A powerful CLI-based skill to manage Home Assistant entities, services, and automations with a built-in multi-level safety system.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install moltbot-ha
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 moltbot-ha 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 (moltbot-ha)?
moltbot-ha is a specialized skill designed to bridge the gap between AI agents and smart home environments. By leveraging the Home Assistant API, this Openclaw Skills integration allows developers and power users to control lights, switches, covers, and complex services directly from a command-line interface. It provides a structured way for AI agents to interact with physical hardware while maintaining strict security protocols.
The skill is built with a focus on reliability and safety, ensuring that critical operations like unlocking doors or opening garage doors require explicit confirmation. Whether you are building automated morning routines or monitoring sensor data, this tool provides the necessary hooks to turn your Home Assistant instance into a fully programmable environment.
Home Assistant Control (moltbot-ha) Use Cases
- Automating daily routines like morning lighting and climate control.
- Monitoring real-time sensor data such as temperature, humidity, and motion.
- Executing complex Home Assistant service calls and scripts through an AI agent.
- Managing security-sensitive devices with a multi-level safety confirmation workflow.
- Batch controlling devices by domain (lights, switches, etc.) for efficient smart home management.
How Home Assistant Control (moltbot-ha) Works
- The user or agent initiates a command via the moltbot-ha CLI to interact with a specific entity.
- The skill validates the command against the local TOML configuration and safety levels.
- If the action is classified as critical (e.g., locks or covers), the system prompts for user confirmation before proceeding.
- Upon validation or confirmation, the skill sends a request to the Home Assistant API using a Long-Lived Access Token.
- The action is executed on the physical device, and the resulting state or error is returned and logged.
Home Assistant Control (moltbot-ha) Setup
Install the tool using uv and initialize the configuration:
uv tool install moltbot-ha
moltbot-ha config init
Next, set your Home Assistant Long-Lived Access Token as an environment variable:
export HA_TOKEN="your_token_here"
Finally, verify the connection to your Home Assistant instance:
moltbot-ha test
Home Assistant Control (moltbot-ha) Data Schema & Taxonomy
The skill uses a local configuration directory at ~/.config/moltbot-ha/ to store settings and logs.
| File | Purpose |
|---|---|
config.toml |
Main configuration file for API URL, safety levels, and entity filters. |
actions.log |
A detailed log of all write operations performed by the skill. |
Configuration Keys
- server.url: Your Home Assistant instance URL.
- safety.level: Numeric level (0-3) determining the strictness of command execution.
- safety.critical_domains: List of domains requiring confirmation flags.
- safety.blocked_entities: Entities permanently excluded from CLI control.
Home Assistant Control (moltbot-ha) Advanced Features
- Multi-level safety system (Level 3 by default) to prevent accidental execution of critical smart home actions.
- Support for custom service calls with raw JSON data for complex Home Assistant integrations.
- Entity filtering via allowed and blocked lists using wildcards for fine-grained access control.
- Agent-optimized error messages that guide Openclaw Skills through the confirmation process for high-risk commands.
- Built-in logging for all state-changing actions to maintain a transparent audit trail of home automations.
SKILL.md
Loading
Related Openclaw Skills
Carapace Runtime Security
A runtime security shell that hardens AI agents against prompt injection, data exfiltration, and unauthorized operations.
Eridian Carapace
A comprehensive security hardening layer that protects OpenClaw agents from prompt injection, data exfiltration, and unauthorized operations at runtime.
PostNitro Carousel Generator
Automate the creation of professional social media carousel posts from text, articles, or social media threads using AI.
Sarvam AI
A comprehensive toolkit for Indian language processing including speech-to-text, text-to-speech, translation, and chat capabilities.
ImaginePro AI Image Generation
A powerful AI image generation skill integrating Midjourney, Flux, and video creation via a streamlined API wrapper.
Memori Extension
A memory augmentation and LLM interception tool that provides agents with persistent knowledge retrieval and injection capabilities.
Featured*
