A robust technical bridge allowing AI agents to control, inspect, and automate Home Assistant devices through a secure REST API interface.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install home-assistant-control
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 home-assistant-control 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 Control?
Home Assistant Control is a specialized integration designed for developers and power users who want to manage their smart home ecosystem via an AI coding agent. By utilizing the Home Assistant REST API and a long-lived access token, this skill enables seamless interaction with entities, services, scenes, and scripts. It bridges the gap between complex home automation logic and natural language execution, making it a cornerstone for those using Openclaw Skills to build personalized automation workflows.
The skill is built with a focus on reliability and developer experience, featuring scripts for entity discovery, state verification, and safe action execution. Whether you are adjusting lighting, monitoring sensor data, or triggering complex security scenes, this skill provides a structured and secure way to interact with your Home Assistant instance directly from your development environment.
Home Assistant Control Use Cases
- Toggling smart lights, switches, and appliances via command-line or AI prompts.
- Monitoring real-time sensor data and climate states across the home.
- Triggering complex Home Assistant scenes and scripts for automated routines.
- Performing safety-critical actions like locking doors or arming security systems with built-in confirmation checks.
- Inventorying home entities to map natural language aliases to technical entity IDs.
How Home Assistant Control Works
- The AI agent interprets a user request to identify the specific Home Assistant service or entity involved.
- It checks local reference files for naming aliases to ensure the correct entity ID is targeted.
- The skill verifies the current state and existence of the entity before attempting any state changes.
- A secure POST or GET request is dispatched to the Home Assistant REST API using the configured access token.
- The skill analyzes the API response and performs a follow-up state check to confirm the action was successful and report the result to the user.
Home Assistant Control Setup
To get started with this integration in your Openclaw Skills collection, follow these steps:
# Set your Home Assistant credentials
export HA_TOKEN="your_long_lived_access_token"
export HA_URL_PUBLIC="https://your-ha-instance.duckdns.org"
# Optional: Set a local URL for faster network access
export HA_URL_LOCAL="http://192.168.1.100:8123"
# Run the self-check script to verify connectivity
./scripts/self_check.sh
# Generate your entity inventory
./scripts/fill_entities_md.sh
Ensure that bash, curl, and jq are available in your environment.
Home Assistant Control Data Schema & Taxonomy
The skill organizes its operational data and context through the following file structure:
| File Path | Description | Data Type |
|---|---|---|
references/entities.md |
A complete inventory of available Home Assistant entities and their current states. | Markdown Table |
references/naming-context.md |
Custom mappings that link natural language names to technical entity IDs. | Markdown List |
scripts/ha_call.sh |
Core API wrapper for handling HTTP requests and authentication. | Bash Script |
scripts/ha_safe_action.sh |
Logic for executing high-risk services with manual confirmation triggers. | Bash Script |
Home Assistant Control Advanced Features
- Intelligent URL fallback: Prioritizes local network connections while maintaining public access as a reliable backup.
- Risk Mitigation: Built-in safety confirmations for high-impact domains like alarms, locks, and heating systems.
- Entity Discovery: Dynamic generation of entity inventories with domain-specific filtering to keep the agent context clean.
- Alias Memory: Maintains a naming context to help the agent remember that "the desk lamp" refers to a specific technical entity ID.
- Dry-run Support: Allows users to validate service calls without physically triggering the device, essential for testing Openclaw Skills automations.
SKILL.md
Loading
Related Openclaw Skills
confcli
A high-performance CLI tool for interacting with Confluence Cloud spaces, pages, and attachments directly from your terminal.
ThingsBoard
A comprehensive automation tool for managing ThingsBoard IoT platform resources, telemetry data, and dashboard configurations via REST API.
Relationship Coach
An AI-driven relationship coaching agent utilizing Internal Family Systems and Emotionally Focused Therapy to help couples navigate conflict and deepen connection.
X Hot Topics Daily
An automated social intelligence skill that scrapes X for high-value trends in AI, LLM, and global news while filtering out marketing noise.
Intelligent Delegation Framework
A 5-phase framework for reliable AI-to-AI task delegation and coordination inspired by Google DeepMind research.
pubmed2blog
A CLI-driven skill that automates the conversion of complex PubMed research papers into accessible, SEO-optimized healthcare blog content.