android-device-automation

What this skill does

# Android Device Automation

> **CRITICAL RULES — VIOLATIONS WILL BREAK THE WORKFLOW:**
>
> 1. **Never run midscene commands in the background.** Each command must run synchronously so you can read its output (especially screenshots) before deciding the next action. Background execution breaks the screenshot-analyze-act loop.
> 2. **Run only one midscene command at a time.** Wait for the previous command to finish, read the screenshot, then decide the next action. Never chain multiple commands together.
> 3. **Allow enough time for each command to complete.** Midscene commands involve AI inference and screen interaction, which can take longer than typical shell commands. A typical command needs about 1 minute; complex `act` commands may need even longer.
> 4. **Always report task results before finishing.** After completing the automation task, you MUST proactively summarize the results to the user — including key data found, actions completed, screenshots taken, and any relevant findings. Never silently end after the last automation step; the user expects a complete response in a single interaction.

Automate Android devices using `npx -y @midscene/android@1`. Each CLI command maps directly to an MCP tool — you (the AI agent) act as the brain, deciding which actions to take based on screenshots.

## What `act` Can Do

Inside a single `act` call on Android, Midscene can tap, double-tap, long-press, type, clear text, scroll or swipe in any direction, pull to refresh, drag items, zoom with two fingers, press keys, and use system navigation such as Back, Home, or recent apps while working from the current visible screen.

## Prerequisites

Midscene requires models with strong visual grounding capabilities. The following environment variables must be configured — either as system environment variables or in a `.env` file in the current working directory (Midscene loads `.env` automatically):

```bash
MIDSCENE_MODEL_API_KEY="your-api-key"
MIDSCENE_MODEL_NAME="model-name"
MIDSCENE_MODEL_BASE_URL="https://..."
MIDSCENE_MODEL_FAMILY="family-identifier"
```

Example: Gemini (Gemini-3-Flash)

```bash
MIDSCENE_MODEL_API_KEY="your-google-api-key"
MIDSCENE_MODEL_NAME="gemini-3-flash"
MIDSCENE_MODEL_BASE_URL="https://generativelanguage.googleapis.com/v1beta/openai/"
MIDSCENE_MODEL_FAMILY="gemini"
```

Example: Qwen 3.5

```bash
MIDSCENE_MODEL_API_KEY="your-aliyun-api-key"
MIDSCENE_MODEL_NAME="qwen3.5-plus"
MIDSCENE_MODEL_BASE_URL="https://dashscope.aliyuncs.com/compatible-mode/v1"
MIDSCENE_MODEL_FAMILY="qwen3.5"
MIDSCENE_MODEL_REASONING_ENABLED="false"
# If using OpenRouter, set:
# MIDSCENE_MODEL_API_KEY="your-openrouter-api-key"
# MIDSCENE_MODEL_NAME="qwen/qwen3.5-plus"
# MIDSCENE_MODEL_BASE_URL="https://openrouter.ai/api/v1"
```

Example: Doubao Seed 2.0 Lite

```bash
MIDSCENE_MODEL_API_KEY="your-doubao-api-key"
MIDSCENE_MODEL_NAME="doubao-seed-2-0-lite"
MIDSCENE_MODEL_BASE_URL="https://ark.cn-beijing.volces.com/api/v3"
MIDSCENE_MODEL_FAMILY="doubao-seed"
```

Commonly used models: Doubao Seed 2.0 Lite, Qwen 3.5, Zhipu GLM-4.6V, Gemini-3-Pro, Gemini-3-Flash.

If the model is not configured, ask the user to set it up. See [Model Configuration](https://midscenejs.com/model-common-config) for supported providers.

## Commands

### Common Android CLI Flags

Use these flags on commands that create or use the Android agent, such as `connect`, `take_screenshot`, `act`, `assert`, and `tap`:

- `--device-id <id>`: Target a specific Android device from `adb devices`.
- `--use-scrcpy`: Enable scrcpy accelerated screenshots. Use this when normal screenshot capture is slow or unstable. Because CLI invocations are stateless, pass this flag on each Android Midscene command where you want scrcpy-based screenshots.

### Connect to Device

```bash
npx -y @midscene/android@1 connect
npx -y @midscene/android@1 connect --device-id emulator-5554
npx -y @midscene/android@1 connect --device-id emulator-5554 --use-scrcpy
```

### Launch an App or URL

Use the dedicated launch step when you want a deterministic starting point before the rest of the task:

```bash
npx -y @midscene/android@1 launch --uri https://www.ebay.com
npx -y @midscene/android@1 launch --uri com.android.settings
npx -y @midscene/android@1 launch --uri com.android.settings/.Settings
```

### Run a Raw Android Shell Command

Use this when the task needs lower-level device control that is not best expressed as a visible UI interaction:

```bash
npx -y @midscene/android@1 runadbshell --command "dumpsys battery"
```

This is forwarded to `adb shell` on the connected device. In practice, the underlying command is `adb -s <deviceId> shell dumpsys battery` and some environments may also include the default ADB server port, such as `adb -P 5037 -s <deviceId> shell dumpsys battery`.

### Take Screenshot

```bash
npx -y @midscene/android@1 take_screenshot
npx -y @midscene/android@1 take_screenshot --device-id emulator-5554 --use-scrcpy
```

After taking a screenshot, read the saved image file to understand the current screen state before deciding the next action.

### Perform Action

Use `act` to interact with the device and get the result. It autonomously handles all UI interactions internally — tapping, typing, scrolling, swiping, waiting, and navigating — so you should give it complex, high-level tasks as a whole rather than breaking them into small steps. Describe **what you want to do and the desired effect** in natural language:

```bash
# specific instructions
npx -y @midscene/android@1 act --prompt "type hello world in the search field and press Enter"
npx -y @midscene/android@1 act --prompt "long press the message bubble and tap Delete in the popup menu"
npx -y @midscene/android@1 act --device-id emulator-5554 --use-scrcpy --prompt "type hello world in the search field and press Enter"

# or target-driven instructions
npx -y @midscene/android@1 act --prompt "open Settings and navigate to Wi-Fi settings, tell me the connected network name"
```

### Assert Current Screen State

Use `assert` to verify that the current screen satisfies a natural language condition. It does not perform UI actions; it checks the visible screen state and passes only when the assertion is true. Use this for validation, QA checks, and final state verification after `act`.

```bash
npx -y @midscene/android@1 assert --prompt "there is a login button visible"
npx -y @midscene/android@1 assert --prompt "the settings screen shows Wi-Fi and Bluetooth options"
npx -y @midscene/android@1 assert --device-id emulator-5554 --prompt "the app shows a successful login message"
npx -y @midscene/android@1 assert --device-id emulator-5554 --use-scrcpy --prompt "the app shows a successful login message"
```

By default a failed assertion throws an AI-generated reason. Pass `--message` to throw a custom error message instead, which is useful for surfacing the intended outcome in QA and CI logs.

```bash
npx -y @midscene/android@1 assert \
  --prompt "the order confirmation screen is visible" \
  --message "the order should be confirmed after tapping Pay"
```

When the assertion needs to compare against a reference image (icon, logo, screenshot), pass `--image` for the URL/path and `--image-name` for its display name. Each `--image` may be an http(s) link, a `data:` URI, or a local file path. Repeat both flags in matching order when you need to attach more than one image. Add `--convertHttpImage2Base64 true` when the model cannot reach the URL directly. Requires `@midscene/[email protected]+`.

```bash
npx -y @midscene/android@1 assert \
  --prompt "the visible app icon matches the supplied reference image" \
  --image "https://github.githubassets.com/assets/GitHub-Mark-ea2971cee799.png" \
  --image-name "icon" \
  --convertHttpImage2Base64 true

# or with a local file
npx -y @midscene/android@1 assert \
  --prompt "the header on screen matches the local screenshot" \
  --image "./fixtures/header.png" \
  --image-name "header"

# multiple reference images — pair --