API Catalog logo

API Catalog

Community
tonylofgren
API Catalog

Reference guide for connecting popular APIs to Home Assistant via Node-RED, YAML, or custom integrations. Covers authentication, endpoints, and complete working examples for: energy APIs (Tibber, Nordpool), weather (SMHI, OpenWeatherMap, yr.no), transport (SL, Trafikverket, Resrobot), smart home clouds (Shelly, Tuya, Philips Hue, IKEA), and global APIs (OpenAI, Spotify, Google Calendar, Telegram, GitHub). Use this skill whenever the user mentions a specific external service, API, or data source they want to connect to Home Assistant - even if they don't say "API".

Overview

Publishertonylofgren
Repositoryaurora-smart-home
Skill nameAPI Catalog
Stars
109
Forks
5
Bundled files
5
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.

  • 5 bundled files

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

  • Open source

    Published by tonylofgren on GitHub. Read the source before you install it.

Installation

Install the API Catalog 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/tonylofgren/aurora-smart-home/tree/main/api-catalog
  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/tonylofgren/aurora-smart-home.git /tmp/aurora-smart-home
mkdir -p .claude/skills
cp -r /tmp/aurora-smart-home/api-catalog .claude/skills/tonylofgren-api-catalog
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable API Catalog 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 API Catalog 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 API Catalog 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.

API Catalog for Home Assistant

Reference skill for connecting external APIs and services to Home Assistant.

Overview

This skill covers authentication patterns and working code examples for connecting popular APIs to Home Assistant via three methods:

  • Node-RED - HTTP request node flows (fastest to get running)
  • HA YAML - rest sensor and rest_command (good for simple polling)
  • Custom integration - Full HACS-publishable Python component (use ha-integration skill)

The Iron Law

CREDENTIALS IN SECRETS - NEVER HARDCODED IN FLOWS OR YAML

API keys belong in Node-RED credentials, ESPHome secrets.yaml, or HA secrets.yaml. Never paste real tokens into chat, flows that get exported, or YAML committed to git.

How to Use This Skill

  1. User mentions an API or service by name
  2. Read the relevant reference file for auth setup and endpoints
  3. Generate working code for the user's chosen method (Node-RED / YAML / integration)
  4. Include credential setup instructions

Reference Files

CategoryFileAPIs Covered
Energy & electricityreferences/energy-apis.mdTibber, Nordpool, Energi Data Service
Weatherreferences/weather-apis.mdSMHI, OpenWeatherMap, yr.no, Tomorrow.io
Transportreferences/transport-apis.mdSL, Trafikverket, Resrobot, Entur (NO)
Smart home cloudsreferences/smarthome-apis.mdShelly Cloud, Tuya IoT, Philips Hue, IKEA Dirigera
Global / otherreferences/global-apis.mdOpenAI, Spotify, Google Calendar, Telegram, GitHub

Authentication Patterns at a Glance

PatternHow it worksExamples
API key in headerAuthorization: Bearer {key} or X-API-Key: {key}Tibber, OpenAI
API key in URL?appid={key} appended to URLOpenWeatherMap
OAuth2Get access token first, refresh periodicallySpotify, Google
Local tokenOne-time press-button auth on devicePhilips Hue
No authPublic API, no credentials neededSMHI, yr.no, Nordpool
Basic authUsername + password Base64-encodedSome local devices

Output Methods

For each API, generate code for the method the user needs:

Node-RED: http request node + function node to parse + api-call-service to push to HA HA YAML: rest sensor platform or rest_command under configuration.yaml Full integration: Use ha-integration skill with the polling-integration template

Common Patterns

Node-RED: API key in header

json
{
  "type": "http request",
  "method": "GET",
  "url": "https://api.example.com/data",
  "headers": {"Authorization": "Bearer {{env.API_KEY}}"},
  "ret": "obj"
}

Node-RED: GraphQL (Tibber-style)

json
{
  "type": "http request",
  "method": "POST",
  "url": "https://api.tibber.com/v1-beta/gql",
  "headers": {
    "Authorization": "Bearer {{env.TIBBER_TOKEN}}",
    "Content-Type": "application/json"
  },
  "payload": "{\"query\": \"{ viewer { homes { currentSubscription { priceInfo { current { total } } } } } }\"}",
  "ret": "obj"
}

HA YAML: REST sensor

yaml
rest:
  - scan_interval: 300
    resource: https://api.example.com/current
    headers:
      Authorization: !secret example_api_key
    sensor:
      - name: "Example Value"
        value_template: "{{ value_json.data.value }}"
        unit_of_measurement: "°C"

Pre-Output Checklist

  • Credentials use !secret (YAML), Node-RED credentials, or env vars - never hardcoded
  • Rate limits respected (include scan_interval or flow timer accordingly)
  • Error handling included (Node-RED catch node or YAML timeout)
  • For OAuth2: refresh token flow explained
  • Attribution: which API endpoint, what data it returns

Integration

Pairs with:

  • node-red skill - for flow JSON implementation
  • ha-yaml skill - for YAML sensor and automation using the fetched data
  • ha-integration skill - for building a full HACS-publishable Python integration

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 API Catalog AI skill do?

Reference guide for connecting popular APIs to Home Assistant via Node-RED, YAML, or custom integrations. Covers authentication, endpoints, and complete working examples for: energy APIs (Tibber, Nordpool), weather (SMHI, OpenWeatherMap, yr.no), transport (SL, Trafikverket, Resrobot), smart home clouds (Shelly, Tuya, Philips Hue, IKEA), and global APIs (OpenAI, Spotify, Google Calendar, Telegram, GitHub). Use this skill whenever the user mentions a specific external service, API, or data source they want to connect to Home Assistant - even if they don't say "API".

Why use API Catalog on TypingMind?

Because you install it once and use it with any model. API Catalog 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 API Catalog in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/tonylofgren/aurora-smart-home/tree/main/api-catalog. 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 API Catalog?

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 API Catalog?

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

Is the API Catalog AI skill free?

Yes. It is published on GitHub by tonylofgren 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 👇