Elgato Key Light

Before you start: read this whole install prompt, tell me in a few lines what this skill does and what installing it involves, and wait for my go-ahead before you do anything else. Prerequisites — Muse Home Link and a compatible physical device are required to USE this skill, not to install it: installing the skill file itself needs no account, no key and no device, and this install does NOT set up Home Link, pair anything or ask for any credential. But the skill is instructions only. To use it I must read and follow ~/docs/devices/home_link.md in my Muse environment, have the compatible physical device named below already set up on my local network, and have an Elgato Key Light (board type 53) already on Wi-Fi on my local network, identified by fresh discovery, and know that its local HTTP API is unauthenticated: that does not waive host/action authorization, and I must never expose this API outside my trusted network. No credential is involved. Installing the file configures none of that. Install "Elgato Key Light" for me. It controls Elgato Key Light power, brightness, white temperature and requested identification through Muse Home Link, using the local HTTP light API. It is used when fresh discovery identifies an Elgato Key Light: it matches _elg._tcp with manufacturer Elgato and model/board metadata (usual API port 9123, but the discovered port is used), GETs /elgato/accessory-info and confirms productName, hardwareBoardType 53 and lights capability, keeping serial, MAC and network metadata private; Air, Mini and Light Strip are distinct variants whose additional capabilities are outside this skill. The light must already be on Wi-Fi. The local HTTP API is unauthenticated; that does not waive host/action authorization, and this API must never be exposed outside the trusted network. Before acting it confirms the requested lighting change will not unexpectedly disrupt a call, recording or live stream. It GETs /elgato/lights and reads numberOfLights plus the target light's current on, brightness and temperature, then PUTs /elgato/lights sending only requested fields: on:1 or on:0, brightness as an integer percent within the supported range (3-100 is the useful range for board type 53, while 0-2 may have no visible effect), or temperature in mireds, round(1000000 / kelvin) clamped to 143-344 for board 53 (4000 K is 250 mireds; smaller values are cooler). If explicitly asked to identify the panel, it POSTs /elgato/identify once; it visibly blinks and may return an empty body. It polls /elgato/lights to read back changes and serializes requests rather than simulating fades with rapid bursts. It checks actual on/brightness/temperature values after a write and converts units clearly; an empty successful identify response is expected, but visible identification still needs observation, and temporary identification settings are restored when appropriate. Limits: no power-on configuration, rename, restart or firmware-update operations, and no colour/RGB support inferred from a white-temperature panel. Repository: https://github.com/facebookincubator/muse-gadget-sdk (the skill is the whole skills/gadget-elgato-key-light/ folder at the pinned commit: SKILL.md only, 1 file) Pinned version: install the code at commit e6fe5174092702ffddae6f90759a38d55a4ebae1 exactly. Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Clone https://github.com/facebookincubator/muse-gadget-sdk into a temporary folder, check out commit e6fe5174092702ffddae6f90759a38d55a4ebae1, and copy the skills/gadget-elgato-key-light/ folder from that checkout. Then compare every file in the folder with the fingerprints recorded for this listing on 2026-10-22: [FINGERPRINTS] - SKILL.md: SHA-256 2c43c56d61015e2580ac34b519b18555598a2ba3e3daefc91a2e09174fd48f9b If a file does not match, it changed since the listing was prepared: do not install it yet, tell me what you found and let me decide. 2. Read SKILL.md in full, and tell me in plain words: what the skill does when used, what it connects to, whether it reads or sends any personal information or credentials, and anything that seems unusual. Stop on any red flag and tell me before going further. Confirm these points from the files: - The skill folder holds 1 file only: SKILL.md (2 686 bytes). There is no script, no code and no configuration in it; the procedure runs at use time through Muse Home Link against my own local device. It has no dependency on any other gadget skill in this lot. - Nothing is sent anywhere during installation itself; the only download at install time is the skill folder from GitHub at the pinned commit. No device is contacted, no pairing is started and no key is asked for during installation. - At use time, exchanges go only to my local Elgato Key Light over its local HTTP API: GET/PUT /elgato/lights, GET /elgato/accessory-info and, only if I explicitly ask for identification, one POST /elgato/identify. The API is unauthenticated, which does not waive host/action authorization, and it must never be exposed outside my trusted network. No credential is read or sent at use time. - The skill does not do power-on configuration, rename, restart or firmware updates, does not infer colour/RGB support from a white-temperature panel, and does not cover the Air, Mini or Light Strip variants. - Do not pair any device, do not ask for or set any credential, do not run any control, print, scan or playback action, and do not use the skill in any way during this install: Home Link setup, pairing and use are my decisions, later, when I actually ask for them. 3. When I say "yes, install", install it as a skill: copy the whole gadget-elgato-key-light folder into the agent's skills directory, in a folder named exactly "gadget-elgato-key-light", keeping its 1 file (SKILL.md at its root). The exact folder name matters: relative links between sibling gadget skills depend on these exact names. 4. Verify with no network calls: frontmatter valid (name: gadget-elgato-key-light), the 1 file in place with matching fingerprint. Do not run anything and do not connect to any device to verify. 5. Report what was installed, where, and what I still need to do myself (for example: read ~/docs/devices/home_link.md in my Muse environment and follow its Home Link rules; have an Elgato Key Light (board type 53) already on Wi-Fi on my local network, knowing its local HTTP API is unauthenticated and must never be exposed outside my trusted network; no credential is involved; using the skill is a separate step that only starts when I ask for it, and the use-time exchanges disclosed above happen only then). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.