← 返回 Skills 市场
2591
总下载
2
收藏
9
当前安装
1
版本数
在 OpenClaw 中安装
/install mijia
功能描述
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.
安全使用建议
Before installing or running this skill, consider the following:
- The skill will require you to set MIJIA_LAMP_DID and to login to your Xiaomi account (QR code). Confirm where the mijiaAPI library stores login tokens/credentials on disk (cookies, config files) and whether you are comfortable with that storage location.
- The registry metadata does NOT list MIJIA_LAMP_DID as a required env var, and SKILL.md/README use inconsistent directory paths (~/.clawdbot vs ~/.claude vs /path/to). Ask the author to fix metadata and docs so requirements are explicit.
- The skill depends on the third-party package 'mijiaapi' (pyproject.toml). Inspect that package's source or its PyPI/GitHub repo for any network endpoints, telemetry, or unexpected behaviors before running 'uv sync'.
- Run the skill in an isolated environment (virtualenv or disposable VM) the first time to observe what files/tokens it creates and what network calls it makes.
- If you only want the AI to issue commands and not perform autonomous installs/logins, avoid allowing autonomous invocation until metadata and behavior are clarified.
If the author can (1) list MIJIA_LAMP_DID in the skill metadata, (2) fix the path inconsistencies, and (3) document where login tokens are stored (and confirm no unrelated credentials are accessed), this would reduce the outstanding concerns.
功能分析
Type: OpenClaw Skill
Name: mijia
Version: 0.1.0
The skill is designed to control Xiaomi Mijia smart home devices, and all analyzed files align with this stated purpose. The `SKILL.md` provides clear instructions for the AI agent to execute commands via `scripts/lamp_cli.py`, which interacts with the `mijiaAPI` library. The script reads the `MIJIA_LAMP_DID` environment variable for device identification and calls `api.login()` for authentication, both of which are necessary and explicitly documented for smart home device control. There is no evidence of prompt injection with malicious intent, data exfiltration to unauthorized endpoints, malicious execution, persistence mechanisms, or obfuscation. The dependency on `mijiaapi` is declared in `pyproject.toml` and is central to the skill's functionality.
能力评估
Purpose & Capability
Name/description align with included code: the CLI (scripts/lamp_cli.py) and README implement lamp control via a mijiaAPI library. The declared project dependency (mijiaapi) is appropriate for the stated function.
Instruction Scope
SKILL.md instructs the agent to install dependencies (uv sync), set MIJIA_LAMP_DID, login via Xiaomi QR code, and run scripts/lamp_cli.py. Those steps are within scope for a device-control skill, but the skill documentation uses multiple inconsistent install/run paths (e.g., ~/.clawdbot/skills/mijia, ~/.claude/skills/mijia, and /path/to/mijia-skill) and the runtime instructions rely on the external mijiaAPI library (which will perform network login and store tokens) without describing where credentials/tokens are persisted.
Install Mechanism
No install spec is declared in the registry (instruction-only), but a pyproject.toml lists mijiaapi as a dependency and README/SKILL.md require running 'uv sync' / 'uv run'. The skill will therefore pull a third-party package from PyPI (or equivalent) when installed — the package source and behavior are not included in the skill, so you must audit that dependency separately. No arbitrary HTTP downloads or embedded obfuscated installers were found in the skill itself.
Credentials
The registry metadata lists no required env vars or primary credential, but SKILL.md and the CLI require MIJIA_LAMP_DID and the user to login to a Xiaomi account. The skill does not declare this required environment variable in its metadata, and it does not explain where login tokens will be stored. Asking for a Xiaomi account login and device ID is expected for this functionality, but the mismatch between declared requirements and actual instructions is a gap that could hide assumptions about stored credentials or token persistence.
Persistence & Privilege
The skill does not request always:true, does not declare system-wide config paths, and does not attempt to modify other skills. It requires the agent to run the CLI manually (or be invoked), and the included code performs only device operations via the external library.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install mijia - 安装完成后，直接呼叫该 Skill 的名称或使用
/mijia触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v0.1.0
- Initial release: Control Xiaomi Mijia smart home devices via command line.
- Supports turning lights on/off, toggling, adjusting brightness and color temperature, and switching modes (reading, computer, night, etc).
- Provides natural language mappings for common lighting commands.
- Setup instructions included for device ID configuration and first-run authentication.
- Usage details and example commands for lamp control added.
元数据
常见问题
Mijia 是什么？
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. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 2591 次。
如何安装 Mijia？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install mijia」即可一键安装，无需额外配置。
Mijia 是免费的吗？
是的，Mijia 完全免费（开源免费），可自由下载、安装和使用。
Mijia 支持哪些平台？
Mijia 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Mijia？
由 Kai Wang（@hqman）开发并维护，当前版本 v0.1.0。
推荐 Skills