argent-device-interact

Automate touch and UI interactions on iOS simulators and Android emulators.

34|2|Updated Aug 16, 2025
One-click install
npx skills add https://github.com/FilenCloudDienste/filen-ts --skill argent-device-interact-filenclouddienste
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: argent-device-interact
Source: https://github.com/FilenCloudDienste/filen-ts/tree/main/.claude/skills/argent-device-interact
Command: npx skills add https://github.com/FilenCloudDienste/filen-ts --skill argent-device-interact-filenclouddienste

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill solves the problem of reliably performing touch-based device interactions—like tapping, swiping, typing, and screenshots—across iOS simulators and Android emulators in an automated way.

Core Features & Use Cases

  • Unified device interaction: Use the same interaction tool names for iOS and Android by providing a udid that auto-dispatches to the correct platform (iOS simulator vs Android adb serial).
  • UI discovery-first workflow: Prefer accessibility-based discovery with describe, and use native-describe-screen or React Native-specific debugger-component-tree when needed.
  • Complete interaction surface: Perform taps, swipes, pinch/rotate gestures, hardware button presses, app launching, opening URLs, typing (iOS paste, cross-platform keyboard), and orientation changes.
  • Deterministic sequencing: Use run-sequence to batch interactions in one call when you do not need visual confirmation between steps.

Quick Start

Use list-devices to find a ready simulator/emulator udid, then use describe to locate UI targets before calling gesture-tap or keyboard to interact.

Frequently Asked Questions about argent-device-interact

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate touch interactions and UI testing across iOS simulators and Android emulators?

You can automate touch interactions across iOS simulators and Android emulators using a unified tool surface that dispatches commands via a device udid. It supports taps, swipes, gestures, typing, screenshots, and orientation changes for consistent cross-platform testing.

What's the best way to locate UI elements before performing automated gestures on a mobile simulator?

The best way to locate UI elements is a discovery-first workflow using accessibility-based discovery commands. You can also use screen description tools or React Native-specific component tree debugging to identify targets before executing gestures.

Does automated mobile testing work with both iOS simulator and Android emulator using the same interaction commands?

Yes, cross-platform automated testing works by providing a device udid that auto-dispatches to the correct platform. The same interaction tool names handle both iOS simulator and Android emulator commands, though typing differs slightly with iOS using paste versus cross-platform keyboard input.

How do I type text into an iOS simulator versus an Android emulator during automated testing?

To type text during automated testing, iOS simulators use a paste command while Android emulators use a cross-platform keyboard command. Both methods accept normalized coordinates and target the active text field identified during UI discovery.

Can I batch multiple mobile device interactions like taps and swipes into a single automated call?

Yes, you can batch multiple device interactions into a single call using deterministic sequencing. This allows you to group taps, swipes, and text input together when visual confirmation between steps is not required.

Why do my automated gesture taps miss the target UI element on the mobile emulator?

Automated gesture taps miss targets when coordinates are not normalized to the 0.0 to 1.0 range. You must use normalized coordinates and ensure the correct tool schema is loaded for gesture tools to accurately hit the discovered UI elements.