ios-device-automation

Control and verify iOS screens with natural-language steps.

mobile test automation

What it does

Automates and verifies visible iOS device interactions through screenshot-driven natural-language control.

When to use it

Use for iPhone or iPad interaction, testing, navigation, QA, and visual verification.

Give it an iOS automation or verification request; it controls the device and returns results, findings, and generated-file paths.

This skill

configured model API

Write

Sends screenshots for AI inference

reference image URLs

Read

Fetches supplied reference images

@midscene/ios@1

Execute

The Midscene iOS CLI

iOS device

Write

Controls your iOS device

Requires an iOS device connected through USB and trusted by the computer.

WebDriverAgent must be installed and running on the device.

Requires a configured visual-grounding model endpoint for screenshot analysis and inference.

Reads the model API key from a system environment variable or a .env file in the current working directory.