Set soundscape

Skill sumitaich1998/jarvisvr/skills/media/set-soundscape

An AI agentic operating system for mixed reality on the Meta Quest 3 — your own J.A.R.V.I.S. Multi-agent orchestration, multimodal perception (sight/hearing/gaze), 42 holographic widgets, 20 LLM providers.

Install

npx -y skills add sumitaich1998/jarvisvr --skill set-soundscape

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Play looping ambient soundscapes for focus, relaxation, or sleep — rain, café, forest, white noise — with an optional audio-reactive visualizer. Use for "play some rain sounds", "café ambience", "white noise to focus", or "ocean waves to sleep". Triggers: ambience, soundscape, background sounds, rain sounds, white noise, focus sounds, calm, nature sounds.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.6 KB, as published. Nobody here has run it

Set Soundscape

Create a calm, looping background atmosphere with a low-key visual. Distinct from control-media-playback (foreground tracks) — soundscapes are ambient, looped, and quiet by default.

Steps

Map the mood to a soundscape (rain, café, forest, ocean, white/brown noise, fireplace).
Loop it with play_media (media_type:"audio", loop:true, gentle volume). Keep the player unobtrusive.
Add a subtle visual with show_music_visualizer (style:"wave" or "particles") when the user wants something to look at.
Pair with focus — offer a Pomodoro (productivity-agent) for work sessions, or a sleep timer (manage-timers) to fade out.
Control like any media (volume, stop) via the player's events.

Output

Looping ambience (play_media → media_player):

{ "widget_type": "media_player",
  "transform": { "anchor": "world", "billboard": true },
  "props": { "title": "Rain", "source_url": "https://cdn.jarvisvr.app/audio/rain.mp3",
             "media_type": "audio", "state": "playing", "volume": 0.4, "loop": true } }

Calm visual (show_music_visualizer):

{ "widget_type": "music_visualizer",
  "props": { "track": "Rain", "style": "wave", "amplitude": [0.2,0.3,0.25,0.35,0.3],
             "color": "#7FE7FF", "playing": true } }

agent.speech: { "text": "Rain sounds on, nice and low. Want a focus timer with that?", "final": true }

Edge cases

Too loud by default → start quiet (≈0.4); soundscapes shouldn't startle.
Sleep request → set a fade-out / stop via a manage-timers sleep timer.
Layering → if a foreground track is already playing, ask before stacking audio; usually replace rather than mix.
Named song, not ambience → that's control-media-playback.
Battery/thermal → a static loop is cheap; drop the visualizer if perception.state.thermal is elevated.