# macos-computer-use-kit

> macos-computer-use-kit — sur-cai-macos-computer-use-kit. Use this tool when you need to interact with macOS computers in an accessible and safe manner, leveraging features like accessibility-tree targeting and read-back verification to ensure accurate and reliable input. It solves problems related to automated computer use, providing a calibrated and guarded approach to decision-making and action execution. Ideal for AI agents requiring precise control over macOS systems, with interfaces including a pip CLI, pi package, and DeepSeek Harness plugin.

Canonical page: https://skillsregistry.net/skills/sur-cai-macos-computer-use-kit  
JSON: https://api.skillsregistry.net/v1/skills/sur-cai-macos-computer-use-kit

## Description

AX-first computer use for AI agents on macOS with optional Jev (TypeSafe System One) semantic guards: calibrated target/input judgments before an irreversible action, decisions kept in code. Accessibility-tree targeting, window-scoped input, clipboard-safe paste, read-back verification. Ships a pip CLI, a pi package and a DeepSeek Harness plugin.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/Sur-Cai/macos-computer-use-kit)

## 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": "sur-cai-macos-computer-use-kit"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/sur-cai-macos-computer-use-kit` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/sur-cai-macos-computer-use-kit/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