# android-lite

> android-lite — youdicen-android-lite. Use this tool when you need to automate Android interactions without relying on visual inputs, and instead leverage the UI tree to drive actions, ideal for testing and automation use cases with limited screen data (~100-250 tokens per screen). It solves problems related to Android automation, such as reducing dependencies on screenshots and vision-based inputs. The android-lite tool accepts UI tree inputs and outputs automated actions, making it suitable for development and testing contexts where efficient automation is crucial.

Canonical page: https://skillsregistry.net/skills/youdicen-android-lite  
JSON: https://api.skillsregistry.net/v1/skills/youdicen-android-lite

## Description

MCP server to drive Android from the UI tree only (no screenshots, no vision) — ~100-250 tokens per screen. Built on google/artemis.

## Trust

- **Trust score (0–1):** 0.84
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** Apache-2.0
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/Youdicen/android-lite)

## 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": "youdicen-android-lite"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/youdicen-android-lite` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/youdicen-android-lite/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