Use Case
MachineCommander is a powerful AI agent skill that extends your assistant with new capabilities. Use the Machinery Commander MCP service to query real-time data, status and location information of construction machinery and ships. Used to answer questions about the status, location, working conditions, etc. of machinery and equipment (excavators, loaders, dump trucks, concrete mixer trucks, etc.) and ships (transport ships, tugs, etc.) in construction projects. This skill must be used when users ask for specific data such as equipment quantity, location distribution, construction status, fuel consumption, alarms, etc. This guide walks you through installing MachineCommander, configuring it for your setup, and running your first commands β so you can start getting value in minutes.
Install MachineCommander: npx clawhub@latest --dir ~/.claude/skills install machine-commander-query
Restart your AI client (Claude Code, Cursor, Gemini CLI, or OpenClaw)
Type a natural language request related to data & analytics to trigger MachineCommander
Review the output and refine your prompt for better results
Combine MachineCommander with other skills to build multi-step workflows
Copy these prompts and use them with your AI agent after installing MachineCommander
Help me get started with MachineCommander
What can MachineCommander do for my data & analytics workflow?
Show me an example of using MachineCommander
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install machine-commander-queryOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install machine-commander-queryβ οΈ Requires Node.js 18+. No Node? Use Option 2 below to download the ZIP instead. Install Node.js β
Option 2: Manual install (no Node required)
Download the ZIP, extract it, and place the folder at the path below. Restart your agent to activate.
Install path
~/.claude/skills/machine-commander-query/π‘Extract and place the folder at the path above, then restart your agent.