick Start

List available windows, view a compact UI summary, and click a Save button in Notepad.

Frequently Asked Questions about desktop-cli

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

FAQPage Schema
How do I automate Windows desktop UI interactions without writing code?

Windows desktop automation can be achieved reliably without coding by using a CLI that drives UI navigation, repeated window interactions, and data entry across applications like Notepad.

Can I target a specific window when multiple instances are open?

Window targeting includes smart disambiguation to correctly identify and control specific windows when multiple matching instances are open during desktop automation.

What UI actions can I perform with LLM-integrated desktop automation?

UI automation actions include clicking, typing, sending key sequences, scrolling, and dumping the UI tree with compact summaries for LLM processing.

Does desktop automation work with complex applications like Altium Designer?

Desktop automation supports repeated window interactions and UI navigation across various applications, explicitly including complex software like Altium Designer and Notepad.

How do I extend desktop CLI automation with custom scripts and references?

The CLI uses YAML frontmatter in SKILL.md to define optional resource directories for scripts, references, and assets, extending functionality for custom automation workflows.

What's the best way to discover controllable applications for UI automation?

The CLI provides an LLM-optimized command surface that lists available windows and generates compact UI summaries to discover and control desktop applications efficiently.