Update to Voyager Video & 3D

{
  "description": "Cloud: generate or edit still images with Voyager, including branded images and images of saved Cast characters.",
  "included_files": [
    {
      "relative_path": "references/color-and-brand.md",
      "size_in_bytes": 1534
    },
    {
      "relative_path": "references/typography.md",
      "size_in_bytes": 1023
    }
  ],
  "name": "voyager-cloud-image",
  "skill_md_contents": "---\nname: voyager-cloud-image\ndescription: \"Cloud: generate or edit still images with Voyager, including branded images and images of saved Cast characters.\"\n---\n\n# Images\n\nFollow `voyager-cloud` (read it with `load_skill` if it isn't loaded) for account,\nmodels, costs and jobs.\nChoose the image model as `voyager-cloud` describes. Honor an explicit size,\naspect ratio, count and quality; otherwise make one square image.\n\n## Source real subjects\n\nFor a real subject, use the first usable source: the user's asset (brief,\nattachments in this conversation or a brand kit), then the\nsubject's official source or open libraries/stock, then generation when exact\nstructure or labels are not required, then a hand-built depiction labeled\nschematic. The user's explicitly requested version wins; a guessed asset type\nis not such a request. Abstract or invented subjects are made freely. Follow the\nruntime's likeness, licensing and factual-claim boundaries.\n\n## Recurring characters\n\nFor a character across several images, use a Cast card as `voyager-cloud`\ndescribes and pass its ID with `generate_image` on every image, edits included.\nAdditional style, composition or edit references stay explicit asset IDs.\n\n## Exact words, logos and layouts\n\nImage models misspell and redraw. When the brief needs exact words, a real logo\nor several sizes, generate the picture without lettering and say that exact text\nand layout are finished in a design tool; pass a real logo only as an imported or\nbrand-kit asset ID, never redrawn from memory. A thumbnail may heighten the real\nstory; it should not imply events the video never contains.\n\n## Generate or edit\n\nWrite the prompt as subject, action, setting, composition, light and look. For an\nedit, import the image with `import_reference`, pass its asset ID and describe\nonly the change and what must stay the same. Say which reference does what when\nthere are several (\"image 1 sets the look; image 2 is the product\"). Show every\noutput; offer one targeted retake rather than a batch of guesses.\n\n## The style key wins over photo references\n\nImage models follow a photo more readily than words: given a photo of a person\nand \"line art\", they tend to return a photo of the person. Once a style is set\n(a requested look such as line art or a storyboard sketch, or a style key image),\nhold it:\n\n- For a recurring character, pass Cast IDs on every\n  image/video estimate and run. The adapter adds its fixed description, refs\n  and model token mapping. Write shot action, composition, camera, look and\n  sound around the character's name; do not invent numbered Cast-ref tokens.\n- Pass a photo only for identity: the face, hair, wardrobe, a product's shape and\n  markings, a prop. Say which image does what, and that the photo does not set\n  the look: \"Use image 2 only for the woman's face, hair and coat. Draw the whole\n  frame as loose black line art on white, like image 1, not as a photograph.\"\n- Pass the style key image, when there is one, with every frame, and repeat its\n  words in every prompt. A shot under a film's scoped look (a photoreal\n  flashback) takes that look's image and words instead.\n- Before accepting a frame, compare it with the look that applies to it: the\n  same medium, line, fill, texture and palette. A frame that matches its scoped\n  look is not a failed take. A frame that drifted toward the photo is a\n  failed take, not a variant. Keep the same `cast` IDs and strengthen the style\n  direction on a correction. Do not drop identity refs or substitute text-only\n  identity. Report\n  likeness results separately from style inspection: a face match can still be\n  off-look, and an unavailable check is not a match.\n\n## Brand and type\n\n- [Typography](references/typography.md) for any lettered image.\n- [Color and brand](references/color-and-brand.md) for named brands, brand kits and contrast.\n\nWhen these files aren't available, read them with `load_skill` for this skill and\n`file` set to the path.\n\n"
}