Token导航 LogoToken导航

Agent Skill · 开发

hivehome(hivehome 控制)

hivehome 用于补充开发相关能力,适合在 OpenClaw 中需要让 Agent 承接开发相关任务时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

hivehome 是开发类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为接触敏感数据;许可证为 MIT-0,第三方扫描已通过,按安装量在开发类的 21,746 个 Skill 里排第 4,371。

总安装 8,412周安装 337GitHub Stars 公开资料未说明下载 2,723核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.1

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:hivehome(hivehome 控制)
来源仓库:https://github.com/m0nkmaster/hivehome
安装命令:
openclaw skills install hivehome
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install hivehome

这个 Skill 是做什么的

开发类 Skill 面向写代码、改代码和排查问题,一般会读写仓库文件,部分还会执行构建或测试命令。

通过非官方 API 控制英国 Hive Home 智能家居设备。适用于家庭自动化温控、灯光与电器管理。hivehome 属于开发类 Skill,可作为该场景下的辅助能力补充。支持查询状态与远程调节,提升生活便利性。使用非官方接口存在服务中断风险,建议备用手动方案。设备控制权变更可能导致保修失效,请谨慎操作。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install hivehome;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

hivehome 怎么安装?

在终端执行 openclaw skills install hivehome。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

hivehome 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

hivehome 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

hivehome 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

hivehome 用的人多吗?

公开数据是累计安装 8,412 次,近一周安装 337 次,下载 2,723 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

hivehome 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理开发类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

开发类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
skill-vetter

技能审查员 · OpenClaw

8,779,018986操作浏览器MIT-0通过
ontology

本体论 · OpenClaw

6,636,960576只读MIT-0通过
entra-app-registration

内部应用程序注册 · Codex、Claude

6,631,872764接触敏感数据未明确通过
entra-app-registration

内部应用程序注册 · Codex、Claude

3,757,680201接触敏感数据未明确通过
nano-banana-pro

纳米香蕉专业版 · OpenClaw

3,526,898364接触敏感数据MIT-0有提醒
hivehome

hivehome 控制 · 本页

8,412—接触敏感数据MIT-0通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
hivehome
description
Control and query Hive Home (UK) smart heating, hot water, lights and devices via the unofficial API. Use when the user mentions Hive, Hive Home, Hive thermostat, smart heating, Hive app, British Gas Hive, or wants to automate or script Hive devices.
license
MIT
compatibility
Requires Python 3, pyhiveapi>=1.0.0, network access. Hive UK account (my.hivehome.com). For non-interactive use set HIVE_DEVICE_* env vars after first login.
homepage
https://github.com/yourusername/agent-skills
metadata

Hive Home (UK)

Control Hive thermostats, hot water, lights and other devices programmatically. Hive does not provide a public API; this skill uses the community Pyhiveapi library, which talks to the same backend as the Hive app.

Prefer the bundled scripts for common actions. Run scripts/hive_control.py from the skill directory (or {baseDir}/scripts/hive_control.py when the agent has the skill path). Only generate custom Pyhiveapi code when the user needs something the scripts do not support (e.g. lights, multi-zone by name, or custom logic).

Important: The API is unofficial. Never hardcode credentials or 2FA codes in prompts, logs or code. Use environment variables or a secure secret store.

Bundled scripts

From the skill root (e.g. hivehome/ or the skill directory loaded by your agent):

# Status (heating + hot water)
python scripts/hive_control.py status

# Heating
python scripts/hive_control.py set-temp 21
python scripts/hive_control.py mode heat
python scripts/hive_control.py mode schedule
python scripts/hive_control.py boost 30 21    # 30 min at 21°C
python scripts/hive_control.py boost-off

# Hot water
python scripts/hive_control.py hotwater-boost 30
python scripts/hive_control.py hotwater-boost-off
python scripts/hive_control.py hotwater-mode schedule
python scripts/hive_control.py hotwater-mode off

# Multiple zones (default zone 0)
python scripts/hive_control.py --zone 1 set-temp 20

Requires HIVE_USERNAME, HIVE_PASSWORD; for non-interactive use (e.g. agent runs) set HIVE_DEVICE_GROUP_KEY, HIVE_DEVICE_KEY, HIVE_DEVICE_PASSWORD after one interactive first-time login.

Credentials

Required env vars: HIVE_USERNAME, HIVE_PASSWORD. For automation (no 2FA each run): HIVE_DEVICE_GROUP_KEY, HIVE_DEVICE_KEY, HIVE_DEVICE_PASSWORD.

Where to set them:

  • Generic / Cursor / CLI: Set in your shell (export HIVE_USERNAME=...) or in a local .env file that is not committed. Run the script in an environment where these are set.
  • OpenClaw: Set in ~/.openclaw/openclaw.json under skills.entries.hivehome.env. OpenClaw injects these into the process for the agent run; they are not put in prompts or logs.
  • Other agents: Use that agent’s recommended way to inject env vars or secrets so the skill’s scripts see them at runtime.

Agent instruction: If credentials are missing, do not ask the user to paste passwords or keys in chat. Tell them to set the required environment variables (or configure the skill in their agent’s config) and run the script again. See references/CREDENTIALS.md for platform-specific notes.

When to use this skill

  • User asks to control Hive heating, thermostat, or hot water.
  • User wants to script or automate Hive devices (heating, lights, plugs).
  • User mentions Hive, British Gas Hive, or the Hive app in the context of automation or code.

Prerequisites

  • Python 3 with pyhiveapi>=1.0.0 (session API): pip install "pyhiveapi>=1.0.0". If you see attribute or method errors, run pip install -U pyhiveapi and try again.
  • Hive account (UK; my.hivehome.com). First-time login requires SMS 2FA; subsequent logins can use device credentials to avoid 2FA.

Authentication

First-time login (username + password + 2FA)

Hive enforces two-factor authentication. After initial login, capture device credentials for future runs so the user does not need to enter a 2FA code every time.

import os
from pyhiveapi import Hive, SMS_REQUIRED

username = os.environ.get("HIVE_USERNAME")
password = os.environ.get("HIVE_PASSWORD")
if not username or not password:
    raise SystemExit("Set HIVE_USERNAME and HIVE_PASSWORD")

session = Hive(username=username, password=password)
login = session.login()

if login.get("ChallengeName") == SMS_REQUIRED:
    code = input("Enter 2FA code from SMS: ")
    session.sms2fa(code, login)

# Save these for next time (e.g. to env or a secure store)
device_data = session.auth.getDeviceData()
print("Store for device login:", device_data)

session.startSession()
# Now use session.heating, session.hotwater, session.light, etc.

Device login (no 2FA after first time)

Use after the user has run first-time login and stored device credentials. Set HIVE_DEVICE_GROUP_KEY, HIVE_DEVICE_KEY, HIVE_DEVICE_PASSWORD (or pass them another secure way).

import os
from pyhiveapi import Hive

session = Hive(
    username=os.environ["HIVE_USERNAME"],
    password=os.environ["HIVE_PASSWORD"],
    deviceGroupKey=os.environ["HIVE_DEVICE_GROUP_KEY"],
    deviceKey=os.environ["HIVE_DEVICE_KEY"],
    devicePassword=os.environ["HIVE_DEVICE_PASSWORD"],
)
session.deviceLogin()
session.startSession()

Device lists

After session.startSession(), devices are in session.deviceList by type:

heating = session.deviceList["climate"]
water_heaters = session.deviceList["water_heater"]
lights = session.deviceList["light"]
switches = session.deviceList["switch"]
sensors = session.deviceList["sensor"]
binary_sensors = session.deviceList["binary_sensor"]

Use the first (or chosen) device when calling the methods below.

Heating (thermostat)

if heating:
    zone = heating[0]
    # Read
    session.heating.getMode(zone)
    session.heating.getState(zone)
    session.heating.getCurrentTemperature(zone)
    session.heating.getTargetTemperature(zone)
    session.heating.getBoostStatus(zone)
    session.heating.getBoostTime(zone)
    session.heating.getOperationModes()  # e.g. SCHEDULE, HEAT, OFF

    # Write
    session.heating.setMode(zone, "SCHEDULE")
    session.heating.setMode(zone, "HEAT")
    session.heating.setTargetTemperature(zone, 21)
    session.heating.setBoostOn(zone, 30, 21)   # 30 min at 21°C
    session.heating.setBoostOff(zone)

Hot water

if water_heaters:
    hw = water_heaters[0]
    session.hotwater.getMode(hw)
    session.hotwater.getState(hw)
    session.hotwater.getBoost(hw)
    session.hotwater.setMode(hw, "OFF")
    session.hotwater.setMode(hw, "SCHEDULE")
    session.hotwater.setBoostOn(hw, 30)
    session.hotwater.setBoostOff(hw)

Lights

if lights:
    light = lights[0]
    session.light.getState(light)
    session.light.getBrightness(light)
    session.light.getColorTemp(light)
    session.light.getColor(light)
    # Set state (exact method names depend on pyhiveapi version; see reference)

Quick reference

  • Modes (heating): SCHEDULE, HEAT, OFF (and others per getOperationModes()).
  • Temperatures: Use integers (e.g. 21 for 21°C). Check session.heating.getMinTemperature(zone) / session.heating.getMaxTemperature(zone) for limits.
  • Boost: Heating boost takes (minutes, target_temp); hot water boost takes (minutes) only.

Additional resources

External endpoints

This skill ships scripts (scripts/hive_control.py) that call the Pyhiveapi Python library. The agent should run these scripts for common actions. When the user needs unsupported behaviour (e.g. lights), the agent may generate Pyhiveapi code. In all cases, only the following endpoints are used. No direct HTTP is made from the skill; Pyhiveapi encapsulates it.

PurposeEndpoint / hostData sent
Login (first time)beekeeper.hivehome.com / api.prod.bgchprod.info (via Pyhiveapi)Hive username, password; after 2FA, device registration
Device loginSameUsername, password, device group key, device key, device password
Device control (heating, hot water, lights, etc.)SameSession token; device IDs and command payloads (e.g. target temperature, mode)

Credentials and 2FA codes must be supplied via environment variables or user input; the skill never contains or logs them. The bundled script includes a SECURITY MANIFEST header (env vars and endpoints used).

Security and privacy

  • What leaves the machine: Hive account credentials (username, password, and optionally device keys) and API requests (device state, setpoints, mode changes) are sent to Hive’s backend (Centrica/British Gas). The skill does not send data elsewhere.
  • What stays local: Credentials should be stored only in the user’s environment or secret store; the skill instructs the agent never to hardcode or log them.
  • Autonomous invocation: When this skill is enabled, the agent may suggest or generate code that calls the Hive API when the user asks about heating, thermostats, or Hive. The user controls whether to run that code and what credentials to provide.

Trust statement

By using this skill, you send your Hive account credentials and device commands to Hive’s servers (beekeeper.hivehome.com / api.prod.bgchprod.info). Only install and use this skill if you trust that infrastructure and the Pyhiveapi library. This skill is not affiliated with Hive or British Gas.

平台分布

OpenClaw

73.61%
按下载量换算2,004

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills