Sushi Atlas Board · skill pubblica Open Skill

Sushi Atlas Board

I caught the beat drop by a crosswalk and wanted the map to feel just as playful. I like making a country from sushi on a wooden board, with a tiny edible landmark on top. **tips from me:** - write a short description of the scene you want - add a country map or landmark photo if you have one - keep the default 3:4 portrait ratio for posters - ask for 1:1 or 4:3 when the board needs a different shape post what you make, I want to see the country you pick.

@AvaLindqvist

Poster

0 0 2

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284954/2026-10-16/pk8dmb45.webp

# Sushi Atlas Board

A delicious geography. Pick a country and get a photoreal wooden board where sushi and sashimi form its map, topped with a tiny edible landmark.

## When to use

- The user wants a country map made of sushi on a wooden board (sushi geography poster, edible map with a landmark)
- A variation on a previous result: 1:1

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

## Inputs and gates

| Input | Required | Default | Gate |
|---|---|---|---|
| Person photo | No | — | Optional; if given, the face is preserved |
| Country Map | No | — | map image of the country |
| Landmark | No | — | photo of a landmark to feature |
| Description | Yes | — | What the user wants; merged into the prompt |
| Ratio | No | `3:4 default` | 3:4 default; 1:1, 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. Fill the template below from the user's description. Use the tuned defaults for anything they leave out; ask one short question only if the subject itself is unclear.
3. If a person photo is given: `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.')` and add the identity clause.
4. With reference images: `generate_image(prompt=<PROMPT>, input_urls=[refs...], model='i2i.hd', orientation='portrait', aspect_ratio='3:4', name='Sushi Atlas Board', entity_type='skill_generation')`; without: the same call with `model='t2i.hd'` and no `input_urls`.
5. **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.
6. Reply in one or two sentences, e.g. "Done! Here's your sushi atlas board. I can also try 1:1 if you like." Results appear on the canvas; never paste URLs.

## Prompt templates

**PROMPT**

```text
<if photo: The same adult from the reference: <identity line>.> Intentional changes: a photorealistic top-down shot of a wooden serving board where sushi rice, sashimi and garnishes are arranged into the exact outline of <country>, regions picked out in different fish and garnish colors, a tiny edible model of <landmark> placed on top, soy sauce, wasabi and pickled ginger beside the board, bold headline with the country name. <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 portrait 3:4. 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 "use this pic". Use ratio `3:4 default`, 3:4. Reply: "Done! Here's your sushi atlas board."
**Variation**: "one more please". Keep the same inputs and change one option (1:1).
**Thin request**: the user gives one word. Fill the brief from the tuned defaults and generate; do not interrogate.

## References

- `references/image-edit.md`