LG webOS TVs

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 already-configured display, normal on-screen approval for the client registration when needed (the returned client key is stored securely and reused), and my permission for the requested input, app, audio, notification or remote operation. Installing the file configures none of that. Install "LG webOS TVs" for me. It works with a confirmed LG webOS display exposing its local SSAP WebSocket service, through a compatible SSAP client such as bscpylgtv using Home Link TCP/WebSocket access; the exact model/webOS version and the discovered endpoint are confirmed first, because capabilities vary by model and firmware. It connects and registers using the normal SSAP pairing flow, preserving the configured TLS trust and the stored client key; a rejected or cancelled prompt is not authorization. It reads available system, power, audio, input and application information and selects actual returned input/app IDs rather than guessing, then issues only the requested supported SSAP control: audio/mute, input selection, installed-app launch, notification or remote action. If a pointer/button socket URL is returned, its host is validated and authorization obtained for a changed destination before it is opened. Cast stays separate: a DIAL advertisement is not proof of Cast, and only if current firmware independently advertises a Cast receiver and I want its media controls does it follow the shared Google Cast skill (../gadget-google-cast/SKILL.md), without duplicating its procedure. Limits: no UDP wake, no silent pairing bypass, no cloud alternative, no assumed inbound media server; no arbitrary device configuration, software installation or screenshot path; an unreachable sleeping TV cannot be promised a local wake. Repository: https://github.com/facebookincubator/muse-gadget-sdk (the skill is the whole skills/gadget-lg-webos-tvs/ 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-lg-webos-tvs/ 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 b64b1ff146036e634908c0bab74f90aa0a6f8412bb2f6f90c3d1694b3cc7f7d2 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 (2,700 bytes). There is no script, no code and no configuration in it; at use time it works through a compatible SSAP client such as bscpylgtv over Home Link TCP/WebSocket against my own LG webOS TV. Its one cross-skill reference is the shared Google Cast skill (../gadget-google-cast/SKILL.md), followed only when a separate Cast receiver is independently advertised; no other dependency exists 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 TV is contacted and no client registration is started during installation. - At use time, exchanges go only to my local TV: registration is the normal SSAP pairing flow I approve on screen — a rejected or cancelled prompt is not authorization — and the returned client key is stored securely and reused, never logged. There is no silent pairing bypass and no cloud alternative. - If a pointer/button socket URL is returned, its host is validated and authorization is obtained for a changed destination before the socket is opened. The skill does no UDP wake, assumes no inbound media server, and does no arbitrary device configuration, software installation or screenshots. - 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-lg-webos-tvs folder into the agent's skills directory, in a folder named exactly "gadget-lg-webos-tvs", 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-lg-webos-tvs), 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 already-configured LG webOS TV on my local network; and approve the normal on-screen client registration when needed, with the returned client key stored securely — and, only if a separate Cast receiver is advertised, optionally also install the shared gadget-google-cast skill for its media controls; 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.