# Box

> Box — jegly-box. Use this tool when you need to leverage private on-device AI capabilities on Android, solving problems such as secure image generation, voice chat, and vision AI tasks with CPU/NPU/GPU acceleration. It accepts various inputs, including voice and image data, and outputs generated images, chat responses, and more, all while maintaining encrypted history and biometric lock security. Ideal for use cases requiring local, private AI processing on Android devices.

Canonical page: https://skillsregistry.net/skills/jegly-box  
JSON: https://api.skillsregistry.net/v1/skills/jegly-box

## Description

The most advanced, fully offline client-side AI suite on Android today.

## Trust

- **Trust score (0–1):** 0.65
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/jegly/Box)

## 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": "jegly-box"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/jegly-box` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/jegly-box/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