# Atomic Computer

> Use this tool when you need to automate interactions with native Windows desktop applications, such as clicking, typing, or inspecting windows, and require precise control over mouse and keyboard inputs. It provides low-level primitives for screen capture, window inspection, and input simulation, making it suitable for vision-capable AI models. Ideal for use cases where browser-based automation is not feasible, and deterministic desktop automation is required.

Canonical page: https://skillsregistry.net/skills/dawdler-g-atomic-computer  
JSON: https://api.skillsregistry.net/v1/skills/dawdler-g-atomic-computer

## Description

Exposes low-level, non-browser desktop automation primitives for Windows. Provides screen capture with DPI-aware coordinate mapping, foreground window inspection, mouse click and drag, keyboard press and type operations, and condition-based waiting. Designed as a deterministic tool layer for vision-capable AI models to interact with native desktop applications.

## Trust

- **Trust score (0–1):** 0.83
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** browser-automation
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/dawdler-g-atomic-computer)
- **Repository:** <https://github.com/dawdler-g/atomic-computer-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": "dawdler-g-atomic-computer"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/dawdler-g-atomic-computer` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/dawdler-g-atomic-computer/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