# frigate.yaml
mqtt:
  enabled: true
  host: mosquitto
  user: frigate
  password: "{FRIGATE_MQTT_PASSWORD}"

detectors:
  coral:
    type: edgetpu
    device: usb

cameras:
  front_door:
    ffmpeg:
      inputs:
        - path: rtsp://user:pass@192.168.1.100:554/stream1
          roles:
            - detect
            - record
        - path: rtsp://user:pass@192.168.1.100:554/stream2
          roles:
            - rtmp
    detect:
      width: 1920
      height: 1080
      fps: 5
    objects:
      track:
        - person
        - car
        - dog
      filters:
        person:
          min_area: 5000
          threshold: 0.7
    zones:
      porch:
        coordinates: 0,1080,500,1080,500,0,0,0
        objects:
          - person
    record:
      enabled: true
      retain:
        days: 7
        mode: motion
      events:
        retain:
          default: 30

go2rtc:
  streams:
    front_door:
      - rtsp://user:pass@192.168.1.100:554/stream1

# Generic camera
camera:
  - platform: generic
    name: Front Yard
    still_image_url: http://192.168.1.100/snapshot.jpg
    stream_source: rtsp://user:pass@192.168.1.100:554/stream


...(truncated)

</details>

### energy-management

<details>
<summary>View skill definition</summary>

# Energy Management Skill

Home Assistant energy monitoring and optimization patterns.

## Activation Triggers

- Working with energy dashboard
- Solar/battery integration
- EV charger configuration
- Utility rate management
- Power monitoring

## Core Patterns

### Energy Dashboard Configuration

```yaml
# configuration.yaml
energy:

# The Energy dashboard is configured via UI
# Settings > Dashboards > Energy

# Whole home power
sensor:
  - platform: template
    sensors:
      home_power:
        friendly_name: "Home Power"
        unit_of_measurement: "W"
        device_class: power
        value_template: >
          {{ states('sensor.main_meter_power') | float(0) }}          

      home_energy_daily:
        friendly_name: "Daily Energy"
        unit_of_measurement: "kWh"
        device_class: energy
        value_template: >
          {{ states('sensor.main_meter_energy') | float(0) }}          

# Solar production template
template:
  - sensor:
      - name: "Solar Power"
        unit_of_measurement: "W"
        device_class: power
        state_class: measurement
        state: "{{ states('sensor.inverter_power') | float(0) }}"

      - name: "Solar Energy Today"
        unit_of_measurement: "kWh"
        device_class: energy
        state_class: total_increasing
        state: "{{ states('sensor.inverter_energy_today') | float(0) }}"

      - name: "Solar Self Consumption"
        unit_of_measurement: "kWh"
  

...(truncated)

</details>

### ha-automation

> "What this automation does and why"

<details>
<summary>View skill definition</summary>

# Home Assistant Automation Skill

Automation YAML patterns, triggers, conditions, actions, and best practices for Home Assistant.

## Activation Triggers

Activate this skill when:
- Creating or modifying automations
- Working with automation YAML
- Designing trigger logic
- Building condition chains
- Creating action sequences

## Automation Structure

```yaml
# Complete automation template
alias: "Descriptive Name"
id: unique_automation_id  # Optional but recommended
description: "What this automation does and why"
mode: single  # single, restart, queued, parallel

# Variables available throughout
variables:
  room: "living_room"
  default_brightness: 80

trigger:
  - platform: state
    entity_id: binary_sensor.motion
    to: "on"
    id: motion_detected  # For use in choose

condition:
  - condition: sun
    after: sunset

action:
  - service: light.turn_on
    target:
      entity_id: "light.{{ room }}"
    data:
      brightness_pct: "{{ default_brightness }}"

trigger:
  - platform: state
    entity_id: binary_sensor.door
    from: "off"
    to: "on"
    for:
      seconds: 30
    attribute: any  # Optional: trigger on attribute change

trigger:
  - platform: time
    at: "06:30:00"

  # Multiple times
  - platform: time
    at:
      - "07:00:00"
      - "12:00:00"
      - "18:00:00"

  # Input datetime
  - platform: time
    at: input_datetime.wake_up_time

trig

...(truncated)

</details>

### ha-core

<details>
<summary>View skill definition</summary>

# Home Assistant Core Skill

Core Home Assistant API integration patterns, authentication, and entity management.

## Activation Triggers

Activate this skill when working with:
- Home Assistant REST API
- WebSocket API connections
- Entity state management
- Service calls
- Event bus subscriptions

## Authentication

### Long-Lived Access Token

```python
import httpx

class HAClient:
    def __init__(self, url: str, token: str):
        self.url = url.rstrip('/')
        self.headers = {
            "Authorization": f"Bearer {token}",
            "Content-Type": "application/json"
        }

    async def get_states(self) -> list:
        async with httpx.AsyncClient() as client:
            response = await client.get(
                f"{self.url}/api/states",
                headers=self.headers
            )
            response.raise_for_status()
            return response.json()

    async def get_state(self, entity_id: str) -> dict:
        async with httpx.AsyncClient() as client:
            response = await client.get(
                f"{self.url}/api/states/{entity_id}",
                headers=self.headers
            )
            response.raise_for_status()
            return response.json()

    async def call_service(
        self,
        domain: str,
        service: str,
        data: dict = None,
        target: dict = None
    ) -> dict:
        payload = {}
        if data:
            payload.update(data)
        if target:
            payload["target

...(truncated)

</details>

### local-llm

<details>
<summary>View skill definition</summary>

# Local LLM Integration Skill

Deploy and integrate local LLMs with Ollama, LocalAI, and Home Assistant for privacy-focused voice assistants and automation.

## Activation Triggers

Activate this skill when:
- Setting up Ollama or LocalAI
- Configuring local voice assistants
- Integrating LLMs with Home Assistant
- Optimizing local model performance
- Building LLM-powered automations

## Ollama Installation

### Ubuntu/Debian
```bash
# Install Ollama
curl -fsSL https://ollama.com/install.sh | sh

# Start as service
sudo systemctl enable ollama
sudo systemctl start ollama

# Pull models
ollama pull llama3.2:3b
ollama pull fixt/home-3b-v3  # HA-optimized

# docker-compose.yaml
services:
  ollama:
    image: ollama/ollama:latest
    container_name: ollama
    restart: unless-stopped
    ports:
      - "11434:11434"
    volumes:
      - ./ollama:/root/.ollama
    # GPU support (NVIDIA)
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]

import httpx

async def generate(prompt: str, model: str = "llama3.2:3b") -> str:
    async with httpx.AsyncClient() as client:
        response = await client.post(
            "http://localhost:11434/api/generate",
            json={
                "model": model,
                "prompt": prompt,
                "stream": False,
                "options": {
      

...(truncated)

</details>

## Source

[View on GitHub](https://github.com/Lobbi-Docs/claude)