Skip to main content
Mobilerun publishes an agent skill — a self-contained knowledge pack that tells an AI agent everything it needs to know to use the Mobilerun API. Once installed, the agent can take screenshots, tap and swipe, type, manage apps, and run autonomous tasks on a real Android device, all without any manual API wiring on your part.

​
What Is a Skill?

A skill is a bundle of markdown reference files with a SKILL.md entry point. When loaded by a compatible agent runtime (such as OpenClaw), the agent reads these files at the start of a session and gains structured knowledge about an API — its endpoints, authentication, error handling, and usage patterns. The Mobilerun skill includes:

​
Requirements

​
Installation

If you are using the OpenClaw agent CLI, install the skill as a plugin:
See the OpenClaw setup guide for full configuration instructions.

​
Direct Download (other runtimes)

Download the pre-packaged .skill file and load it into any compatible agent runtime:

mobilerun.skill

Download the latest release from GitHub
The .skill file is a zip archive containing the full set of reference documents. Refer to your agent runtime’s documentation for how to load a .skill file.

​
What the Skill Enables

Once installed and given an API key, the agent gains two ways to control a device:

Direct Phone Control

Step-by-step device interaction: screenshot, tap, swipe, type, press keys, open apps. Best for quick, precise actions.

Autonomous Agent Tasks

Submit a natural language goal ("Book a table for 2 at 7pm") and the Mobilerun AI agent executes it on the device end-to-end. Requires credits.

​
How the Agent Uses the Skill

The agent follows a structured initialization flow on every session:
  1. Checks for an API key — looks in MOBILERUN_API_KEY env var or the OpenClaw config file. If missing, it asks the user once.
  2. Verifies the key and discovers devices — calls GET /devices. A 200 response with a ready device means the agent proceeds immediately.
  3. Guides setup only when needed — if no device is found, the agent walks the user through installing the Mobilerun Portal app and connecting.
  4. Executes the request — once a ready device is confirmed, the agent completes the user’s task without additional prompts.

​
Available LLM Models for Agent Tasks

When submitting autonomous tasks, you can specify which model drives the agent. The Agent page holds the canonical catalog of llmModel values. To see the live list your account can use, call GET /v1/models, or use client.models.list() in the SDK.

​
Source

The skill is open source and maintained in the droidrun/skills repository. New releases are built automatically on every push to master.