A conversational companion layer for Roborock vacuums that enables natural language control for room-specific cleaning and status monitoring.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install roborock-conversational-control
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install roborock-conversational-control using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Jojo Bot?
Jojo Bot is a specialized high-level companion layer designed to transform standard Roborock vacuum cleaners into interactive agents within the Openclaw Skills ecosystem. Unlike raw device controllers, Jojo Bot provides a conversational persona, allowing users to interact with their hardware using intuitive phrases. It is specifically optimized for OpenClaw chat interfaces and Telegram bot integrations, making home maintenance feel like a dialogue rather than a technical task.
By acting as a bridge between the user and the python-roborock CLI, this skill manages complex room mappings and device states. It allows developers to deploy a dedicated device identity that understands context, such as cleaning specific areas or returning to the dock, without requiring the user to memorize technical command syntax.
Jojo Bot Use Cases
- Controlling Roborock vacuums through natural language in Telegram or OpenClaw chat.
- Triggering room-specific cleaning cycles using friendly aliases like kitchen or living room.
- Checking vacuum battery levels and operational status via conversational queries.
- Pausing or docking the vacuum quickly during phone calls or meetings.
How Jojo Bot Works
- The AI agent receives a natural language prompt from the user through the Openclaw Skills interface.
- The agent identifies the intent (e.g., start, stop, room clean) and maps it to the appropriate command.
- The skill executes a local shell wrapper located at scripts/jojo.sh using the exec tool.
- The wrapper reads configuration details and room aliases from a local jojo.env file.
- Commands are passed to the underlying Roborock CLI to perform the physical action on the device.
- The agent provides a short, conversational confirmation or status update back to the user.
Jojo Bot Setup
To get started with Jojo Bot in your collection of Openclaw Skills, follow these steps:
- Ensure you have
bash,python3, and theroborockCLI installed on your system. - Navigate to the skill directory and create a configuration file:
cp jojo.env.example jojo.env
- Edit
jojo.envto include yourJOJO_DEVICE_IDand desiredROOM_<ALIAS>mappings. - To automatically map your rooms from the Roborock cloud, run:
bash ./scripts/refresh_room_aliases.sh
Jojo Bot Data Schema & Taxonomy
The skill manages its operational data and hardware mappings through a structured environment configuration:
| Data Point | Source | Purpose |
|---|---|---|
| JOJO_DEVICE_ID | jojo.env | Unique identifier for the Roborock hardware |
| ROOM_ALIAS | jojo.env | Maps friendly names (e.g., 'Kitchen') to numeric Roborock IDs |
| Status Metadata | Roborock CLI | Real-time battery, state, and location data |
| Execution Logs | Local Shell | Tracks command history and success rates |
Jojo Bot Advanced Features
- Room Alias Bootstrapping: Use the refresh script to automatically sync your physical floor plan with conversational aliases.
- Intent Mapping: Advanced logic to handle ambiguous room requests with intelligent follow-up questions.
- Dedicated Persona: Optimized for Telegram bot binding to create a standalone vacuum agent.
- Local Wrapper Execution: Uses direct shell execution for low-latency response times compared to session-based control.
SKILL.md
Loading
Related Openclaw Skills
Hita Mind and Knowledge
A sophisticated dual-module memory and knowledge management system designed to give AI agents long-term recall and structured expertise.
Child Growth Tracker & Assessment V2
An advanced child development tracking system based on an 8-dimensional psychological model to monitor growth while protecting internal motivation.
a2a.fun
a2a.fun is a coordination harness designed for seamless multi-agent collaboration on shared projects, tasks, and proposals.
Excalidraw Diagram Generator
A powerful AI skill that transforms natural language descriptions into professional, hand-drawn Excalidraw visual diagrams.
IFTTT Integration for AI Agents
A powerful integration skill that enables AI agents to automate workflows by managing IFTTT applets, triggers, and actions through the Membrane ecosystem.
Amazon SageMaker
A comprehensive integration for managing Amazon SageMaker machine learning resources and automating data workflows.
Featured*
