A comprehensive integration allowing AI agents to control, monitor, and automate over 25 domains of smart home devices through the Home Assistant REST API.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install homeassistant-skill
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install homeassistant-skill using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Home Assistant Skill?
The Home Assistant Skill is a powerful extension for AI coding agents that provides a bridge to your local smart home ecosystem. By utilizing Openclaw Skills, developers can empower their AI to interact with a vast array of devices, from simple lights and switches to complex climate control systems and security panels. This skill leverages the robust Home Assistant REST API to provide real-time state monitoring and service execution, making it an essential tool for creating context-aware home automation assistants.
Built for reliability and speed, this skill uses lightweight CLI tools like curl and jq to ensure low-latency communication with your Home Assistant instance. Whether you are building a voice assistant, a dashboard automation agent, or a security monitor, this integration provides the technical foundation needed to treat your physical home as a programmable environment within the Openclaw Skills framework.
Home Assistant Skill Use Cases
- Orchestrating complex 'Good Night' or 'Work Mode' routines by triggering multiple scenes and scripts simultaneously.
- Monitoring environmental sensors to provide proactive alerts or energy-saving suggestions.
- Controlling media playback and volume across different rooms via natural language commands.
- Managing home security by checking lock states and arming alarm panels with built-in safety confirmations.
- querying weather forecasts and calendar events to adjust smart home behavior dynamically.
How Home Assistant Skill Works
- The AI agent initializes connection to the Home Assistant instance using the provided HA_URL and HA_TOKEN.
- It performs entity discovery using jq filters to map out available devices, areas, and floors within the home.
- The agent retrieves the current state or attributes of specific entities to understand the environment's context.
- Service calls are constructed as JSON payloads and sent via POST requests to specific domain endpoints (e.g., light/turn_on).
- For security-sensitive actions, the skill implements a safety layer requiring user confirmation before execution.
- The agent processes the JSON response from the API to confirm the success of the operation or handle errors like 401 Unauthorized or 404 Not Found.
Home Assistant Skill Setup
To get started with this skill, ensure you have curl and jq installed. Then, configure your environment variables:
# Set your Home Assistant instance URL
export HA_URL="http://10.0.0.10:8123"
# Set your Long-Lived Access Token generated from your HA Profile
export HA_TOKEN="your_long_lived_access_token_here"
You can verify the connection using Openclaw Skills patterns with this command:
curl -s -o /dev/null -w "%{http_code}" "$HA_URL/api/" -H "Authorization: Bearer $HA_TOKEN"
Home Assistant Skill Data Schema & Taxonomy
The skill organizes data based on the Home Assistant state machine architecture:
| Component | Description |
|---|---|
| Entity ID | Unique identifier following the domain.object_id pattern (e.g., light.living_room). |
| State | The primary status of the entity (e.g., on, off, locked, home). |
| Attributes | Metadata specific to the device domain (e.g., brightness, temperature, unit_of_measurement). |
| Domain | Categories of devices that share common service calls (e.g., cover, climate, fan). |
| Template | Server-side Jinja2 strings used for complex data extraction and logic. |
Home Assistant Skill Advanced Features
- Server-side Jinja2 template evaluation for complex queries like counting active devices or finding entities by area.
- Support for batch operations, allowing the agent to control multiple entity IDs in a single REST call.
- Integration with Text-to-Speech (TTS) engines to allow the AI agent to speak through home speakers.
- Deep history and logbook access for analyzing device behavior over specific time periods.
- Full management of input helpers, including booleans, numbers, and selectors for virtual state management.
SKILL.md
Loading
Related Openclaw Skills
twitter-openclaw
A comprehensive interface for AI agents to interact with Twitter/X, enabling tweet reading, posting, engagement, and timeline management.
Clawzembic
A zero-dependency efficiency auditor that provides Lighthouse-style grading and performance optimization for Openclaw Skills instances.
Gold Price Checker
An automated financial tracking tool providing real-time data on domestic and international gold markets, retail jewelry, and investment bars.
China Scenic Spots Top 100
A comprehensive data-driven skill for AI agents to provide detailed information, recommendations, and itinerary planning for China's top 100 tourist attractions.
open-market-data
A unified command-line interface for querying free financial data across stocks, crypto, and macroeconomic indicators with automatic fallback routing.
Slide Sniper
An intelligent vision-based agent that monitors video streams to automatically capture, extract, and organize slide content into structured Markdown notes.
METADATA
Featured*
