Android Device Automation

If you need to automate Android UI testing but don't have access to the DOM or accessibility tree, this handles it with computer vision instead. It works directly from screenshots, which means you can test apps where traditional automation tools can't hook in, or where the UI hierarchy is a mess. The approach is straightforward: you tell it what to do, it looks at the screen, finds the elements visually, and interacts with them. It's from the Midscene project (223 stars, 1.6K installs), so there's some community validation. The tradeoff is obvious: vision-based automation is inherently less precise than DOM-based, but when you literally can't access the structure, this gives you an option that actually works.

skills.sh installs: 5.5K
GitHub stars: 321
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add web-infra-dev/midscene-skills --skill android-device-automation --agent claude-code

Installs into .claude/skills of the current project.

Files

Android Device Automation

CRITICAL RULES — VIOLATIONS WILL BREAK THE WORKFLOW:

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.

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.

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.

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.