mijia-control

Control and monitor Xiaomi Mijia smart home devices. Use this skill when the user wants to: 1) Switch device status (on/off, brightness, etc.) 2) List available home devices 3) Run automation scenes 4) Check environmental statistics.

40 stars
Complexity: medium

About this skill

The Mijia Control skill empowers AI agents to seamlessly interact with Xiaomi Mijia smart home devices via a locally encapsulated `mijiaAPI`. It provides agents with the ability to manage various aspects of a smart home environment, from basic device control to advanced scene automation and environmental monitoring. Key use cases include allowing an AI agent to respond to user commands for switching lights on or off, adjusting brightness or temperature, querying the status of all connected devices, and triggering predefined automation scenes within the Mijia ecosystem. Users can also request real-time environmental data, such as temperature or humidity, from their smart sensors. This skill is invaluable for anyone looking to integrate their Xiaomi Mijia smart home into an AI-driven automation framework. It enables more intuitive control through natural language commands processed by an AI agent, enhancing convenience and providing a centralized point of management for smart home functionalities.

Best use case

mijia-control is best used when you need a repeatable smart home & iot workflow instead of a one-off prompt. It is especially useful for teams working in multi. Control and monitor Xiaomi Mijia smart home devices. This skill allows an AI agent to switch device status, list available devices, run automation scenes, and check environmental statistics.

Control and monitor Xiaomi Mijia smart home devices. Use this skill when the user wants to: 1) Switch device status (on/off, brightness, etc.) 2) List available home devices 3) Run automation scenes 4) Check environmental statistics.

Users should expect a more consistent smart home & iot output, faster repeated execution, and less time spent rewriting prompts from scratch.

Practical example

Example input

Use the "mijia-control" skill to help with this smart home & iot task. Context: Control and monitor Xiaomi Mijia smart home devices. This skill allows an AI agent to switch device status, list available devices, run automation scenes, and check environmental statistics.

Example output

A structured smart home & iot result with clearer steps, more consistent formatting, and an output that is easier to reuse in the next run.

When to use this skill

  • Use this skill when you want a reusable workflow rather than writing the same prompt again and again.
  • Use it when you are solving a smart home & iot task and want a more structured operating flow.
  • Use it when you can invest a small amount of setup effort for a more repeatable workflow.

When not to use this skill

  • Do not use this when you only need a one-off answer and do not need a reusable workflow.
  • Do not use it if you cannot install or maintain the related files, repository context, or supporting tools.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/mijia-control/SKILL.md --create-dirs "https://raw.githubusercontent.com/lllooollpp/clawdbot-cn/main/skills/mijia-control/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/mijia-control/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How mijia-control Compares

Feature / Agentmijia-controlStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexitymediumN/A

Frequently Asked Questions

What does this skill do?

Control and monitor Xiaomi Mijia smart home devices. Use this skill when the user wants to: 1) Switch device status (on/off, brightness, etc.) 2) List available home devices 3) Run automation scenes 4) Check environmental statistics.

How difficult is it to install?

The installation complexity is rated as medium. You can find the installation instructions above.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Mijia Control Skill (Universal AI Agent Skill)

该技能使 AI 代理能够通过本地封装的 `mijiaAPI` 驱动,接管并控制小米米家智能家居设备。

> **注意**:本技能包内的所有脚本路径均为相对于本文件所在目录。执行时请务必使用**绝对路径**。

## 快速开始

1. **环境自检**:运行 `<SKILL_ROOT>/scripts/setup_env.py`。
2. **安装/登录**:
   - 安装:`python <SKILL_ROOT>/scripts/setup_env.py --install`。
   - 登录:运行 `mijiaAPI -l`。
3. **执行控制**:所有操作均通过 `<SKILL_ROOT>/scripts/` 下的脚本完成。

## 决策逻辑 (Decision Logic)

- **设备查询**:当用户询问“有哪些设备”、“状态如何”时 -> 执行 `scripts/list_devices.py` 获取实时快照。
- **设备控制**:当用户要求开关、调节亮度/温度等 -> 解析意图 -> 查阅 `reference/device_catalogs.md` -> 执行 `scripts/control_device.py`。
- **场景触发**:用户要求运行场景 -> 调用 CLI 命令执行。

## 约束建议 (Guardrails)

- 对于**窗帘、空调、锁**等涉及安全和昂贵能耗的设备,操作前需口头确认。
- 绝不向用户泄露 `auth.json` 中的敏感 Token。

## 更多信息
- 详尽 SOP 请参阅 [instructions.md](./instructions.md)。

Related Skills

ecovacs-robot-control

3891
from openclaw/skills

Control Ecovacs/DEEBOT robot vacuums via the Ecovacs IoT API. Use when the user wants to control a robot vacuum, check battery, start/stop/pause cleaning, return to dock, check clean status, set suction/water level, manage schedules, check consumables, or control auto-empty station. Covers all mainstream Ecovacs protocols including clean_V2, charge, getBattery, getCleanInfo_V2, getStats, getSpeed/setSpeed, getWaterInfo/setWaterInfo, getWorkMode/setWorkMode, getLifeSpan, getAutoEmpty/setAutoEmpty, getCachedMapInfo, getMapSet, getSched_V2/setSched_V2.

Smart Home & IoT

weather

40
from lllooollpp/clawdbot-cn

Get current weather and forecasts (no API key required).

wacli

40
from lllooollpp/clawdbot-cn

Send WhatsApp messages to other people or search/sync WhatsApp history via the wacli CLI (not for normal user chats).

voice-call

40
from lllooollpp/clawdbot-cn

Start voice calls via the Clawdbot voice-call plugin.

video-frames

40
from lllooollpp/clawdbot-cn

Extract frames or short clips from videos using ffmpeg.

```skill

40
from lllooollpp/clawdbot-cn

---

things-mac

40
from lllooollpp/clawdbot-cn

Manage Things 3 via the `things` CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks Clawdbot to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.

spotify-player

40
from lllooollpp/clawdbot-cn

Terminal Spotify playback/search via spogo (preferred) or spotify_player.

sonoscli

40
from lllooollpp/clawdbot-cn

Control Sonos speakers (discover/status/play/volume/group).

songsee

40
from lllooollpp/clawdbot-cn

Generate spectrograms and feature-panel visualizations from audio with the songsee CLI.

trello

40
from lllooollpp/clawdbot-cn

Manage Trello boards, lists, and cards via the Trello REST API.

tmux

40
from lllooollpp/clawdbot-cn

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.