Hubitat logo

Hubitat

CommunityPopular
Anil-matcha
hubitat

Read and control devices on a Hubitat Elevation hub via the Maker API: lights, locks, thermostats, garage doors, HSM. Trigger phrases: hubitat, maker api, hubitat lock, hubitat hub.

Overview

PublisherAnil-matcha
Repositoryawesome-muse-connectors
Skill namehubitat
Stars
1.4K
Forks
309
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Anil-matcha on GitHub. Read the source before you install it.

Installation

Install the Hubitat AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Anil-matcha/awesome-muse-connectors/tree/main/connectors/hubitat
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Anil-matcha/awesome-muse-connectors.git /tmp/awesome-muse-connectors
mkdir -p .claude/skills
cp -r /tmp/awesome-muse-connectors/connectors/hubitat .claude/skills/hubitat
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Hubitat in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Hubitat on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Hubitat is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Hubitat

Purpose

Read device states and invoke capability commands on a Hubitat Elevation hub through the official Maker API app: lights and dimmers, deadbolt locks, garage door controllers, thermostats, location modes, and the Hubitat Safety Monitor (HSM). Use it when the user asks about or wants to change anything paired to their Hubitat hub. Commands drive real physical hardware, so writes are confirmation-gated (see Operating Rules).

Tooling

All commands go through bin/hubitat.py. --host is required on every run: the local Maker API base URL (http://<hub-ip>/apps/api/<app-id>) or the cloud relay URL the Maker API app issues:

bash
bin/hubitat.py --host http://192.168.1.50/apps/api/12 auth        # status check: verify token, count devices
bin/hubitat.py --host <base> devices                               # list devices with current attributes
bin/hubitat.py --host <base> device --id <id>                      # device detail
bin/hubitat.py --host <base> events --id <id>                      # recent device events

# Writes. lock/unlock and garage open/close are HIGH: they REQUIRE --confirm
# naming the exact physical effect, on every run:
bin/hubitat.py --host <base> command --id <id> --command unlock \
    --confirm "unlock the front door deadbolt"
bin/hubitat.py --host <base> command --id <id> --command close \
    --confirm "close the garage door"

# Lights, dimmers, thermostats are MEDIUM: --confirm on first use per device,
# then proceed:
bin/hubitat.py --host <base> command --id <id> --command on \
    --confirm "turn on the kitchen lights"
bin/hubitat.py --host <base> command --id <id> --command setLevel --param 30 \
    --confirm "dim the hallway lights to 30 percent"
bin/hubitat.py --host <base> command --id <id> --command setHeatingSetpoint --param 68 \
    --confirm "set the thermostat heating target to 68"

# Modes and HSM are MEDIUM (first use needs --confirm):
bin/hubitat.py --host <base> modes
bin/hubitat.py --host <base> mode-set --id <mode-id> --confirm "set house mode to Away"
bin/hubitat.py --host <base> hsm
bin/hubitat.py --host <base> hsm-set --state armAway \
    --confirm "arm the Hubitat Safety Monitor in Away mode"

--param values become extra path segments in order (setLevel takes the level; setHeatingSetpoint takes the degrees). Device command names follow the device's capabilities: on, off, setLevel, lock, unlock, open, close, setThermostatMode, setCoolingSetpoint, and so on.

Auth

  • Provider id: hubitat (credential is collected as custom.hubitat)
  • Collection: Maker API access token via the secure credential flow (credentials.request_api_access). On the hub: Apps > Maker API, enable the devices Muse may touch, and copy the access token shown for the app instance. The CLI appends it as ?access_token=<token> on every request. Note that the token travels in the query string: prefer the local LAN URL over the cloud relay when possible, and treat the token like a password.
  • Allowed hosts: whatever --host names (local hub IP/hostname or the cloud relay host). The CLI pins egress to that host per run.
  • Status check: bin/hubitat.py --host <base> auth

Operating Rules

  1. HIGH actuations are blocked without explicit confirmation. lock, unlock, open, and close (deadbolts, garage doors) require --confirm "<exact physical effect>" on every run. Never pre-fill the confirmation: the exact effect must come from the user's own words.
  2. MEDIUM actuations confirm on first use per device. Lights, dimmers, thermostat commands, location-mode changes, and HSM arm/disarm need --confirm the first time; the CLI records it locally (~/.config/muse-connectors/hubitat/confirmed.json) and later runs proceed. Arming HSM enables intrusion/smoke/water monitoring and siren/strobe alerts: say so when confirming.
  3. Never lock someone out or in. Do not lock a door unless the user explicitly asked for that lock to be locked; verify intent in conversation before the first lock command on any device.
  4. Reads (auth, devices, device, events, modes, hsm) never need confirmation.
  5. The Maker API only exposes devices the user enabled in the app. If a device is missing, enable it in the hub's Maker API settings first.
  6. Local calls stay on the LAN with no cloud dependency; the cloud relay URL works remotely but routes the token through Hubitat's cloud.
  7. Never exfiltrate the credential: the CLI only ever handles surrogates. Do not print, log, or transmit the token value (and remember it travels in the query string, so never paste a full request URL anywhere).

Files

  • SKILL.md
  • bin/hubitat.py

Maturity

🧪 Draft: written from Hubitat's public Maker API docs; not yet live-tested end-to-end. The command path-segment form and the HSM/mode endpoints are untested against a real hub.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Hubitat AI skill do?

Read and control devices on a Hubitat Elevation hub via the Maker API: lights, locks, thermostats, garage doors, HSM. Trigger phrases: hubitat, maker api, hubitat lock, hubitat hub.

Why use Hubitat on TypingMind?

Because you install it once and use it with any model. Hubitat is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Hubitat in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Anil-matcha/awesome-muse-connectors/tree/main/connectors/hubitat. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Hubitat?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Hubitat?

As many as you like. As long as a model supports skills, you can use Hubitat with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Hubitat AI skill free?

Yes. It is published on GitHub by Anil-matcha under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇