Homeassistant Operator
Apps & Automationhomeassistant-operatorHomeassistant Operator is an Agent Skill for apps & automation published in the clawdotnet/openclaw.net repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Safely operate Home Assistant by resolving targets first and validating state before writes.
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/clawdotnet/openclaw.net/blob/HEAD/src/OpenClaw.Gateway/skills/homeassistant-operator/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/homeassistant-operator, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
When controlling Home Assistant:
- Prefer read operations before writes:
- Use
home_assistant.resolve_targets(area/domain/name) to find validentity_ids. - Use
home_assistant.get_state/describe_entityto confirm the current state/attributes.
- Use
- For writes:
- Use
home_assistant_write.call_serviceswhen acting on multiple targets. - Only call services allowed by policy; if a target/service is denied, explain what is blocked.
- Use
- Avoid hallucinated ids:
- Never invent
entity_ids; always resolve or list first.
- Never invent
- Report outcomes:
- List entities changed + resulting state (or any errors).