Agent skill

Home Assistant Manager

by komal-SkyNET in komal-SkyNET/claude-skill-homeassistant

Edits, validates, deploys and verifies Home Assistant YAML configuration over SSH, hass-cli or MCP, including automations and Lovelace dashboards.

MITAuto-check: warningsProductivity & Automation

Install Home Assistant Manager

The automated check flagged lines worth reading first. See the safety section below.

skills CLI
$ npx skills add komal-SkyNET/claude-skill-homeassistant --skill home-assistant-manager -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install komal-SkyNET/claude-skill-homeassistant home-assistant-manager --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/komal-SkyNET/claude-skill-homeassistant.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/home-assistant-manager .claude/skills/home-assistant-manager && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
home-assistant-manager
GitHub stars
967
Token cost
~1.8k tokens
SKILL.md length
801 words
Files
4
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Edits, validates, deploys and verifies Home Assistant YAML configuration over SSH, hass-cli or MCP, including automations and Lovelace dashboards.

  • Works in 6 steps: Edit YAML locally. → Validate: ssh root@homeassistant.local… → Commit + push: git add … && git commit… → …
  • Editing Home Assistant automations, scripts, scenes or templates
  • SKILL.md covers Assumptions, Remote access — pick the right…, The deploy pipeline (the one… and Reload vs restart, plus 6 more sections
  • Calls ssh, git and scp; needs HASS_TOKEN

What it does

The skill treats the repository as the Home Assistant `/config` directory, connected through git to the instance, and sets out one deploy pipeline: edit YAML locally, validate with `ha core check`, commit and push, pull on the instance, then reload or restart and verify from logs, traces and entity state. For quick loops, such as dashboards, it allows copying files straight over with `scp` and reloading before committing.

It compares access routes: SSH `ha` always works, `hass-cli` needs `HASS_SERVER` and `HASS_TOKEN` set before the session, and an MCP server, either the official integration or the community ha-mcp, is preferred when present. Guidance says when the slow config check can be skipped for an isolated edit and when it must run, namely before a restart or for `configuration.yaml`. The agent edits only YAML and Markdown files and never reads or writes `.env` or `secrets.yaml`, using `!secret` references instead. Reference notes cover automations and dashboards.

When your agent uses it

  • Editing Home Assistant automations, scripts, scenes or templates
  • Deploying configuration changes and deciding between a reload and a restart
  • Building or adjusting a Lovelace dashboard
  • Checking from logs and traces that an automation change actually worked

Example prompts

  • “Add an automation that turns on the hallway light when motion is detected after sunset, then deploy it.”
  • “Validate my configuration and tell me whether I need a restart or just a reload.”
  • “Why didn't the garage door automation fire last night? Check the traces.”

Requirements

  • A Home Assistant instance reachable over SSH, hass-cli or an MCP server
  • The Home Assistant config directory kept in a git repository

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Edit YAML locally.
  2. Validate: ssh root@homeassistant.local "ha core check" (slow, ~30-60s — see "when to
  3. Commit + push: git add … && git commit -m "…" && git push.
  4. Make it live: ssh root@homeassistant.local "cd /config && git pull".
  5. Apply: reload if possible, else restart (table below).
  6. Verify (next section).

What it can do on your machine

Read from SKILL.md and the folder at commit 2112679. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • ssh
    • git
    • scp
    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use ssh, git and scp, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • HASS_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Home Assistant Manager loads about 1.8k tokens when it runs. Until then it costs about 106 tokens; SKILL.md has 801 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~106
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: warnings

The automated check found patterns that need a careful read before installing.

  • WarningMentions a credentials file (SSH keys, cloud or package-manager tokens)SKILL.md:15
    (project CLAUDE.md, `~/.ssh/config`, or ask) and if it isn't recorded in the project
  • NoteMentions a .env fileSKILL.md:18
    `.yaml`/`.yml`/`.md`. Never read/write `.env` or `secrets.yaml`; use `!secret`.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from komal-SkyNET/claude-skill-homeassistant at commit 2112679, republished under its MIT licence (© komal-SkyNET). 801 words, ~1,779 tokens.

Download SKILL.mdSave it as .claude/skills/home-assistant-manager/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
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.
  • root@homeassistant.local 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 root@homeassistant.local "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 root@homeassistant.local "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 root@homeassistant.local:/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

ChangeAction
automations, scripts, scenes, groups, template entities, themesreload 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 root@homeassistant.local "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 root@homeassistant.local "ha core logs | grep -iE '<name>|error' | tail -20". Good: Running automation actions, Executing step …. Bad: Invalid data for call_service, TypeError, Template variable warning, Error executing script.
  4. Confirm the real outcome: device/sensor state (hass-cli state get <entity>), or ask the user for notification-type actions.
  5. On error: fix → re-pull/scp → reload → re-check. Loop until clean.
Show full SKILL.md (271 more words)Show less

Automations — write modern syntax

HA 2024.10 renamed the keys; legacy syntax still works but don't emit it in new code: top-level triggers:/conditions:/actions: (plural), trigger: not platform: inside a trigger, action: not service: for calls. Every automation gets a stable id: (traces and UI editing need it) plus an alias.

Full automation reference (syntax table, mode: behavior, blueprints, trace debugging, pitfalls) → read reference/automations.md when writing or debugging automations.

Templates — the precision rules

  • Always coerce types before comparing: states('sensor.x') | int(0) < 7. Bare states are strings; '5' < 7 raises TypeError. Provide a default (int(0)) so startup None doesn't error.
  • Test in Developer Tools → Template before committing.
  • state_attr(...) returns None if the entity/attr is missing — guard it.

Conventions

  • Surgical edits; preserve comments; 2-space indent.
  • Validate before restart; prefer reload; verify from logs.
  • Use context7 MCP for current HA docs before non-trivial or unfamiliar config.

Dashboards

Lovelace dashboards live in .storage/lovelace.* (JSON). UI edits show on a browser refresh; direct file edits (scp/git) may not appear until a ha core restart — HA caches the lovelace store in memory. Adding a new dashboard to .storage/lovelace_dashboards also needs a restart. scp + refresh is the fast loop; validate JSON first: python3 -m json.tool .storage/lovelace.x > /dev/null. After deploying, validate the UI visually in the browser (see the reference) — logs/state won't catch a broken card or a mis-sorted popup.

Full dashboard reference (view types, card catalog, template cards, tablet layout, pitfalls, debugging) → read reference/dashboards.md when doing UI work. Modern HA: native sections view (drag-drop grid, badges, heading cards) and feature-rich tile cards now cover most needs without custom cards; reach for Mushroom only when you want its specific look.

Quick reference

bash
# Validate / apply
ssh root@homeassistant.local "ha core check"
ssh root@homeassistant.local "ha core restart"
ssh root@homeassistant.local "cd /config && git pull"     # make pushed changes live

# Logs
ssh root@homeassistant.local "ha core logs | grep -iE 'error|<name>' | tail -20"

# State / services (needs env loaded, or use MCP)
hass-cli state get <entity>
hass-cli service call <domain>.reload
hass-cli service call automation.trigger --arguments entity_id=automation.<id>

# Rapid deploy
scp <file>.yaml root@homeassistant.local:/config/ && hass-cli service call automation.reload

© komal-SkyNET, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files in skills/home-assistant-manager of komal-SkyNET/claude-skill-homeassistant.

  • SKILL.md
  • dashboard.png
  • reference/automations.md
  • reference/dashboards.md

Open the folder on GitHubat commit 2112679

Compare with similar skills

Home Assistant Manager next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Home Assistant Manager compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Home Assistant Manager this skillkomal-SkyNET/claude-skill-homeassistant967—~1.8kAutomated safety check: WarnMIT
Pluggedin Stack OpsVeriTeknik/pluggedin-app103—~1.3kAutomated safety check: NotesMIT
Foremergenaw103/foremerge538—~2.4kAutomated safety check: PassApache-2.0
Zed Configwcygan/dotfiles194—~930Automated safety check: PassNone
Edt MCP Ready To DeployDitriXNew/EDT-MCP296—~1.6kAutomated safety check: PassAGPL-3.0
RenderLeoYeAI/openclaw-master-skills2.2k—~4.8kAutomated safety check: PassMIT

Similar skills

  • Pluggedin Stack Ops

    VeriTeknik/pluggedin-app

    A skill your agent uses when deploying, restarting, verifying or rolling back the containerised plugged.in production stack, when the site returns 404 or 5xx after a deploy or git operation, or when…

    103 GitHub stars~1.3k tokensUpdated 4 days ago
    DevOps & CloudAuto-check: notes
  • Foremerge

    naw103/foremerge

    Coordinate parallel coding agents with Foremerge's local Git-compatible CLI and MCP server.

    538 GitHub stars~2.4k tokensUpdated 6 days ago
    Agent WorkflowsAuto-check passed
  • Zed Config

    wcygan/dotfiles

    Zed editor configuration expert. An agent skill from wcygan/dotfiles.

    194 GitHub stars~930 tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Edt MCP Ready To Deploy

    DitriXNew/EDT-MCP

    The final "definition of done" / ready-to-deploy checklist for EDT-MCP — the ordered gate to run when a piece of work is finished, before declaring it done or merging.

    296 GitHub stars~1.6k tokensUpdated 3 days ago
    Testing & QAAuto-check passed
  • Render

    LeoYeAI/openclaw-master-skills

    Deploy and operate apps on Render (Blueprint + one-click Dashboard deeplink, same flow as Codex render-deploy).

    2.2k GitHub stars~4.8k tokensUpdated 2 mo ago
    Productivity & AutomationAuto-check passed
  • N8n CLI

    n8n-io/n8n

    Official

    Use the n8n CLI to manage workflows, credentials, executions, and more on an n8n instance.

    207k GitHub stars~3k tokensUpdated today
    Productivity & AutomationAuto-check passed

Questions about Home Assistant Manager

What does Home Assistant Manager do?

Edits, validates, deploys and verifies Home Assistant YAML configuration over SSH, hass-cli or MCP, including automations and Lovelace dashboards. The skill treats the repository as the Home Assistant `/config` directory, connected through git to the instance, and sets out one deploy pipeline: edit YAML locally, validate with `ha core check`, commit and push, pull on the instance, then reload or restart and verify from logs, traces and entity state. For quick loops, such as dashboards, it allows copying files straight over with `scp` and reloading before committing.

When should I use Home Assistant Manager?

Home Assistant Manager fits situations like: editing Home Assistant automations, scripts, scenes or templates; deploying configuration changes and deciding between a reload and a restart; building or adjusting a Lovelace dashboard; checking from logs and traces that an automation change actually worked.

How do I install Home Assistant Manager in Claude Code?

Run `npx skills add komal-SkyNET/claude-skill-homeassistant --skill home-assistant-manager -a claude-code`. Or copy the skill folder (skills/home-assistant-manager in komal-SkyNET/claude-skill-homeassistant) into .claude/skills/home-assistant-manager in your project. Claude Code loads it when a task matches its description.

How do I install Home Assistant Manager in Codex?

Run `npx skills add komal-SkyNET/claude-skill-homeassistant --skill home-assistant-manager -a codex`. Or copy the skill folder (skills/home-assistant-manager in komal-SkyNET/claude-skill-homeassistant) into .agents/skills/home-assistant-manager in your project. Codex loads it when a task matches its description.

Can I use Home Assistant Manager in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add komal-SkyNET/claude-skill-homeassistant --skill home-assistant-manager -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/home-assistant-manager, .gemini/skills/home-assistant-manager, .github/skills/home-assistant-manager and .opencode/skills/home-assistant-manager in your project.

What does Home Assistant Manager need to run?

Going by SKILL.md and its folder, Home Assistant Manager needs the command-line tools its instructions call (ssh, git, scp and python3) and credentials named HASS_TOKEN. Our summary lists: A Home Assistant instance reachable over SSH, hass-cli or an MCP server; The Home Assistant config directory kept in a git repository.

Does Home Assistant Manager access the network?

SKILL.md contains no URLs. Its commands use ssh and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Home Assistant Manager safe to install?

Our automated static check of SKILL.md flagged 1 warning(s): mentions a credentials file (ssh keys, cloud or package-manager tokens). Read the flagged lines before installing; the check is not a guarantee either way.

What licence does Home Assistant Manager use?

Home Assistant Manager is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Home Assistant Manager use?

About 1.8k tokens (SKILL.md is roughly 7.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Home Assistant Manager?

Skills that share tags, products or a category with Home Assistant Manager: Pluggedin Stack Ops (VeriTeknik/pluggedin-app, 103 stars), Foremerge (naw103/foremerge, 538 stars), Zed Config (wcygan/dotfiles, 194 stars) and Edt MCP Ready To Deploy (DitriXNew/EDT-MCP, 296 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Home Assistant Manager?

komal-SkyNET (a GitHub user) maintains it in komal-SkyNET/claude-skill-homeassistant, which has 967 GitHub stars. The repository was last updated on July 4, 2026.

Source: komal-SkyNET/claude-skill-homeassistant on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.