agentleFS
facebookincubatorfacebookincubator/muse-gadget-sdk/skills/gadget-google-nest-thermostats/SKILL.md

gadget-google-nest-thermostats

Skill2.6k starsChanged 25 days agoApache-2.0View on GitHub

Read and adjust Google Nest thermostats through Google's Smart Device Management API via an existing self-hosted bridge on the home network (for example Home Assistant on a Raspberry Pi) using Muse Home Link. Not Google Cast, not the Google Home app, and not Matter commissioning.

Trending

More talk lately.thin dataabout the whole repository

Dec 2025: 0 mentionsJan 2026: 0 mentionsFeb 2026: 0 mentionsMar 2026: 0 mentionsApr 2026: 0 mentionsMay 2026: 0 mentionsJun 2026: 0 mentionsJul 2026: 0 mentionsAug 2026: 0 mentionsSep 2026: 0 mentionsOct 2026: 13 mentionsNov 2026: 1 mention
Dec 2025Jun 2026Nov 2026
Mentions a month of the facebookincubator/muse-gadget-sdk repository that our weekly crawl found: only 14 in all, so this is a hint, not a trend. There is no adoption data for this file yet.

Who's talking about facebookincubator/muse-gadget-sdk

The biggest 5 of 14 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 14

Talked about on GitHub, Bluesky and Hacker News (14 times).

On GitHub · 11

6 more on GitHub

On Hacker News · 1

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the home's Nest thermostats are already bridged into a local system Muse can reach — most commonly Home Assistant on a …

    line 12
  2. Distinctive:

    Read current ambient temperature, humidity, mode, and setpoint from the bridge before changing anything, so a change can be verified …

    line 20
  3. Distinctive:

    If no bridge or no thermostat is reachable, stop and give the user these steps — do not create projects, consent to OAuth, or handle tokens …

    line 25
  4. Very specific:

    Read and follow the Home Link networking and safety rules in ~/docs/devices/home_link.md.

    line 39
  5. Distinctive:

    If reads return stale data, say so and give the last-update time rather than presenting it as current.

    line 60
  6. Distinctive:

    No changes to the Device Access project, OAuth grants, account sharing, or thermostat schedules and learning features from a skill session.

    line 65

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Google Nest Thermostats — Smart Device Management Bridge

Use this skill when the home's Nest thermostats are already bridged into a local system Muse can reach — most commonly Home Assistant on a Pi — through Google's Device Access program, and the user asks about indoor temperature, setpoints, or HVAC mode.

Identify the Device

  • Confirm which thermostats the bridge exposes and match them to rooms with the user; SDM device names rarely match room names out of the box.
  • Read current ambient temperature, humidity, mode, and setpoint from the bridge before changing anything, so a change can be verified against the prior state.

Guided Setup Check

If no bridge or no thermostat is reachable, stop and give the user these steps — do not create projects, consent to OAuth, or handle tokens on their behalf.

  1. In the Google Device Access Console, create a Device Access project and enable the Smart Device Management API. Google charges a one-time US$5 registration fee; it is a developer program, and Google can change its terms, quotas, or availability.
  2. As the Google account owner, complete the OAuth consent flow and connect the project in the local bridge (for example the Home Assistant Google Nest integration). Refresh tokens stay in the bridge; if they expire, only the owner can re-consent.
  3. List the devices the project exposes and match each thermostat to its room with the user before answering questions about it.

Prerequisites

Read and follow the Home Link networking and safety rules in ~/docs/devices/home_link.md.

  • The guided setup check passes: a Device Access project exists, the bridge holds valid tokens, and the thermostats are reachable through the bridge's local API or entities.
  • Note: SDM writes can lag and occasionally report success before the thermostat applies them; the workflow below verifies after every write. Newer Nest models may also support Matter locally — prefer whichever path the home already runs rather than migrating as a side effect.

Workflow

  1. For status questions, read the thermostat traits through the bridge's local API or entities: ambient temperature and humidity, HVAC status, mode, active setpoint.
  2. For an adjustment the user requested, set the mode or setpoint through the bridge, then re-read the device state after a short wait to confirm it applied.
  3. Report temperatures in the units the household uses, with the read time.

Verify the Result

  • A successful API response is not proof the thermostat changed: confirm via a fresh state read showing the new setpoint or mode.
  • If reads return stale data, say so and give the last-update time rather than presenting it as current.

Limits

  • No changes to the Device Access project, OAuth grants, account sharing, or thermostat schedules and learning features from a skill session.
  • Comfort control only: never present thermostat automation as freeze, heat-safety, or occupancy protection.
  • Temperature history is household data; report what the user asked for, nothing more.

Sources

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.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

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.