Samsung Tizen 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 my approval of the normal TV pairing prompt when required, with secure storage and reuse of its returned token, plus permission for the requested screen/audio/app action (and, for Frame art, permission for the particular content and operation). Installing the file configures none of that. Install "Samsung Tizen TVs" for me. It works with a confirmed Samsung Tizen TV exposing a compatible local remote WebSocket service, through a compatible client routed through Home Link with device-specific TLS trust preserved (documented client: samsung-tv-ws-api). It confirms model, firmware and the actual remote endpoint; a Frame model's Art API is separate from the remote interface, and Art support is never inferred from the Samsung brand alone. It connects with a recognizable client name and a valid saved token, or completes normal user-approved pairing, then reads available device, power, app or Art status using interfaces documented for this model — never substituting a cloud API when a local read is unavailable. For remote control it sends only the requested supported key or app operation, resolving real app identifiers rather than guessing them. On an Art-capable Frame with a supported Art API version, it may use the documented status/mode, available-art selection or requested upload operation, transferring only user-approved media through the documented local client protocol and authorizing any additional destination it requires. Responses and available state are checked after each action; a key sequence is never an unverified substitute for an unavailable direct operation. Limits: no cloud alternatives, no UDP wake, no device-to-agent media fetch without an existing reachable source; no universal Frame Art coverage, app installation, unrequested content replacement/deletion or firmware changes; a sleeping TV may not expose its API. Repository: https://github.com/facebookincubator/muse-gadget-sdk (the skill is the whole skills/gadget-samsung-tizen-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-samsung-tizen-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 89576bd5dd090512e8459fa481a16b732c5f5c5ea0f64e7477c04b4b4ae4d2d9 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 (2,829 bytes). There is no script, no code and no configuration in it; at use time it works through a compatible local WebSocket client (samsung-tv-ws-api) routed through Muse Home Link against my own Samsung Tizen TV, with device-specific TLS trust preserved. 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 TV is contacted and no pairing prompt is triggered during installation. - At use time, exchanges go only to my local TV: the connection uses a recognizable client name and a valid saved pairing token, or completes the normal pairing prompt I approve on screen, and the returned token is stored securely and reused, never logged. No cloud API is ever substituted when a local read is unavailable. - Frame Art is a separate API from the remote interface: Art operations happen only when the exact model and Art API version support them, and only user-approved media is transferred through the documented local client protocol, with any additional destination it requires authorized first. The skill does no app installation, no unrequested content replacement or deletion, no firmware changes and no UDP wake. - 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-samsung-tizen-tvs folder into the agent's skills directory, in a folder named exactly "gadget-samsung-tizen-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-samsung-tizen-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 a compatible Samsung Tizen TV already set up on my local network; and approve the normal on-screen pairing prompt when required, with its returned token stored securely — plus separate permission for any Frame Art content and operation; 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.