agentleFS
facebookincubatorfacebookincubator/muse-gadget-sdk/skills/gadget-velux-klf200/SKILL.md

gadget-velux-klf200

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

Read positions and control commissioned windows, blinds, shutters, or existing scenes through VELUX KLF200 using Muse Home Link. Use the local binary TCP API with its API credential; not KLF150 or new motor pairing.

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

8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    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 device is a VELUX KLF200 gateway with commissioned compatible windows, blinds or shutters.

    line 11
  2. Distinctive:

    Use node and scene enumeration to identify downstream actuators.

    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:

    Read gateway information, enumerate nodes/scenes and obtain the target's current position, movement and error state.

    line 29
  5. Distinctive:

    Use the exact node type's position semantics and supported functions.

    line 30
  6. Distinctive:

    Check scene membership before execution so the user knows which actuators will move.

    line 37
  7. Distinctive:

    No KLF150 support, native HAP assumption, new motor pairing or gateway reconfiguration.

    line 41
  8. Distinctive:

    Do not assume a universal device capacity or single-session restriction.

    line 42

≈ “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

VELUX KLF200

Use this skill when the device is a VELUX KLF200 gateway with commissioned compatible windows, blinds or shutters.

Identify the Device

  • Confirm KLF200 model and its configured local API service. A VELUX KLF150 is not covered by this API.
  • Use node and scene enumeration to identify downstream actuators; the individual radio devices will not appear as independent LAN hosts.

Prerequisites

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

  • An existing commissioned KLF200 and its Wi-Fi/API password, which is distinct from its web-login password.
  • A compatible binary-protocol client such as pyvlx, routed through HomeLink's TCP transport while preserving the device's TLS requirements.
  • Explicit permission for window/shade movement and confirmation that the target area is safe.

Workflow

  1. Establish the documented encrypted local API session and authenticate with the gateway's API credential. Use the confirmed listener, commonly TCP 51200, not an assumed web endpoint.
  2. Read gateway information, enumerate nodes/scenes and obtain the target's current position, movement and error state.
  3. Use the exact node type's position semantics and supported functions. Send the requested position or stop command, or activate a specifically requested existing scene.
  4. Track the API command/session identifiers and completion/status notifications over the outbound connection. Query node state again after movement completes.

Verify the Result

  • Separate command acceptance from completed motion and actual reported position.
  • Report blocked movement, rain protection, unreachable actuators or unknown position without overriding protective behavior.
  • Check scene membership before execution so the user knows which actuators will move.

Limits

  • No KLF150 support, native HAP assumption, new motor pairing or gateway reconfiguration.
  • Do not assume a universal device capacity or single-session restriction. Handle the installed gateway's actual response.
  • Preserve window safety, locks and rain protections.

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.