# Desktop Touch

> Use this tool when you need to automate Windows desktop tasks with high speed and efficiency, solving problems such as slow automation workflows and high token costs. Desktop Touch provides 57 tools for tasks like screen capture, mouse and keyboard input, and browser control, with inputs including element queries and outputs including automated workflows. It is ideal for use cases requiring rapid desktop automation, such as data scraping, UI testing, and workflow batching.

Canonical page: https://skillsregistry.net/skills/harusame64-desktop-touch  
JSON: https://api.skillsregistry.net/v1/skills/harusame64-desktop-touch

## Description

Desktop Touch provides 57 MCP tools for Windows desktop automation, powered by a native Rust engine delivering an 82x speedup over PowerShell-based alternatives. Tools cover screen capture with P-frame compression (reducing token costs to ~160 tokens), mouse and keyboard input, Windows UI Automation, Chrome DevTools Protocol browser control, clipboard management, desktop notifications, and multi-step workflow batching. Designed for LLM efficiency with focused element queries completing in 2ms.

## Trust

- **Trust score (0–1):** 0.33
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** browser-automation
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/harusame64-desktop-touch)
- **Repository:** <https://github.com/harusame64/desktop-touch-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "harusame64-desktop-touch"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/harusame64-desktop-touch` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/harusame64-desktop-touch/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt