home-assistant-manager

Este extracto es una copia guardada durante la revisión. La fuente externa contiene la versión completa y actual.

---
name: home-assistant-manager
description: Manage Home Assistant configuration safely and fast — edit and deploy YAML (automations, blueprints, scripts, scenes, templates, MQTT), validate with ha core check, deploy via git or rapid scp, reload-vs-restart correctly, verify changes from logs, traces and entity state, and build Lovelace dashboards. Use for any Home Assistant config, automation, template, or dashboard work over SSH/hass-cli/MCP.
---

# Home Assistant Manager

Operate a remote Home Assistant instance precisely: make a change, get it live, prove it
worked. Optimize for the fewest safe round-trips.

## Assumptions
- The repo you're editing **is** the HA `/config` dir, git-connected to the instance.
  Edits aren't live until pulled on the instance.
- `[email protected]` in examples is a placeholder. Resolve the real user/host once
  (project CLAUDE.md, `~/.ssh/config`, or ask) and if it isn't recorded in the project
  CLAUDE.md yet, add it so future sessions skip this step.
- Access via one or more of: `hass-cli` (REST), SSH `ha`, or an MCP server (see below).
- Only edit `.yaml`/`.yml`/`.md`. Never read/write `.env` or `secrets.yaml`; use `!secret`.

## Remote access — pick the right tool
- **SSH `ha`** — always works, needs no local env. Use for `ha core check|restart|logs|info`.
- **`hass-cli`** (REST) — state/service calls, but needs `HASS_SERVER`/`HASS_TOKEN` in the
  shell *before* the session starts. If they're unset, hass-cli falls back to the wrong
  host (localhost) and errors — don't retry, check `[ -n "$HASS_TOKEN" ]` once, then use
  SSH or MCP instead.
- **MCP** (preferred when available) — first-class tools for live state/control, no env
  juggling. Official `mcp_server` integration (HA core ≥2025.2) or community `ha-mcp`
  (richer, 80+ tools). Use it instead of shelling out when present.

## The deploy pipeline (the one canonical flow)
Changes are not live until step 4.
1. Edit YAML locally.
2. Validate: `ssh [email protected] "ha core check"` (slow, ~30-60s — see "when to
   skip" below).
3. Commit + push: `git add … && git commit -m "…" && git push`.
4. **Make it live:** `ssh [email protected] "cd /config && git pull"`.
5. Apply: **reload** if possible, else **restart** (table below).
6. Verify (next section).

**Rapid iteration:** skip git and `scp` straight to the instance, then reload — good for
dashboards and tight test loops. Commit to git only once stable.
`scp automations.yaml [email protected]:/config/` → reload.

**When to skip `ha core check`:** it parses the whole config and is slow. For an isolated
YAML edit you're confident in, a domain reload surfaces errors faster and the logs tell
you immediately. Always run it before a *restart* or for `configuration.yaml` changes.

## Reload vs restart
| Change | Action |
|--------|--------|
| automations, scripts, scenes, groups, template entities, themes | **reload** the domain (`hass-cli service call automation.reload`, etc.) |
| `configuration.yaml` core, new integrations, platform sensors (min/max), MQTT sensor/binary_sensor platforms, dashboard registry (`lovelace_dashboards`) | **restart** (`ssh … "ha core restart"`, ~30s) |

Prefer reload. Never restart without a passing `ha core check`. Before risky changes
(core `configuration.yaml` surgery, removing an integration), snapshot first — it's cheap:
`ssh [email protected] "ha backups new --name pre-<change>"`.

## Verify — don't assume it worked
1. Reload/restart the right domain.
2. For automations, **trigger manually** for instant feedback:
   `hass-cli service call automation.trigger --arguments entity_id=automation.<id>`
   (or call the service via MCP). This **bypasses `conditions` by default** — it proves the
   actions, not the gate. To test conditions too, pass `skip_condition: false` or exercise
   the real trigger, then read the automation's trace in the UI.
3. Read the logs filtered to your change:
   `ssh [email protected] "ha core logs