← 返回 Skills 市场
harrey401

Lofy Home

作者 Harreynish Gowtham · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
929
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install lofy-home
功能描述
Smart home control for the Lofy AI assistant — scene modes (study, chill, sleep, morning, grind), device management via Home Assistant REST API, presence-based automation, natural language commands for lights, music, thermostat, and PC wake-on-LAN. Use when controlling smart home devices, activating scene modes, or managing home automation.
使用说明 (SKILL.md)

Home Commander — Environment Control

Controls smart home and computing environment via Home Assistant. Manages scene modes, device control, and presence-based actions.

Data File: data/home-config.json

{
  "scenes": {
    "study": { "lights": { "desk_lamp": { "on": true, "brightness": 100, "color_temp": "cool" } }, "music": { "playlist": "lofi-focus", "volume": 25 }, "other": { "dnd": true } },
    "chill": { "lights": { "desk_lamp": { "on": true, "brightness": 40, "color_temp": "warm" } }, "music": { "playlist": "chill-vibes", "volume": 35 }, "other": {} },
    "sleep": { "lights": {}, "music": { "playlist": "white-noise", "volume": 15 }, "other": {} }
  },
  "devices": {
    "desk_lamp": { "entity_id": "light.desk_lamp", "type": "light" },
    "speaker": { "entity_id": "media_player.room_speaker", "type": "media_player" }
  },
  "home_assistant": { "url": "http://homeassistant.local:8123", "token_env": "HA_TOKEN" }
}

Scene Activation

When user says "study mode", "chill mode", etc.:

  1. Read scene definition from data/home-config.json
  2. Execute each device command via Home Assistant API
  3. Confirm briefly: "Study mode ✓ — desk lamp bright, lo-fi on, DND"

Home Assistant API

# Light control
curl -s -X POST "$HA_URL/api/services/light/turn_on" \
  -H "Authorization: Bearer $HA_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"entity_id": "light.desk_lamp", "brightness_pct": 100}'

# Media playback
curl -s -X POST "$HA_URL/api/services/media_player/play_media" \
  -H "Authorization: Bearer $HA_TOKEN" \
  -d '{"entity_id": "media_player.speaker", "media_content_id": "spotify:playlist:xxx", "media_content_type": "playlist"}'

# Wake-on-LAN
curl -s -X POST "$HA_URL/api/services/wake_on_lan/send_magic_packet" \
  -H "Authorization: Bearer $HA_TOKEN" \
  -d '{"mac": "XX:XX:XX:XX:XX:XX"}'

Quick Commands

  • "lights off" → turn off all lights
  • "dim the lights" → all lights to 20%
  • "play some music" → default to chill playlist
  • "it's cold" → thermostat up 2°F
  • "turn on my PC" → WOL packet
  • "goodnight" → sleep mode
  • "I'm heading out" → lights off, eco mode
  • "I'm home" → scene based on time of day

Instructions

  1. Read data/home-config.json for device mappings and scenes
  2. Confirm actions in ONE short message
  3. If a device fails, report which one and suggest a fix
  4. Never execute "turn off all devices" without confirmation
  5. If Home Assistant is unreachable, report and suggest checking connection
  6. Device entity_ids must be configured by user — prompt if missing
安全使用建议
This skill appears to do what it says (control Home Assistant scenes, lights, media, and WOL), but the instructions expect an HA URL and a bearer token even though the skill metadata does not declare those required credentials. Before installing or using it: (1) verify the skill's origin — there is no homepage or source listed; (2) do not hand over an admin account token. Create a Home Assistant long‑lived access token with the minimum scopes needed (or a dedicated user with limited permissions) and provide only the HA_URL and that least‑privilege token when prompted; (3) confirm and review the data/home-config.json device entity_ids and MAC addresses so the skill cannot act on devices you didn't intend; (4) prefer using this only on a trusted local network or with network rules preventing unwanted external access; (5) if you cannot verify the publisher or you are uncomfortable supplying tokens, do not install—ask the publisher to update the registry metadata to declare required env vars (HA_URL/HA_TOKEN) and to provide a homepage/source for auditability.
功能分析
Type: OpenClaw Skill Name: lofy-home Version: 1.0.0 The skill is designed to control smart home devices via Home Assistant. It uses `curl` to interact with a local Home Assistant instance (`http://homeassistant.local:8123`), authenticating with a token read from the `HA_TOKEN` environment variable. The instructions in `SKILL.md` for the AI agent are clear, aligned with the stated purpose, and even include a safety measure to prevent broad actions without confirmation. There is no evidence of data exfiltration to external endpoints, malicious execution, prompt injection, or other high-risk behaviors.
能力评估
Purpose & Capability
Name and description match the instructions: the SKILL.md describes Home Assistant scene and device control, WOL, and media commands, which align with the skill's home‑automation purpose.
Instruction Scope
The SKILL.md instructs the agent to read a local data file (data/home-config.json) and to make HTTP requests against a Home Assistant instance using environment variables ($HA_URL, $HA_TOKEN). Those runtime actions are within the declared purpose, but the instructions assume access to environment variables and a local config that are not declared in the registry metadata. There is nothing in SKILL.md that demands reading unrelated system files, but the missing declaration means the agent will need to prompt for or access secrets at runtime.
Install Mechanism
This is an instruction‑only skill with no install spec and no code files, so nothing will be written to disk by an installer—this is the lowest install risk.
Credentials
The skill clearly requires a Home Assistant URL and an authorization token (token name referenced as HA_TOKEN in the config example), but the registry lists no required environment variables or primary credential. Requesting an HA token is proportionate to the task, but the omission in metadata is a red flag because the skill will need a secret (Bearer token) to function; users must be aware which secret will be requested and should provide a least‑privilege token. The SKILL.md uses $HA_URL and $HA_TOKEN but does not document what scopes or privileges that token needs.
Persistence & Privilege
The skill does not request always:true and is user‑invocable only; it does not claim to modify other skills or system settings. No elevated persistence or cross‑skill modifications are indicated.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install lofy-home
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /lofy-home 触发
  4. 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
v1.0.0
Initial release
元数据
Slug lofy-home
版本 1.0.0
许可证
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Lofy Home 是什么?

Smart home control for the Lofy AI assistant — scene modes (study, chill, sleep, morning, grind), device management via Home Assistant REST API, presence-based automation, natural language commands for lights, music, thermostat, and PC wake-on-LAN. Use when controlling smart home devices, activating scene modes, or managing home automation. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 929 次。

如何安装 Lofy Home?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install lofy-home」即可一键安装,无需额外配置。

Lofy Home 是免费的吗?

是的,Lofy Home 完全免费(开源免费),可自由下载、安装和使用。

Lofy Home 支持哪些平台?

Lofy Home 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 Lofy Home?

由 Harreynish Gowtham(@harrey401)开发并维护,当前版本 v1.0.0。

💬 留言讨论