agentleFS
facebookincubatorfacebookincubator/muse-gadget-sdk/skills/gadget-lutron-smart-bridges/SKILL.md

gadget-lutron-smart-bridges

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

Read or control lights and shades on compatible Lutron Smart Bridges through Muse Home Link. Use authorized HAP pairing or independently paired LEAP; preserve any existing Apple Home setup.

1 other project uses a version of this, 1 of them edited.

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.

Most recently taken up by

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

11 rules. About 0 are common, 8 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when fresh discovery identifies a compatible Lutron Smart Bridge and the user requests light or shade status/control.

    line 11
  2. Distinctive:

    Use exact discovered endpoints.

    line 16
  3. Very specific:

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

    line 20
  4. Distinctive:

    Prefer the HAP path when authorized pairing is available.

    line 28
  5. Very specific:

    When the advertisement has ff=1, select PairSetupWithAuth.

    line 29
  6. Distinctive:

    Read the target light/shade state and supported ranges.

    line 31
  7. Distinctive:

    Write only the requested characteristic, then read back the individual result.

    line 32
  8. Very specific:

    Check the intended accessory's resulting on/brightness/position state, not merely a successful session or write acknowledgement.

    line 37
  9. Distinctive:

    If pairing or a command fails, report that exact limitation without implying the bridge has no local API.

    line 39
  10. Distinctive:

    No assumed LIP/telnet access, cloud fallback, broad product compatibility or replacement of someone's existing Home.

    line 43
  11. Distinctive:

    Do not add schedules, change bridge configuration or discover room mappings by unrequested toggling.

    line 44

≈ “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

Lutron Smart Bridges: Light and Shade Control

Use this skill when fresh discovery identifies a compatible Lutron Smart Bridge and the user requests light or shade status/control.

Identify the Device

  • Match bridge model and current advertised HAP or documented LEAP service, not the brand alone.
  • Use exact discovered endpoints. Lutron product families do not all expose the same protocols.

Prerequisites

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

  • HAP requires the eight-digit setup code for a pairable bridge or previously authorized controller pairing keys.
  • A bridge already in Apple Home does not automatically give Muse its credentials. Do not reset or remove an existing pairing. If access is unavailable, use only a supported independently authorized alternative or request setup.
  • LEAP uses a separate physical pairing flow and client certificate/private key; HAP credentials do not substitute for them.

Workflow

  1. Prefer the HAP path when authorized pairing is available. Use a maintained HAP client over the shared network access.
  2. When the advertisement has ff=1, select PairSetupWithAuth; plain PairSetup can fail at M2 with kTLVError_Authentication. Keep that exchange on one persistent connection.
  3. Store successful pairing material in approved credential storage (private file permissions if file-backed). Open an encrypted session and enumerate actual accessories, services and characteristics.
  4. Read the target light/shade state and supported ranges. Resolve ambiguous generic accessory names before writing; any physical identification action must be explicitly requested.
  5. Write only the requested characteristic, then read back the individual result. For partial batch failures, inspect each target before retrying uncertain operations.
  6. For a compatible bridge using LEAP instead, follow pylutron-caseta's pairing routine with the user present, store its own credentials, enumerate devices with the authenticated client and use its documented level/cover operations.

Verify the Result

  • Check the intended accessory's resulting on/brightness/position state, not merely a successful session or write acknowledgement.
  • For shade movement, observe progress and final state; preserve obstruction and motor behavior.
  • If pairing or a command fails, report that exact limitation without implying the bridge has no local API.

Limits

  • No assumed LIP/telnet access, cloud fallback, broad product compatibility or replacement of someone's existing Home.
  • Do not add schedules, change bridge configuration or discover room mappings by unrequested toggling.

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.