Update to Orisu

{
  "description": "Use when the user wants a thumbnail or cover image for a video, Reel, YouTube upload, podcast episode, blog post or product launch, built from their product photo or an image they supply, with a short readable title. Not for ad sets across placements (use product-ad-set).",
  "included_files": [],
  "name": "thumbnail-and-cover",
  "skill_md_contents": "---\nname: thumbnail-and-cover\ndescription: Use when the user wants a thumbnail or cover image for a video, Reel, YouTube upload, podcast episode, blog post or product launch, built from their product photo or an image they supply, with a short readable title. Not for ad sets across placements (use product-ad-set).\n---\n\n# Thumbnail and cover\n\nMake cover images that read at a glance: one subject, one short title, strong contrast. Built from the user's own product photo or image, so the product or the supplied face stays faithful.\n\n## What you need\n\n- The main image: a product photo, a still from their video or a photo they are allowed to use. Use people's faces only from photos the user supplies, and keep them as they are.\n- The title: four words or fewer works best. Use the user's exact wording.\n- Where it goes: YouTube 16:9 (default), Reels or TikTok cover 9:16, podcast or square post 1:1.\n\n## Recipe\n\n1. `upload_asset({ url })` for the image; `get_brand_context` once for colors and type style. For a product on a designed background, cut it out first with `remove_background` and use the cutout as `input_image`, so the old background isn't pasted in as a framed photo.\n2. Make two variants in one go so the user can choose. One call per variant, each with a different layout:\n\n```json\n{ \"tool\": \"edit_image\", \"arguments\": {\n  \"config\": { \"model\": \"nano-banana-2\", \"aspectRatio\": \"16:9\", \"resolution\": \"2K\", \"prompt\": \"YouTube thumbnail. Keep this exact product unchanged, large on the right third, on a deep navy background with a soft rim light. Bold white title \\\"Made by Hand\\\" on the left, large and easy to read at small size. No other text.\" },\n  \"inputs\": { \"input_image\": { \"kind\": \"image\", \"assetId\": \"<asset_id>\" } },\n  \"confirm_above_credits\": 40,\n  \"idempotency_key\": \"thumbnail-and-cover-1\"\n} }\n```\n\nSecond variant: swap sides, change the background color or try a close-up crop of the product.\n\n3. Show both with `preview_asset`, and remind the user that thumbnails are judged at about 200 pixels wide.\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 variant; pass `confirm_above_credits`. On `timed_out: true`, `wait_for_run`. Redo only a failed variant, with a new key.\n\n## Quality check\n\n- Title spelled exactly, readable when small, not covering the product or a face.\n- Subject faithful to the supplied image and placed on the new background, not inside a rectangle of the old photo; no invented logos, badges or claims.\n- Correct aspect ratio for the platform.\n\nGenerated lettering is not guaranteed. If the title is wrong after one retry, offer a version without text that the user can add a title to in their own editor.\n"
}