LaunchKit · 2026
Back to Skills

midscene-android-automation

Vision-driven Android device automation using Midscene.

0
1.1k downloads
by @quanru

Setup & Installation

openclaw skills install @quanru/midscene-android-automation

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install midscene-android-automation

Version History

v1.0.2Mar 7, 2026 - Version note by skill developer:

- Added rule: always summarize and report automation results to the user after completing tasks; never end silently. - Updated model configuration section with new examples for Qwen 3.5 and Doubao Seed 2.0 Lite, replacing older Qwen3-VL and Doubao Seed 1.6 references. - Enhanced workflow pattern and best practices to mandate proactive user reporting, specifying what information must be included in the summary. - Minor clarifications and improvements to existing documentation for prerequisites and expected output.

What This Skill Does

Controls Android devices using screenshot-based vision, with no DOM access or accessibility labels required. Accepts natural language commands to tap, swipe, type, launch apps, and capture screenshots. Works across any Android app regardless of the underlying framework.

Unlike Appium or UI Automator, it requires no accessibility labels or view hierarchy access, so it works on any app including games and fully custom-rendered UIs.

When to use it

  • Automating repetitive tasks in mobile apps that have no scriptable API
  • Extracting data from Android apps without a web or API equivalent
  • Testing a mobile UI without writing platform-specific test code
  • Running multi-step workflows in messaging or social apps
  • Capturing screenshots of specific app states for documentation or bug reports

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: 'Open Settings, go to Wi-Fi, and tell me the connected network name'

AGENT
  1. 1Connect to the Android device via ADB
  2. 2Launch the Settings app using adb shell am start and take a screenshot to confirm it is in the foreground
  3. 3Run act with the prompt 'navigate to Wi-Fi settings and read the connected network name'
  4. 4Take a screenshot to verify the current screen state
  5. 5Disconnect and report the network name extracted from the screen
OUTPUT

Connected Wi-Fi network name read from the device screen and reported to the user

Requirements

Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.

MIDSCENE_MODEL_API_KEY environment variable from a supported AI vision model providerMIDSCENE_MODEL_NAME, MIDSCENE_MODEL_BASE_URL, and MIDSCENE_MODEL_FAMILY environment variablesAndroid SDK Platform Tools (provides adb)Android device with USB debugging enabled in Developer Options