agent-device
The agent-device skill provides a routing interface for the agent-device CLI to automate iOS, tvOS, macOS, and Android applications. It facilitates device interaction including navigation, UI inspection, input simulation, and performance data collection.
Is agent-device safe to install?
Review the source first: our audit of agent-device's source files found 10 shell commands, 0 external URLs, file reads and writes (high risk). Every command and URL listed appears verbatim in the skill's source. The skill executes shell commands on the host machine and interacts with local device environments, which carries risks associated with arbitrary command execution and local system access.
How we audit skills: our security review methodology.
Who is this skill for?
Developers and testers automating mobile and desktop application workflows on Apple and Android platforms.
What can you do with it?
- Navigating mobile and desktop applications
- Capturing screenshots and UI snapshots
- Simulating user input such as tapping, typing, and scrolling
- Extracting UI information and device logs
- Collecting network and performance evidence
- Preflighting iOS environments with doctor commands
How good is this skill?
Quality score: 5/10. The skill documentation is clear and provides specific instructions for CLI interaction and environment setup. It correctly identifies the need for version matching and safe execution practices.
What does the skill file contain?
# agent-device Router only. Private setup before using this skill: ```bash agent-device --version ``` If that fails but the user may have installed `agent-device` globally, check the user's configured login/interactive shell and environment before using `npx`. Resolve the command the same way the user would from a normal terminal session, then run the absolute binary path if found. This may require inspecting shell startup behavior or package-manager/global bin locations; do not assume the Codex process `PATH` is the user's `PATH`. Require `agent-device >= 0.14.0`; older CLIs lack these he...
Frequently asked questions
What are the prerequisites for using this skill?
The user must have agent-device version 0.14.0 or higher installed on their system.
How does the skill handle environment paths?
The skill inspects shell startup behavior and package manager locations to resolve the absolute binary path rather than relying on the default process PATH.
Can the skill update the agent-device CLI automatically?
No. The skill prohibits autonomous execution of npm install or npx commands for version upgrades.
Related skills
find-skills
2.3MUsers seeking to extend agent capabilities with specialized tools, workflows, or knowledge packages
The find-skills skill enables agents to search for, discover, and install modular packages from the open agent skills ecosystem using the Skills CLI.
agent-browser
506.7KAI agents and developers requiring programmatic web interaction, exploratory testing, or automation of Electron desktop applications
The agent-browser CLI provides browser automation for AI agents using Chrome or Chromium via CDP. It supports page navigation, form interaction, data extraction, and testing. The tool utilizes accessibility-tree snapshots and element references for interaction.
video-edit
338.7KUsers of the RunComfy CLI who need to automate video editing tasks like restyling, background swapping, or motion transfer
The video-edit skill acts as a router for the RunComfy CLI, selecting between Wan 2.7 Edit-Video, Kling 2.6 Pro Motion Control, and Lucy Edit Restyle models based on user intent to perform video transformations.
agentspace
324.0KDevelopers and AI agent users who need to share, monitor, or collaborate on agent-generated files and workspaces in real-time
Agentspace provides a mechanism to share local agent files, logs, and artifacts via a live browser-accessible URL. It enables remote viewing, commenting, and editing of specified local paths through the ascli command-line tool.