Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
- Added new logs and debug reference: logs-and-debug.md replaces logs.md. - Updated documentation to improve clarity, guidance, and flow structure. - "Logs" references in core docs now point to logs-and-debug.md. - Streamlined main README: more concise starting guide, clarified canonical flows, and improved guardrails section.
What This Skill Does
Automates interactions with iOS simulators, iOS physical devices, Android emulators, and Android devices. Supports tapping, typing, scrolling, screenshots, UI snapshots, and log collection. Can run sequences as batch scripts or replay saved sessions.
Handles both iOS and Android targets through a single CLI interface, eliminating the need to switch between platform-specific tools for cross-platform mobile automation.
When to use it
- Automating a login flow on an iOS simulator
- Taking a screenshot of a specific app screen on Android
- Debugging a crash by capturing logs after reproducing steps
- Verifying UI elements are visible after a navigation action
- Replaying a saved interaction script after an app update
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: open the Settings app on iOS, tap the first element, type 'test' into a field, and take a diff snapshot
- 1Run `agent-device open Settings --platform ios` to start a session
- 2Run `agent-device snapshot -i` to capture the current UI tree with interactive refs
- 3Run `agent-device press @e1` to tap the first element
- 4Run `agent-device fill @e5 "test"` to clear and type into the target field
- 5Run `agent-device diff snapshot -i` to compare the updated UI state
Diff snapshot showing UI changes after the interaction sequence
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.