← PikaCONTENT HISTORYWHAT CHANGED · RULE-BASED ANALYSIS
Update to Pika
Snapshot Oct 10, 2026 · 06:12 UTC · version 0.5.3
Collection source: downloaded plugin package.
First saved snapshot
No earlier snapshot is available to establish a change.
Compare saved observations
Download comparison JSONFull technical diff · 0 changed fields
Full snapshot data
{
"description": "Use when writing or improving the prompt for a Pika image run — create, edit or restyle an image — before running it, whatever the model.",
"included_files": [],
"name": "prompt-image",
"skill_md_contents": "---\nname: prompt-image\ndescription: Use when writing or improving the prompt for a Pika image run — create, edit or restyle an image — before running it, whatever the model.\n---\n\n# Image prompts\n\n## In Pika\n\n- The prompt goes in the tool's `prompt` field (`instructions` in `edit_image`). A template or preset field may replace it; send one or the other.\n- Check the model: `create_image` and `edit_image` take a `model`. For `gpt-image-2` also apply `prompt-gpt-image`; for Nano Banana (`nano-banana`, the default, and its variants) apply `prompt-nano-banana`.\n- Keep the user's intent and words. Expand a described look into concrete visual detail; don't swap in a different idea.\n\n## Structure\n\n1. **Result and use** — what the image is for: product shot, poster, profile photo, thumbnail, illustration.\n2. **Subject** — who or what, pose, expression, clothing, materials.\n3. **Composition** — framing (close-up, full body, overhead flat lay), subject placement, background.\n4. **Light** — source, direction, softness, time of day.\n5. **Style** — photo (lens, depth of field, film stock) or medium (watercolor, 3D render, flat vector, anime), plus a color palette.\n6. **Text**, if any — exact words in quotes, where they sit, and the lettering style.\n\nUse plain descriptive sentences. For a busy scene, short labeled lines (Scene, Subject, Details, Text) stay readable.\n\n## Edits\n\n- Say what changes and list what stays: face, pose, product shape, label, background, lighting, camera angle.\n- One change per run. Feed the result into the next edit for the next change.\n- With several input images, give each a role: \"the person from the first image, the jacket from the second\".\n\n## Leave out\n\n- Empty praise (\"beautiful, stunning, masterpiece, 8K\").\n- Negative lists. Describe the wanted result (\"clean white background\") rather than what to avoid.\n- Style stacks that contradict each other (\"photorealistic watercolor anime\").\n\n## Example\n\n> Product photo for an online store: a matte black water bottle standing on pale travertine, centered, shot from slightly above at a 3/4 angle. Soft daylight from the left with a gentle shadow to the right. Shallow depth of field, neutral warm palette; the bottle is the only object in frame.\n"
}SHA-256 of public snapshot: b95d799aa01f8ceac20b56e6f6e0aeb39fde08f0ea85700b3a9b470234041e5f