Update to Voyager Video & 3D

{
  "description": "Cloud: generate 3D models with Voyager from a text description or a reference image, and retexture them.",
  "included_files": [],
  "name": "voyager-cloud-3d",
  "skill_md_contents": "---\nname: voyager-cloud-3d\ndescription: \"Cloud: generate 3D models with Voyager from a text description or a reference image, and retexture them.\"\n---\n\n# 3D models\n\nFollow `voyager-cloud` (read it with `load_skill` if it isn't loaded) for account,\nmodels, costs and jobs.\n\n## Generate\n\n1. Choose the model as `voyager-cloud` describes. The default makes a model from\n   text, and from a reference image it makes one from the image. For another\n   operation pass its `mode` (retexture, rigging, remesh, animations and more,\n   all listed by `list_models` with `operation` 3d) and omit `model`.\n2. For a specific object, import a clean reference image (one object, plain\n   background, the whole object in view) with `import_reference` and pass its\n   asset ID in `reference_ids`. To retexture, pass the finished 3D job as\n   `source_job_id`. For a concept,\n   describe shape, materials, style and intended use (game asset, product shot,\n   print) in the prompt.\n3. Call `generate_3d` and poll `get_job`. 3D jobs take several\n   minutes.\n4. Present the preview image and the downloadable formats the job returns (for\n   example GLB). Say which format suits the user's tool; don't promise rigging,\n   animation or formats the job did not return.\n"
}