agentleFS
Sign inStart free
MesteriisMesteriis/Engineering-Bible-AI/skills/homeassistant/SKILL.md

homeassistant

Skill0 starsChanged 4 months agoMITView on GitHub

Applies safe Home Assistant rules for automations, templates, integrations, entity behavior, startup states, and validation.

We split this skill into the rules it gives an agent

16 rules. About 0 are common, 14 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈14

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not create automations that can cause unsafe physical behavior.

    line 14
  2. Distinctive:

    Use failsafe defaults where appropriate.

    line 31
  3. Distinctive:

    Before changing Home Assistant config, inspect relevant files when present:

    line 35
  4. Distinctive:

    Do not invent entity IDs.

    line 48
  5. Distinctive:

    Do not hardcode secrets.

    line 50
  6. Distinctive:

    Avoid loops caused by state changes.

    line 54
  7. Distinctive:

    Avoid hidden time assumptions.

    line 58
  8. Very specific:

    Consider mode: single, restart, queued, parallel.

    line 60
  9. Distinctive:

    Document non-obvious triggers and safety conditions.

    line 61
  10. Distinctive:

    Avoid automations that depend on fragile friendly names.

    line 62
  11. Distinctive:

    Avoid exceptions from unavailable attributes.

    line 67
  12. Distinctive:

    Avoid complex business logic hidden in templates when a helper/script is clearer.

    line 70
  13. Distinctive:

    Avoid duplicate entity IDs.

    line 75
  14. Very specific:

    Keep related automations/scripts/packages cohesive.

    line 77
  15. Distinctive:

    Prefer actual validation when available:

    line 81
  16. Distinctive:

    If validation cannot be run, explain why.

    line 91

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Skill: homeassistant

Purpose

Apply safe, explicit, maintainable rules to Home Assistant automations, scripts, templates, integrations, and configuration.

Safety First

Do not create automations that can cause unsafe physical behavior.

Be careful with:

  • heaters;
  • boilers;
  • locks;
  • gates;
  • relays;
  • pumps;
  • power circuits;
  • battery charging;
  • high-current loads;
  • water valves;
  • garage doors;
  • alarms.

Use failsafe defaults where appropriate.

Inspect First

Before changing Home Assistant config, inspect relevant files when present:

  • configuration.yaml
  • automations.yaml
  • scripts.yaml
  • secrets.yaml references only, not values
  • packages
  • blueprints
  • template sensors
  • existing entity IDs
  • helpers/input entities
  • dashboard files if relevant

Do not invent entity IDs.

Do not hardcode secrets.

Automation Rules

  • Avoid loops caused by state changes.
  • Debounce noisy sensors.
  • Handle unknown and unavailable.
  • Use explicit conditions.
  • Avoid hidden time assumptions.
  • Consider restart behavior.
  • Consider mode: single, restart, queued, parallel.
  • Document non-obvious triggers and safety conditions.
  • Avoid automations that depend on fragile friendly names.

Templates

  • Handle missing/unavailable states.
  • Avoid exceptions from unavailable attributes.
  • Prefer explicit defaults.
  • Keep templates readable.
  • Avoid complex business logic hidden in templates when a helper/script is clearer.

Entity and Naming

  • Preserve existing entity IDs.
  • Avoid duplicate entity IDs.
  • Use domain-meaningful names.
  • Keep related automations/scripts/packages cohesive.

Validation

Prefer actual validation when available:

ha core check

Or project-specific container/supervisor validation commands.

Report exact commands and results.

If validation cannot be run, explain why.

Shared Cross-Ecosystem Style

Apply the shared engineering style from:

  • ../../engineering/05_design_principles.md
  • ../../engineering/06_responsibility_model.md
  • ../../engineering/07_complexity_budget.md
  • ../../engineering/12_naming_bible.md

Language-specific idioms control syntax and ecosystem details, but they must not weaken the core rules: small cohesive units, explicit boundaries, honest validation, no dumping grounds, and no fake placeholders.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free