Token导航 LogoToken导航TokenDH.com
开发敏感数据clawhub未标认证来源可访问clear审计通过

hivehomehivehome 控制

Agent Skill

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。

总安装

8,412

周安装

337

GitHub Stars

公开资料未说明

下载量

2,723
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

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

简介

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。

SKILL.md

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.

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

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

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。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills