# computer-use

> Use this tool when you need to control a virtual desktop environment through natural language instructions, automating tasks such as clicking, moving, and typing. It solves problems like automating repetitive tasks, interacting with graphical user interfaces, and simulating user behavior. The tool accepts natural language inputs and outputs virtual desktop actions, making it ideal for use cases requiring human-like interaction with a computer interface.

Canonical page: https://skillsregistry.net/skills/sidebutton-plugin-computer-use  
JSON: https://api.skillsregistry.net/v1/skills/sidebutton-plugin-computer-use

## Description

Exposes Anthropic's computer-use action surface (screenshot, click, move, keyboard, clipboard, batch) against a persistent desktop display via MCP stdio protocol. Enables AI agents to control a virtual desktop environment through natural language instructions.

## Trust

- **Trust score (0–1):** 0.67
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/q9wl1pa40e)
- **Repository:** <https://github.com/sidebutton/plugin-computer-use>

## 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": "sidebutton-plugin-computer-use"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/sidebutton-plugin-computer-use` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/sidebutton-plugin-computer-use/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