{"id":31090,"plugin_id":"plugin_asdk_app_6ac466ba11f4819191ee609ea667f124","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-10-10T06:12:56.426Z","digest":"7e5fcb7273a1bda1576ed01300d16fc6e42c589a03f9d90922ea1bb178d1fa69","against":null,"payload":{"description":"Use when writing or improving a prompt for a Pika run that uses Seedance — `create_video` with model seedance-25, seedance or seedance-mini.","included_files":[],"name":"prompt-seedance","skill_md_contents":"---\nname: prompt-seedance\ndescription: Use when writing or improving a prompt for a Pika run that uses Seedance — `create_video` with model seedance-25, seedance or seedance-mini.\n---\n\n# Seedance prompts\n\nStart from `prompt-video`; this adds what Seedance rewards.\n\n## In Pika\n\n- Model ids: `seedance-25` (Seedance 2.5: up to 30 s, native audio, up to 30 image / 10 video / 10 audio references), `seedance` (2.0: up to 15 s) and `seedance-mini`. `product_ad` (Seedance 2.5) and `short_film` (Seedance 2.5 by default) write their own prompts from their fields; this skill applies where a `prompt` field is open.\n- Mention references as `@image1`, `@video1`, `@audio1`, in the order of the `image_urls`, `video_urls`, `audio_urls` you pass. The `create_video` field descriptions give the exact durations and reference limits for the route.\n\n## Write it like production notes\n\nFor a simple shot, subject plus action is enough. For anything longer, use short labeled blocks, in this order, and skip the ones you don't need:\n\n1. **Format** — length, ratio, live action or animation.\n2. **References** — one job per reference: \"@image1 is the product: keep its shape, color and label exactly. Ignore @image1's background.\"\n3. **Opening state** — where everyone and everything is in the first frame.\n4. **Timeline** — the action in time blocks (\"0–5 s\", \"5–10 s\"). Each block starts from the physical result of the one before. Cause before effect: contact, then the reaction.\n5. **Camera** — shot size, angle and one movement per shot, tied to what happens (\"pushes in as she lifts the cup\").\n6. **Continuity** — when something leaves frame and returns, repeat its key details (same face, same green coat).\n7. **Audio** — dialogue in quotes with who says it, then ambient sound and music. Seedance 2.5 renders audio natively.\n8. **Constraints** — only what the model gets wrong without being told (\"one continuous take\", \"the logo stays readable\").\n\n## Multi-shot\n\nLabel each shot — `Shot 1`, `Shot 2` — each with its own framing, action and end point, and end each with \"Hard cut.\" Keep the cast and product descriptions identical across shots.\n\n## Avoid\n\n- Vague motion words (\"dynamic\", \"epic camera\"): name the move.\n- Several references for the same element; one clear reference per face, product, place or style works better than many.\n- Cramming a 30 s story into one sentence: long clips need a timeline, or actions get skipped or rushed.\n\n## Examples\n\nProduct, 10 s, `@image1` = product photo:\n\n> @image1 is the espresso maker: keep its matte cobalt shell and copper button exactly. On a light oak counter in soft morning light, a hand enters from frame right and presses the button once. Dark espresso streams into the glass below; steam curls up. Close-up at counter height, slow push-in, one continuous take. Sound: a soft click, then a low hiss and pouring.\n\nTwo shots, 12 s:\n\n> Shot 1 (0–6 s): wide shot of a rain-soaked night street, a cyclist in a yellow jacket rides toward camera through neon reflections; the camera tracks backward at her speed. Hard cut.\n> Shot 2 (6–12 s): close-up of the same cyclist in the yellow jacket, rain on her face, as she brakes and looks up at a flickering sign. Static camera. Sound: rain, tire hiss, a distant tram bell.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}