Update to Orisu

{
  "description": "Use when the user wants several distinct creative directions for the same product to compare or A/B test, such as different scenes, angles, moods or visual hooks for one brief. Not for resizing one ad (use ad-placement-adaptation) or a single coordinated set with one message (use product-ad-set).",
  "included_files": [],
  "name": "ad-concept-variations",
  "skill_md_contents": "---\nname: ad-concept-variations\ndescription: Use when the user wants several distinct creative directions for the same product to compare or A/B test, such as different scenes, angles, moods or visual hooks for one brief. Not for resizing one ad (use ad-placement-adaptation) or a single coordinated set with one message (use product-ad-set).\n---\n\n# Ad concept variations\n\nGive the user a few genuinely different directions for one product and brief, so they can pick or test. Each concept changes one clear thing (scene, mood, angle or hook) and keeps the product and the message the same.\n\n## What you need\n\n- A photo of the product (attached or a public URL).\n- The brief: product, audience and the message or offer, exactly as the user states it.\n- Optional: how many concepts. Default three, at most six in one go.\n\n## Recipe\n\n1. `get_brand_context` once; reuse its colors and tone. `upload_asset({ url })` for the photo. For studio or solid-backdrop concepts, cut the product out once with `remove_background` and edit the cutout; scene concepts can start from the photo.\n2. Write the concepts before spending anything. Use `generate_text` only if the user wants help; otherwise draft them yourself. Make them differ on purpose, for example:\n   - **Lifestyle:** the product in use in a real home moment.\n   - **Bold studio:** the product on a saturated brand-color backdrop, hard light.\n   - **Ingredient or detail story:** the product beside what it is made of.\n   Show the list in one message and let the user drop or change any.\n3. One `edit_image` per approved concept, all at the same aspect ratio so they compare fairly:\n\n```json\n{ \"tool\": \"edit_image\", \"arguments\": {\n  \"config\": { \"model\": \"nano-banana-2\", \"aspectRatio\": \"4:5\", \"resolution\": \"2K\", \"prompt\": \"Concept B, bold studio: keep this exact product unchanged on a saturated terracotta backdrop, hard directional light from the upper left, strong shadow. No text.\" },\n  \"inputs\": { \"input_image\": { \"kind\": \"image\", \"assetId\": \"<asset_id>\" } },\n  \"confirm_above_credits\": 40,\n  \"idempotency_key\": \"ad-concept-variations-1\"\n} }\n```\n\n4. Present them side by side with `preview_asset`, each labeled with its concept letter and a one-line description of what it changes.\n\n## Cost, waiting and retries\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\nOne paid generation per concept. State the count before you start and pass `confirm_above_credits` on each call. On `timed_out: true`, `wait_for_run`. Redo only failed concepts, each with a new key.\n\n## Quality check\n\n- Each concept is clearly different from the others at a glance.\n- The product is the same in all of them; no invented text, offers or claims.\n- Don't claim one concept will perform better. Suggest testing them.\n\n## Next edits to offer\n\n- Turn the winner into a full placement set: product-ad-set or ad-placement-adaptation.\n- Animate the winner: product-motion.\n"
}