Update to Pika

{
  "description": "Use when writing or improving the prompt for a Pika video run — text-to-video, image-to-video or a video edit — before running it, whatever the model.",
  "included_files": [],
  "name": "prompt-video",
  "skill_md_contents": "---\nname: prompt-video\ndescription: Use when writing or improving the prompt for a Pika video run — text-to-video, image-to-video or a video edit — before running it, whatever the model.\n---\n\n# Video prompts\n\n## In Pika\n\n- The prompt goes in the tool's `prompt` field. Some apps build the prompt themselves from other fields; fill those instead.\n- Check the model: `create_video` takes a `model`. For Seedance (`seedance-25`, `seedance`, `seedance-mini`) also apply `prompt-seedance`; for MiniMax H3 (`minimax-h3`) apply `prompt-minimax-h3`.\n- Keep the user's intent and words. Expand a described look (\"more cinematic\", \"like a perfume ad\") into the concrete parts below; don't invent a different idea.\n- References are mentioned by kind and position — `@image1`, `@video1`, `@audio1` — matching the order of `image_urls`, `video_urls`, `audio_urls`.\n\n## Structure\n\nWrite it in this order, one or two sentences per part:\n\n1. **Subject** — who or what, with the details that must stay the same (face, outfit, product, logo).\n2. **Action** — one main action per shot, as a sequence of visible physical steps. Say the cause before the effect.\n3. **Scene** — place, time of day, weather, what's in the background.\n4. **Camera** — shot size (wide, medium, close-up), angle (eye level, low, overhead) and one movement (static, push in, pull out, pan, tilt, tracking, orbit, handheld, crane).\n5. **Light and style** — light source and direction (golden hour backlight, soft window light, neon), color palette, medium (live action, 35mm film, 3D animation, anime).\n6. **Pacing** — fit the action to the duration: a 5 s clip holds one beat; 10–15 s holds two or three.\n\nTwo to five sentences is usually enough for one shot.\n\n## Text-to-video vs image-to-video\n\n- **Text-to-video**: describe everything above.\n- **Image-to-video**: the image already sets subject, scene and style. Describe only what moves and how the camera behaves, and name what must stay stable (\"keep the label and the bottle's shape unchanged\").\n- **Edit or restyle a clip**: say what changes and what stays (timing, motion, framing).\n\n## Leave out\n\n- Mood words with nothing visible behind them (\"epic\", \"stunning\", \"dynamic\"): replace each with the light, color or motion that shows it.\n- Several competing camera moves in one shot.\n- Negative lists (\"no blur, no distortion\"). State the wanted result instead: \"steady camera\", \"slow, controlled motion\".\n- Quality tags (\"4K, masterpiece, trending\"): resolution is a field, not a prompt word.\n\n## Example\n\nA photo of a ceramic mug as `@image1`, 5 s:\n\n> Steam rises slowly from the mug in @image1 on a wooden cafe table. Morning sun from a window on the left throws long soft shadows. The camera pushes in gently at eye level until the mug fills the frame. Keep the mug's shape and glaze unchanged.\n"
}