Skip to content
TakoAPI
Back to skills

midscene-android-automation

by quanru

Web & Frontend Development
1.1kDownloads reported by clawskills.sh
0Views
0 likesSign in to like this skill
—Not yet rated
Your rating

Brief

Vision-driven Android device automation using Midscene.

Description

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

INPUT

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

AGENT
  1. 1

    Connect to the Android device via ADB

  2. 2

    Launch the Settings app using adb shell am start and take a screenshot to confirm it is in the foreground

  3. 3

    Run act with the prompt 'navigate to Wi-Fi settings and read the connected network name'

  4. 4

    Take a screenshot to verify the current screen state

  5. 5

    Disconnect 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

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

Installation

clawhub install quanru/midscene-android-automation

Run the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.

Links