Cookie Cutter Die-Cut · skill pubblica Open Skill

Cookie Cutter Die-Cut

Cookie Cutter Die-Cut è una Open Skill pubblica su Digen. Aprila per vedere cosa crea questo workflow.

@HarperDiaz

Product

0 0 0

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284956/2026-10-16/ukw3sxqj.webp

# Cookie Cutter Die-Cut

Bake your silhouette. Your photo's outline becomes a shiny metal cookie cutter beside a flour-dusted dough piece cut to the same shape, shot top-down on a soft-lit table.

## When to use

- The user wants their photo turned into a metal cookie-cutter and matching dough cutout (baking silhouette, cookie cutter of me)
- A variation on a previous result: 3:4

Not for: Video output (use a video skill).

## Inputs and gates

| Input | Required | Default | Gate |
|---|---|---|---|
| Photo | Yes | — | One adult with the face clearly visible. Ask for another photo if the face is tiny, blurred, heavily covered or in profile |
| Ratio | No | `1:1 default` | 1:1 default; 3:4, 4:3 on request |

- If the person may be under 18, stop and decline politely. Real-person photos must be of adults the user has the right to use.
- Fashion, dark and horror themes are fine as stills; refuse explicit sexual content and anything sexualizing minors.

## Steps

1. Read `references/image-edit.md` for prompt structure.
2. **Identity read**: `recognize_image(image_url=<photo>, prompt='Describe this adult for identity preservation: face shape, eye shape and color, brows, nose, lips, skin tone, apparent age range, hair color and length, distinctive marks, glasses. One compact line.')`.
3. **Generate**: `generate_image(prompt=<PROMPT>, input_urls=[photo], model='i2i.hd', orientation='square', aspect_ratio='1:1', name='Cookie Cutter Die-Cut', entity_type='skill_generation')`. Merge the user's details and options into the template.
4. **Self-check, one retry**: look at the result. If a person photo was used and the face no longer reads as the same person, regenerate with the identity clause first. If someone glancing at it would not instantly see the intended change (it reads as a light filter, the old clothes or background remain, or the style is faint), regenerate once with the change described bigger and more concretely.
5. Reply in one or two sentences, e.g. "All set. Your cookie cutter die-cut is on the canvas. Next I can do 3:4." Results appear on the canvas; never paste URLs.

## Prompt templates

**PROMPT**

```text
The same adult from the reference: <identity line>. Same face structure, eyes, skin tone and recognizable likeness; no beautification or face reshaping. Intentional changes: a 1:1 top-down tabletop photo: a polished metal cookie cutter whose closed outline matches the simplified silhouette of the uploaded subject, placed beside a pale raw dough piece cut to the exact same shape, soft flour dust on a rustic wooden board, gentle bakery lighting, identifying features compressed into one clean contour. <user details and options>. Clear focal hierarchy; any text short, in quotes and spelled exactly; no real brands. Lighting and materials described concretely; composition suited to square 1:1. Photoreal unless the style says otherwise, fully clothed, no text unless requested.
```

Quality bar: Keep on-image text short and in quotes; no real brand names or logos; one clear focal hierarchy.

## Failure handling

- `success=false`: say what failed in one sentence; retry once only if transient; never invent links.
- The face changes: regenerate once with the identity clause first; then say so honestly.

## Examples

**Default**: the user says "this one" with a photo. Use ratio `1:1 default`, 1:1. Reply: "All set. Your cookie cutter die-cut is on the canvas."
**Variation**: "next variation". Keep the same inputs and change one option (3:4).
**Missing input**: no photo was sent. Ask: "Drop in one photo of yourself (face clearly visible) to get started."

## References

- `references/image-edit.md`