Update to Pika

{
  "description": "Use when writing or improving a prompt for a Pika run that uses GPT Image — `create_image` or `edit_image` with model gpt-image-2.",
  "included_files": [],
  "name": "prompt-gpt-image",
  "skill_md_contents": "---\nname: prompt-gpt-image\ndescription: Use when writing or improving a prompt for a Pika run that uses GPT Image — `create_image` or `edit_image` with model gpt-image-2.\n---\n\n# GPT Image prompts\n\nStart from `prompt-image`; this adds what GPT Image rewards.\n\n## In Pika\n\n- Model id `gpt-image-2` in `create_image`. Fields besides `prompt`: `aspect_ratio`, `quality`, `background` (transparent for cut-outs and logos), `output_format`, and `image_urls` for edits and references. In `edit_image` the prompt goes in `instructions`, with `reference_urls`, `resolution` and `quality`.\n- Put size, quality and transparency in their fields, not the prompt.\n\n## Structure\n\n- Lead with the result and its use: \"A product photo for a store listing\", \"A poster for a jazz night\".\n- Describe what is visible: materials, textures, light, color, medium. Ask for \"a real photograph\" or \"photorealistic\" when that's the goal.\n- For people: framing (\"full body, feet visible\"), gaze, pose, what they hold.\n- For a long request, labeled sections read best: Scene, Subject, Details, Text, Constraints.\n\n## Photoreal look\n\nDescribe it like a photographer: framing (\"medium close-up at eye level\"), lens (\"50 mm, shallow depth of field\"), film or grain, natural texture (pores, wear, creases), and \"no heavy retouching\" when it should look candid.\n\n## Text in the image\n\n- Exact words in quotes, with position and lettering: `the headline \"OPEN LATE\" in bold condensed white capitals across the top`.\n- Spell unusual names letter by letter if they come back wrong.\n- Ask for no other text. Check the spelling in the result; for small or dense text, try a higher `quality`.\n\n## Edits and references\n\n- Say \"change only …\", then list what must stay: identity, pose, geometry, label, lighting, colors, camera angle, background.\n- Number the inputs and give each a role: \"Image 1 is the person, image 2 is the jacket; dress the person in the jacket.\"\n- One change per run; feed the result into the next edit and repeat what must be preserved.\n\n## Examples\n\n> A photorealistic candid photo of an elderly fisherman mending a net on a small wooden boat at dawn. Weathered skin with visible texture, a faded blue wool sweater. Medium close-up at eye level, 50 mm lens, soft low sun from the right, light film grain, no heavy retouching.\n\n> Change only the background of image 1 to a sunlit white studio sweep. Keep the sneaker's shape, colors, laces and logo exactly, and keep the camera angle and shadows under the shoe.\n\n> A minimal flat logo for a coffee cart named \"Little Bean\": a single coffee bean with a leaf, clean vector shapes, strong silhouette, two colors (espresso brown and cream), balanced negative space, no other text.\n"
}