Halloween Monster Collab · skill Open Skill công khai

Halloween Monster Collab

I like that this one turns an uploaded adult photo into a Halloween portrait with a friendly monster buddy. Costume on, monster buddy in. The candy gloss mood stays playful while the moonlight gets a little spooky. **floor notes:** - upload one adult photo with a clear face, and only use a picture you have the right to use - pick a friendly werewolf, or choose frankenstein giant, classic vampire, or cheerful mummy - start with the witch costume, or keep your own halloween look - choose a 3:4, 2:3, or 9:16 ratio, and add any details you want post what you make.

@SiennaBrooks

Meme

4 1 3

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284952/2026-10-18/dbka7qpf.webp

# Halloween Monster Collab

Costume on, monster buddy in. Your portrait becomes a Halloween look posed naturally next to a friendly monster under moonlight and jack-o'-lantern glow.

## When to use

- The user wants a Halloween collab portrait of themselves in costume posing with a friendly monster buddy (halloween monster buddy photo, witch and werewolf selfie, halloween creature collab)
- A variation on a previous result: frankenstein giant

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

## Inputs and gates

| Input | Required | Default | Gate |
|---|---|---|---|
| Photo | Yes | — | One adult, face clear. Ask for another photo if the face is tiny, blurred or hidden |
| Description | No | tuned default below | What the user wants; merged into the prompt |
| Monster | No | `friendly werewolf` | friendly werewolf (default), frankenstein giant, classic vampire, cheerful mummy, or user-described |
| Costume vibe | No | `witch` | witch (default), vampire host, pumpkin royalty, or keep user's halloween look |
| Ratio | No | `3:4 default` | 3:4 default; 2:3, 9:16 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 Monster Collab', 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 monster collab is on the canvas. Next I can do frankenstein giant." 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: the same adult dressed in a festive Halloween costume posing side-by-side with <monster: a friendly werewolf (default), frankenstein giant, classic vampire, or cheerful mummy> who mirrors a playful peace-sign pose, night forest or graveyard with a full moon and glowing jack-o'-lanterns, warm orange lantern light and cool moonlight, photoreal composite, fully clothed, adults only. <user details and options>. Apply the style to the entire frame with its signature traits (medium, texture, palette, linework); the person stays recognizable under the style. 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: Name the style's visual traits (medium, brushwork or render, palette, line quality) and apply them to the whole frame; keep the face's likeness readable under the style.

## 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 monster `friendly werewolf`, costume vibe `witch`, 3:4. Reply: "All set. Your halloween