Create image

Skill sumitaich1998/jarvisvr/skills/media/create-image

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 create-image

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

Generate images from a text prompt and display them with prompt, status, and progress. Use for "make an image of…", "generate a picture of…", "imagine…", or visualizing a concept/mood. Triggers: generate image, make a picture, draw, imagine, create art, render an image, AI image, visualize this.

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

2.4 KB, as published. Nobody here has run it

Create Image

Turn a prompt into one or more images shown in an image_gen_viewer, reflecting the live generation lifecycle (queued → generating → done).

Steps

Refine the prompt. Keep the user's intent; you may add concise style hints ("synthwave, high detail") but don't override their request.
Spawn the viewer with show_generated_image in queued/generating state and a progress value.
Stream progress with holo.update as generation advances, then set status:"done" with the resulting images.
Speak a short confirmation; offer variations or a save.

Output

image_gen_viewer (show_generated_image, props per registry.json):

While generating:

{ "widget_type": "image_gen_viewer",
  "transform": { "anchor": "world", "billboard": true },
  "props": { "prompt": "a neon city skyline at night, synthwave",
             "status": "generating", "progress": 0.4, "model": "diffusion-xl" },
  "interactions": ["tap","grab","resize","drag","dwell"] }

When done (holo.update):

{ "object_id": "O_imggen",
  "props": { "status": "done", "progress": 1.0,
             "images": [ { "url": "https://cdn.jarvisvr.app/gen/neon1.png", "seed": 42 } ] } }

agent.speech: { "text": "Here's your synthwave skyline.", "final": true }

Edge cases

No provider / generation fails → set status:"error" with an error message; don't spawn fake image URLs.
Unsafe / disallowed prompt → decline briefly and offer a safe reframe.
Multiple variations → return several images; user taps select_image.
Use as cover art / texture → hand the URL to control-media-playback (poster) or a model_viewer/image_board via the stage.
Very slow gen → keep streaming progress; let the user keep talking.