Update to Orisu

{
  "description": "Use when the user wants store or marketplace images made from a photo of their own product, such as a white-background packshot, lifestyle scenes, a detail close-up or a full product-page set (Shopify, Amazon, Etsy and similar). Not for a single retouch of an existing image (use product-image-cleanup or product-scene-styling) or for ads with a headline (use product-ad-set).",
  "included_files": [],
  "name": "ecommerce-product-photos",
  "skill_md_contents": "---\nname: ecommerce-product-photos\ndescription: Use when the user wants store or marketplace images made from a photo of their own product, such as a white-background packshot, lifestyle scenes, a detail close-up or a full product-page set (Shopify, Amazon, Etsy and similar). Not for a single retouch of an existing image (use product-image-cleanup or product-scene-styling) or for ads with a headline (use product-ad-set).\n---\n\n# Product Photo Studio\n\nTurn one photo of a real product into a matching set of store images. Every image is an edit of the user's own photo rather than a new product made from a description. Generative edits can still change details, so check every image against the original and fix or flag anything that drifted.\n\n## What you need\n\n- A photo of the product, attached or as a public image URL. A plain phone photo works; one product per photo.\n- Optional: product name, where it is used (kitchen, bathroom, desk, outdoors) and the look they want.\n- Optional: which images they need. If they don't say, make the standard set.\n\nNo photo? Ask for one. Don't generate a product from a text description; it would not be their product. Ask at most one question about scene or style. Otherwise pick sensible defaults and say what you chose.\n\n## Standard set\n\n| Image | Aspect ratio | Instruction |\n|---|---|---|\n| Packshot | 1:1 | This exact product, centered on a pure white background, soft even studio light, true colors and label, no props. |\n| Lifestyle | 4:5 | This exact product in a realistic scene that matches how it is used, natural light, product in sharp focus. |\n| Detail | 1:1 | A close-up of this exact product's most important detail (texture, material, label), shallow depth of field. |\n| Cutout | original | Optional: the product on a transparent background, for the user's own layouts. |\n\nMatch the scene to the product: a candle in a living room, a trail shoe on a trail, a serum on a bathroom shelf. Four images is the default; make fewer if the user asks for fewer.\n\n## Recipe\n\n1. **Brand look (once).** If the user mentions their brand or style, call `get_brand_context` once and reuse what it says in every instruction. If it is empty, keep the styling neutral.\n2. **Store the photo.**\n\n```json\n{ \"tool\": \"upload_asset\", \"arguments\": { \"url\": \"https://orisu.ai/review-assets/ceramic-mug.jpg\" } }\n```\n\nKeep the returned `asset_id`.\n\n3. **Packshot first.** Marketplaces often require a white main image, and it confirms the product survives the edit before you spend on the rest.\n\n```json\n{ \"tool\": \"edit_image\", \"arguments\": {\n  \"config\": { \"model\": \"nano-banana-2\", \"aspectRatio\": \"1:1\", \"resolution\": \"2K\", \"prompt\": \"Place this exact product, unchanged, centered on a pure white background. Soft even studio lighting, true colors, the label exactly as in the photo, no props, no added text.\" },\n  \"inputs\": { \"input_image\": { \"kind\": \"image\", \"assetId\": \"<asset_id>\" } },\n  \"confirm_above_credits\": 40,\n  \"idempotency_key\": \"ecommerce-product-photos-1\"\n} }\n```\n\n4. **Check it** (see \"Quality check\"). If the product changed, retry once with a stricter instruction (\"do not change the product's shape, label or color\") before moving on. If the original background shows through or the photo appears as a framed picture, cut the product out with `remove_background` (step 6) and run the packshot on the cutout instead.\n5. **Lifestyle and detail.** Same call on the original photo (not on the packshot), one call per image, with the table's instruction, `aspectRatio` and the chosen scene. For two lifestyle options, make two calls with different scenes rather than one vague prompt.\n6. **Cutout (only if asked).**\n\n```json\n{ \"tool\": \"remove_background\", \"arguments\": { \"config\": {}, \"inputs\": { \"input_image\": { \"kind\": \"image\", \"assetId\": \"<asset_id>\" } } } }\n```\n\n7. **Deliver.** Show the set together with `preview_asset` (up to 8 asset ids from each result's `orisu_media.items`). Label each image (Packshot, Lifestyle, Detail) and offer the next edits listed below.\n\n## Cost and waiting\n\nGive every paid call its own `idempotency_key`, unique to that request (for example `mug-packshot-1`). Send the same key again only to resend a call that was interrupted or whose result you never saw, such as after a permission or file-download prompt; the first result then comes back instead of a second charge. Before re-running anything, check `list_runs` or `get_run` for a result that already finished. To redo something on purpose (a failed run, an image that missed, changed settings), use a new key: the old one would replay the same result, failure included.\n\n- Each image is one paid generation, about 10 credits at 2K. Pass `confirm_above_credits` (40 is enough for one image). On `COST_CONFIRMATION_REQUIRED`, show the estimate and call again with a higher limit only after the user agrees.\n- If a result has `timed_out: true`, the run continues: call `wait_for_run` with its `id`. Never start the same image again while it is still running.\n- If one image fails, redo only that image. Keep the finished ones.\n\n## Quality check\n\nLook at every image before presenting it:\n\n- Same product: shape, proportions, label text, logo, color and number of items match the original photo.\n- No invented text, badges, prices or claims; no extra products.\n- Correct aspect ratio; packshot background is clean white with no shadow artifacts cutting the product, and none of the original photo's background left.\n- Lifestyle scene is plausible for the product and the product is the sharpest thing in frame.\n\nIf an image fails, say what is wrong and redo that one image. Don't present a failed image as finished.\n\n## Next edits to offer\n\n- Another color or material: `edit_image` on the packshot (\"Same product, glaze changed to sage green, everything else unchanged\").\n- A story or banner format: the ad-placement-adaptation skill (`change_aspect_ratio` extends the scene instead of cropping the product).\n- Print size: `upscale_image` with `topaz-upscale` and `scale_factor` 4.\n- Ad versions with a headline: the product-ad-set skill.\n- A short clip of the product: the product-motion skill.\n"
}