Home Assistant Manager
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.
Turns a home-automation request into standard, testable automations.yaml, run against Home Assistant Core's real triggers and verified with its own trace tool.
Install Home Assistant Automation Builder
$ npx skills add autonomous-ai/openharness --skill home-assistant -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install autonomous-ai/openharness home-assistant --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/store/agents/home-assistant/skills/home-assistant .claude/skills/home-assistant && rm -rf skills-srcUse ~/.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/
Install the "home-assistant" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/home-assistant/skills/home-assistant into .claude/skills/home-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "home-assistant", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/autonomous-ai/openharness/tree/main/store/agents/home-assistant/skills/home-assistantType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add autonomous-ai/openharness --skill home-assistant -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install autonomous-ai/openharness home-assistant --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .agents/skills && cp -r skills-src/store/agents/home-assistant/skills/home-assistant .agents/skills/home-assistant && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "home-assistant" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/home-assistant/skills/home-assistant into .agents/skills/home-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "home-assistant", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add autonomous-ai/openharness --skill home-assistant -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install autonomous-ai/openharness home-assistant --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/store/agents/home-assistant/skills/home-assistant .cursor/skills/home-assistant && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "home-assistant" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/home-assistant/skills/home-assistant into .cursor/skills/home-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "home-assistant", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/autonomous-ai/openharness.git --path store/agents/home-assistant/skills/home-assistant--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add autonomous-ai/openharness --skill home-assistant -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install autonomous-ai/openharness home-assistant --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/store/agents/home-assistant/skills/home-assistant .gemini/skills/home-assistant && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "home-assistant" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/home-assistant/skills/home-assistant into .gemini/skills/home-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "home-assistant", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install autonomous-ai/openharness home-assistantInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add autonomous-ai/openharness --skill home-assistant -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .github/skills && cp -r skills-src/store/agents/home-assistant/skills/home-assistant .github/skills/home-assistant && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "home-assistant" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/home-assistant/skills/home-assistant into .github/skills/home-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "home-assistant", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add autonomous-ai/openharness --skill home-assistant -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install autonomous-ai/openharness home-assistant --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/store/agents/home-assistant/skills/home-assistant .opencode/skills/home-assistant && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "home-assistant" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/home-assistant/skills/home-assistant into .opencode/skills/home-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "home-assistant", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
home-assistant- GitHub stars
- 1.2k
- Token cost
- ~1.2k tokens
- SKILL.md length
- 614 words
- Files
- 9 (incl. scripts, references)
- Skills in repo
- 100
- Repo updated
- First seen
- Licence
- MIT
At a glance
Turns a home-automation request into standard, testable automations.yaml, run against Home Assistant Core's real triggers and verified with its own trace tool.
- Turning a plain-language automation request into standard Home Assistant YAML
- SKILL.md covers Build, inspect and deliver and Scope and installation boundary
- Runs JavaScript and Shell scripts from its folder; calls bash and node
- Writing test assertions for an automation's normal and non-firing cases
What it does
Produces a standard `automations.yaml` file, a testable brief with a fixture inventory recorded in `project.json`, and a portable installation kit as the actual deliverables, not a diagram or a preview-only dashboard, since Habitat's own interface must be served by its tools rather than opened as a static file. When the user has no real devices, it uses explicitly labeled example entities instead, and if the user supplies existing YAML it is kept and preserved rather than replaced outright, with consequential choices like manual overrides and timeout behavior clarified only when they actually matter.
A dedicated scenarios reference governs the test model, built from Home Assistant Core's actual triggers, conditions, templates and actions rather than a simplified, homegrown stand-in, with a bundled hallway example serving only as an editable starting point rather than defining the system's limits. Test assertions are designed from the brief before the implementation is touched, covering normal operation and the non-firing cases where guards matter, such as interruption, debounce, a missing sensor, or a manual takeover, and checking the exact call sequence, target, timing and final state rather than just whether something ran.
A single build script runs the actual Core test suite, keeps a checked copy of the delivered automation under an output folder, and separately exercises the studio's draft round trip, native trace, ZIP download and desktop and mobile layout inside a real Chromium browser, recording its evidence to dedicated harness log files. A faster CLI-only build script exists for iterating, but it deliberately leaves browser readiness unverified.
When your agent uses it
- Turning a plain-language automation request into standard Home Assistant YAML
- Writing test assertions for an automation's normal and non-firing cases
- Verifying a built automation with Home Assistant Core's native trace tool
- Delivering a portable installation kit for a Home Assistant automation
Example prompts
- “Build an automation that turns on the porch light at sunset, with a test for the no-sensor case.”
- “Here's my existing automations.yaml — add a new motion-triggered scene without touching the rest.”
- “Run the full build and check the native trace for this automation.”
Requirements
- Home Assistant Core
- Node.js
- Chromium, for the browser verification step
What it can do on your machine
Read from SKILL.md and the folder at commit cc4983e. 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
Ships 7 files in scripts/ (JavaScript and Shell), which the agent can run.
Shell commands in SKILL.md call:
bashnode
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Home Assistant Automation Builder loads about 1.2k tokens when it runs, and up to ~2.5k if it reads all its reference files. Until then it costs about 62 tokens; SKILL.md has 614 words of instructions outside code blocks.
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 passed
The automated check found no risky patterns in SKILL.md.
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); the scripts in this folder are not scanned.
SKILL.md
The full file from autonomous-ai/openharness at commit cc4983e, republished under its MIT licence (© autonomous-ai). 614 words, ~1,177 tokens.
Download SKILL.mdSave it as
.claude/skills/home-assistant/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.- name
- home-assistant
- description
- Turn home-automation requirements into editable Home Assistant YAML, tested what-if scenarios, native Core traces and a reviewed installation kit in Habitat. Use for automation authoring and revision, not unrequested device control.
Build an automation people can use
The deliverable is standard automations.yaml, a testable brief and fixture inventory in project.json, and a portable installation kit—not a diagram or a preview-only dashboard. Habitat's index.html is served by tools/serve.mjs; opening it as a static file is insufficient.
Start with the desired outcome and constraints. If the user has no devices, use explicitly labeled example entities. If they provide existing YAML, keep a copy and preserve unrelated entries; do not replace their installation configuration. Clarify consequential choices such as manual overrides, thresholds and timeout behavior when needed, but do not require hardware for a device-free project.
Read references/scenarios.md when creating or changing the test model. Use actual Core triggers, conditions, templates and actions; do not translate them into a homegrown interpreter. Support a new user request with its own entity inventory and meaningful cases. The hallway starter is an editable starting point, not the definition of this harness.
Design assertions from the brief before adjusting the implementation. Cover normal operation and important non-firing cases where guards matter; include interruption, bounce, missing sensor or manual takeover when relevant. Assert exact call sequence, target, timing and important final states. A complete suite requires each automation to finish with a service call in at least one case; this is minimum coverage, not exhaustive proof.
Build, inspect and deliver
From the workspace:
bash "$HA_SKILLS/home-assistant/scripts/build-automations.sh"This runs the actual Core suite, preserves a checked delivery in output/, then tests the studio's draft round trip, native trace, ZIP download and desktop/mobile layout in Chromium. It records source/runtime-bound evidence in .harness/last-run.json and .harness/browser-proof.json. Setup installs pinned Python/Core and browser runtimes; it does not connect to a home. Use node tools/build.mjs for a quick CLI-only check while iterating; it intentionally leaves browser readiness false.
Inspect expected versus actual calls and Core traces, and look at the generated desktop/mobile screenshots. Change the automation to satisfy the intended behavior, not the test to excuse a bug. Rebuild after every substantive revision. For a new workflow, also reopen the saved JSON or exported ZIP in a fresh directory and rerun it; the user must be able to continue their work without the original workspace.
Deliver the editable project, automations.yaml, readable report, evidence, entity checklist and INTEGRATION.md. Explain the behavior, how the user can revise it, the significant scenarios checked, and the remaining limits. Browser edits are unsaved drafts until Save to workspace; saves preserve history and reject concurrent source changes. Any source/runtime edit invalidates checked output. Failed checks preserve the last useful delivery and clear readiness. Never write a passing verdict manually.
Show full SKILL.md (189 more words)Show less
Scope and installation boundary
Core 2026.9.3 executes real automation logic, local services/helpers and native traces. Time and light/fan/switch device I/O are test doubles; registries are non-persistent. A green result does not verify physical devices, a real installation, restart/restore, network failures or notifications on a phone. Do not claim an unsupported adapter was tested or silently omit it. See PROJECT.md for the supported fixture/trigger types and limits.
Keep each rule's stable ID and initial_state: false; only the isolated runner enables its own copy. That line also disables the imported automation at each real startup until deliberately removed/changed after review. Real installation requires a backup, matching IDs/units/capabilities/helpers/time zone, merging only reviewed entries, that installation's own configuration check, and supervised tests including important non-firing behavior. Run actions alone does not test triggers or conditions.
No URL/token entry, discovery, real service call or deployment is part of this workflow. Such actions require separate user authorization. Reports include source text, states and notes; remind the user to review them before sharing. If a native test, adapter or runtime is unavailable, report the precise limit, keep the draft, and do not relabel it as verified.
© autonomous-ai, 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 8 other files (scripts, references) in store/agents/home-assistant/skills/home-assistant of autonomous-ai/openharness.
- SKILL.md
- references/scenarios.md
- scripts/build-automations.sh
- scripts/build.mjs
- scripts/dashboard.html
- scripts/dashboard.js
- scripts/legacy-configuration.yaml
- scripts/legacy-proof.json
- scripts/model.mjs
Open the folder on GitHubat commit cc4983e
Compare with similar skills
Home Assistant Automation Builder 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Home Assistant Automation Builder this skillautonomous-ai/openharness | 1.2k | — | ~1.2k | Automated safety check: Pass | MIT | |
| Home Assistant Managerkomal-SkyNET/claude-skill-homeassistant | 967 | — | ~1.8k | Automated safety check: Warn | MIT | |
| Skyvern Browser AutomationSkyvern-AI/skyvern | 23k | 1 repos | ~2.9k | Automated safety check: Pass | AGPL-3.0 | |
| N8n CLIn8n-io/n8n | 207k | — | ~3k | Automated safety check: Pass | Custom licence | |
| CUAWright Web Task Automationmicrosoft/CUAWright | 6k | — | ~2k | Automated safety check: Notes | MIT | |
| Skyvern Browser AutomationSkyvern-AI/skyvern | 23k | — | ~1.9k | Automated safety check: Pass | AGPL-3.0 |
Similar skills
Skyvern Browser Automation
Skyvern-AI/skyvern
Picks the right Skyvern CLI command for a web task, from quick yes/no checks to reusable multi-page workflows, instead of falling back to plain page fetching.
- Official
N8n CLI
n8n-io/n8n
Use the n8n CLI to manage workflows, credentials, executions, and more on an n8n instance.
- Official
CUAWright Web Task Automation
microsoft/CUAWright
Solves web tasks by driving a local Playwright browser one bash command at a time, saving a reusable script, screenshots and an action log for each run.
Skyvern Browser Automation
Skyvern-AI/skyvern
Automates websites with Skyvern's AI browser agent to fill forms, extract data, download files, log in and run multi-step workflows through SDKs, REST, MCP or a CLI.
Piece Builder
activepieces/activepieces
Build and edit Activepieces pieces (integrations) — creating new pieces, adding actions or triggers, or fixing bugs in existing ones.
More from autonomous-ai/openharness
All 100 skills in this repoG-code Slicer Tool
autonomous-ai/openharness
Slices 3D mesh files into printer-profiled plain G-code through real slicer CLIs, with backend discovery, input inspection, dry runs and static validation.
Score Music Composer
autonomous-ai/openharness
Turns a musical brief into LilyPond concert-pitch music, checked parts for each instrument and a playable practice pack.
OrcaSlicer 3MF and G-code Workflow
autonomous-ai/openharness
Turns an STL and explicit printer and material requirements into compared OrcaSlicer plans, an editable 3MF project, checked G-code and a portable handoff.
Sheets and Docs Report Builder
autonomous-ai/openharness
Builds an editable DOCX report, a formula-driven XLSX workbook and a fresh LibreOffice PDF preview from one structured source file, then checks them together.
Bambu Labs
autonomous-ai/openharness
Dry-run, upload, and cautiously initiate local Bambu Lab print jobs from validated plain .gcode, using Bambu LAN FTPS/MQTT handoffs.
CAD Viewer Launcher
autonomous-ai/openharness
Starts a local CAD Viewer server for a directory of CAD, robot-description or DXF files and returns a live review link, reusing a running instance when one already serves that directory.
Related
Works with
Categories
Questions about Home Assistant Automation Builder
What does Home Assistant Automation Builder do?
Turns a home-automation request into standard, testable automations.yaml, run against Home Assistant Core's real triggers and verified with its own trace tool. json`, and a portable installation kit as the actual deliverables, not a diagram or a preview-only dashboard, since Habitat's own interface must be served by its tools rather than opened as a static file. When the user has no real devices, it uses explicitly labeled example entities instead, and if the user supplies existing YAML it is kept and preserved rather than replaced outright, with consequential choices like manual overrides and timeout behavior clarified only when they actually matter.
When should I use Home Assistant Automation Builder?
Home Assistant Automation Builder fits situations like: turning a plain-language automation request into standard Home Assistant YAML; writing test assertions for an automation's normal and non-firing cases; verifying a built automation with Home Assistant Core's native trace tool; delivering a portable installation kit for a Home Assistant automation.
How do I install Home Assistant Automation Builder in Claude Code?
Run `npx skills add autonomous-ai/openharness --skill home-assistant -a claude-code`. Or copy the skill folder (store/agents/home-assistant/skills/home-assistant in autonomous-ai/openharness) into .claude/skills/home-assistant in your project. Claude Code loads it when a task matches its description.
How do I install Home Assistant Automation Builder in Codex?
Run `npx skills add autonomous-ai/openharness --skill home-assistant -a codex`. Or copy the skill folder (store/agents/home-assistant/skills/home-assistant in autonomous-ai/openharness) into .agents/skills/home-assistant in your project. Codex loads it when a task matches its description.
Can I use Home Assistant Automation Builder 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 autonomous-ai/openharness --skill home-assistant -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, .gemini/skills/home-assistant, .github/skills/home-assistant and .opencode/skills/home-assistant in your project.
What does Home Assistant Automation Builder need to run?
Going by SKILL.md and its folder, Home Assistant Automation Builder needs JavaScript and a shell for the scripts in its folder and the command-line tools its instructions call (bash and node). Our summary lists: Home Assistant Core; Node.js; Chromium, for the browser verification step.
Does Home Assistant Automation Builder access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Home Assistant Automation Builder safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Home Assistant Automation Builder use?
Home Assistant Automation Builder 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 Automation Builder use?
About 1.2k tokens (SKILL.md is roughly 4.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.3k tokens, read only when the agent opens those files.
What are the alternatives to Home Assistant Automation Builder?
Skills that share tags, products or a category with Home Assistant Automation Builder: Home Assistant Manager (komal-SkyNET/claude-skill-homeassistant, 967 stars), Skyvern Browser Automation (Skyvern-AI/skyvern, 23k stars), N8n CLI (n8n-io/n8n, 207k stars) and CUAWright Web Task Automation (microsoft/CUAWright, 6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Home Assistant Automation Builder?
autonomous-ai (a GitHub organization) maintains it in autonomous-ai/openharness, which has 1,210 GitHub stars. The repository holds 100 skills in this directory. The repository was last updated on October 10, 2026.
Source: autonomous-ai/openharness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.