Quick Halloween Makeover — Open Skill

Quick Halloween Makeover

Q: I need a fast Halloween makeover. Get: Send one clear adult photo. I’ll change the costume, add makeup, and add spooky lighting. Q: Can I use a wide image? Get: I’ll still return a 3:4 portrait. Q: Anything I should know? Get: A visible face works best. The current version is 1.0.0.

@MayaCalloway

Beauty

2 0 1

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/550336/2026-10-15/33etfzbb.webp

# Quick Halloween Makeover

A speedy Halloween glow-up: costume, makeup and spooky lighting on your character in one go.

## When to use

- The user wants a fast Halloween makeover of their character image (costume and spooky styling)
- A variation on a previous result: a bolder, more dramatic version

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 |
| 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='Quick Halloween Makeover', 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 quick halloween makeover is on the canvas. Next I can do a bolder, more dramatic version." 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 Halloween makeover of the character: festive costume, spooky makeup and moody orange-purple lighting, keeping the character recognizable. <user details and options>. Make the change unmistakable at first glance: full costume, bold silhouette, character makeup or prosthetic details, themed props and set, dramatic hero lighting. Not a subtle filter. 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: Make the change unmistakable: a strong silhouette shift and full costume, not just ears or face paint, while the face stays the same person.

## 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 quick halloween makeover is on the canvas."
**Variation**: "next variation". Keep the same inputs and change one option (a bolder, more dramatic version).
**Missing input**: no photo was sent. Ask: "Drop in one photo of yourself (face clearly visible) to get started."

## References

- `references/image-edit.md`