Halloween Bus Window · публичный навык Open Skill

Halloween Bus Window

Q: Ask: Why did the bus miss the last stop? A: Get: I make a Halloween photo of you leaning out of a pumpkin-and-bat-covered bus window. “Happy Halloween” in bold. Q: Ask: What photo and details should I send? A: Get: Send one clear adult photo. Add a description for the scene, decorations, or greeting. Q: Ask: What size is the finished photo? A: Get: It comes out as a 3:4 portrait. A visible face works best for the bus window pose.

@MayaCalloway

Poster

0 0 0

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/550336/2026-10-15/hg3e5sg4.webp

# Halloween Bus Window

Arms wide, leaning out of a bus covered in pumpkins and bats, with 'Happy Halloween' in bold letters.

## When to use

- The user wants a festive Halloween photo of themselves leaning out of a decorated bus window with a Happy Halloween greeting
- A variation on a previous result: a different layout

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 |
| Description | No | tuned default below | What the user wants; merged into the prompt |
| Orientation | No | `3:4` portrait | Other ratios 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='portrait', aspect_ratio='3:4', name='Halloween Bus Window', 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 halloween bus window is on the canvas. Next I can do a different layout." 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 festive Halloween photo: the person leaning out of a decorated bus window with arms spread wide, pumpkins, bats and orange lights on the bus, bold 'Happy Halloween' lettering. <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 "this one" with a photo. Use the tuned defaults, 3:4. Reply: "All set. Your halloween bus window is on the canvas."
**Variation**: "next variation". Keep the same inputs and change one option (a different layout).
**Missing input**: no photo was sent. Ask: "Drop in one photo of yourself (face clearly visible) to get started."

## References

- `references/image-edit.md`