30★by hqman
mijia – OpenClaw Skill
mijia is an OpenClaw Skills integration for coding workflows. Control Xiaomi Mijia smart home devices. Use this skill when the user wants to control desk lamps, smart plugs, or other Mijia devices. Supports turning lights on/off, adjusting brightness, setting color temperature, switching modes, and more.
Skill Snapshot
| name | mijia |
| description | Control Xiaomi Mijia smart home devices. Use this skill when the user wants to control desk lamps, smart plugs, or other Mijia devices. Supports turning lights on/off, adjusting brightness, setting color temperature, switching modes, and more. OpenClaw Skills integration. |
| owner | hqman |
| repository | hqman/mijia |
| language | Markdown |
| license | MIT |
| topics | |
| security | L1 |
| install | openclaw add @hqman/mijia |
| last updated | Feb 7, 2026 |
Maintainer

name: mijia description: Control Xiaomi Mijia smart home devices. Use this skill when the user wants to control desk lamps, smart plugs, or other Mijia devices. Supports turning lights on/off, adjusting brightness, setting color temperature, switching modes, and more. invocable: true
Mijia Smart Home Control
Control Xiaomi Mijia smart devices via the mijiaAPI.
Setup
Before using this skill, you need to:
- Install dependencies:
cd /path/to/mijia-skill
uv sync
- Set your device ID as an environment variable:
export MIJIA_LAMP_DID="your_device_id"
- First run will prompt for Xiaomi account login via QR code.
Finding Device IDs
To find your device IDs, use the mijia-api library:
from mijiaAPI import mijiaAPI
api = mijiaAPI()
api.login()
devices = api.get_device_list()
for d in devices:
print(f"{d['name']}: {d['did']}")
How to Use
Skill path: ~/.clawdbot/skills/mijia
Lamp Control Commands
# Navigate to skill directory
cd ~/.claude/skills/mijia
# Check status
uv run python scripts/lamp_cli.py status
# Turn on/off
uv run python scripts/lamp_cli.py on
uv run python scripts/lamp_cli.py off
uv run python scripts/lamp_cli.py toggle
# Adjust brightness (1-100%)
uv run python scripts/lamp_cli.py brightness 50
# Adjust color temperature (2700-6500K)
uv run python scripts/lamp_cli.py temp 4000
# Set mode
uv run python scripts/lamp_cli.py mode reading # Reading mode
uv run python scripts/lamp_cli.py mode computer # Computer mode
uv run python scripts/lamp_cli.py mode night # Night reading
uv run python scripts/lamp_cli.py mode antiblue # Anti-blue light
uv run python scripts/lamp_cli.py mode work # Work mode
uv run python scripts/lamp_cli.py mode candle # Candle effect
uv run python scripts/lamp_cli.py mode twinkle # Twinkle alert
Natural Language Understanding
When the user says the following, execute the corresponding command:
| User Says | Command |
|---|---|
| Turn on the light / open lamp | scripts/lamp_cli.py on |
| Turn off the light / close lamp | scripts/lamp_cli.py off |
| Toggle the light | scripts/lamp_cli.py toggle |
| Brighter / more bright | Check status first, then increase by 20-30% |
| Dimmer / less bright | Check status first, then decrease by 20-30% |
| Full brightness / maximum | scripts/lamp_cli.py brightness 100 |
| Minimum brightness | scripts/lamp_cli.py brightness 1 |
| Warm light | scripts/lamp_cli.py temp 2700 |
| Cool light / white light | scripts/lamp_cli.py temp 6500 |
| Reading mode | scripts/lamp_cli.py mode reading |
| Computer mode | scripts/lamp_cli.py mode computer |
| Night mode | scripts/lamp_cli.py mode night |
| Lamp status / what's the light status | scripts/lamp_cli.py status |
Before Executing
- Navigate to skill directory:
cd ~/.clawdbot/skills/mijia - Ensure
MIJIA_LAMP_DIDenvironment variable is set - Run with uv:
uv run python scripts/lamp_cli.py <command> - Report the result to the user after execution
Mijia Smart Home Control
A skill/plugin for AI coding agents to control Xiaomi Mijia smart home devices through natural language commands.

Works with:
- OpenClaw - Open source AI coding agent
- Claude Code
- OpenCode
- Droid
- Other AI coding assistants that support custom skills/tools
Features
- Control Xiaomi Mijia smart devices via natural language
- Support for desk lamps, smart plugs, and other Mijia devices
- Brightness and color temperature adjustment
- Multiple lighting modes (reading, computer, night, etc.)
- Easy to extend for additional device types
Prerequisites
- Python 3.13+
- uv package manager
- Xiaomi account with Mijia devices
Installation
- Clone this repository:
git clone https://github.com/user/mijia-skill.git
cd mijia-skill
- Install dependencies:
uv sync
- Configure your device ID:
export MIJIA_LAMP_DID="your_device_id"
- First run will prompt for Xiaomi account login via QR code.
Finding Your Device ID
Use the mijia-api library to find your device IDs:
from mijiaAPI import mijiaAPI
api = mijiaAPI()
api.login() # Scan QR code to login
devices = api.get_device_list()
for device in devices:
print(f"{device['name']}: {device['did']}")
Environment Variables
| Variable | Description |
|---|---|
MIJIA_LAMP_DID | Device ID for the desk lamp |
Usage
CLI Commands
# Check status
uv run python scripts/lamp_cli.py status
# Power control
uv run python scripts/lamp_cli.py on
uv run python scripts/lamp_cli.py off
uv run python scripts/lamp_cli.py toggle
# Brightness (1-100%)
uv run python scripts/lamp_cli.py brightness 50
# Color temperature (2700-6500K)
uv run python scripts/lamp_cli.py temp 4000
# Lighting modes
uv run python scripts/lamp_cli.py mode reading # Reading mode
uv run python scripts/lamp_cli.py mode computer # Computer mode
uv run python scripts/lamp_cli.py mode night # Night reading
uv run python scripts/lamp_cli.py mode antiblue # Anti-blue light
uv run python scripts/lamp_cli.py mode work # Work mode
uv run python scripts/lamp_cli.py mode candle # Candle effect
uv run python scripts/lamp_cli.py mode twinkle # Twinkle alert
Natural Language Examples
Once integrated with your AI coding agent, you can use natural language:
- "Turn on the light" / "Turn off the light"
- "Make it brighter" / "Make it dimmer"
- "Set brightness to 80%"
- "Switch to reading mode"
- "Warm light please" / "Cool white light"
- "What's the lamp status?"
Integration
Claude Code
Copy the skill to your Claude Code skills directory:
cp -r . ~/.clawdbot/skills/mijia
Other AI Agents
Add the SKILL.md content to your agent's system prompt or tool configuration. The skill provides:
- Device control commands
- Natural language mapping table
- Usage instructions
Extending
You can extend this skill to support more device types. See scripts/lamp_cli.py for an example implementation.
The mijia-api library supports:
- Smart plugs
- Air purifiers
- Vacuum cleaners
- Rice cookers
- Door locks
- And more Mijia devices
Credits
Built on top of mijia-api by Do1e.
License
MIT License
Permissions & Security
Security level L1: Low-risk skills with minimal permissions. Review inputs and outputs before running in production.
Requirements
- OpenClaw CLI installed and configured.
- Language: Markdown
- License: MIT
- Topics:
FAQ
How do I install mijia?
Run openclaw add @hqman/mijia in your terminal. This installs mijia into your OpenClaw Skills catalog.
Does this skill run locally or in the cloud?
OpenClaw Skills execute locally by default. Review the SKILL.md and permissions before running any skill.
Where can I verify the source code?
The source repository is available at https://github.com/openclaw/skills/tree/main/skills/hqman/mijia. Review commits and README documentation before installing.
