Clothes 2 · skill publik Open Skill

Clothes 2

Clothes 2

@Promise

Health

2 0 11

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/3949831/2026-10-16/3tmty7d7.jpg

# Clothes 2 — Single-Outfit Clothing Swap

This skill does **one job only**: put the **preset Halloween orange-and-black costume lingerie set** onto the **user’s subject photo**, with a natural, well-proportioned fit. Do not change identity, face, hairstyle, pose, camera angle, or background unless the user explicitly asks for something outside clothing replacement (in that case, decline or clarify that this skill is clothing-only).

## When to use

- User uploads (or points to) a photo of a person and wants them dressed in **this skill’s fixed outfit**.
- User asks to “change clothes,” “try on this costume,” or “wear the preset outfit” for their character/person photo.
- User wants to regenerate with a different image model (`i2i.hd.lite`, `i2i.hd`, or `i2i.hd.gpt`) for the same try-on.

**Out of scope (politely decline or redirect):** arbitrary other garments, full body reshaping, nudity/NSFW requests, background replacement, multiple outfits in one run, video, or any task that is not this specific outfit swap.

## Preset outfit reference (admin asset)

After `read_skill`, inspect **`preset_assets`** for the outfit flat-lay reference:

| Key | Label | Role |
|-----|-------|------|
| `outfit_reference` | Halloween orange-black costume set | **Second** image in `generate_image` `input_urls` — defines colors, panels, zigzag seams, and accessories |

- Prefer passing the preset entry’s **`uri`**, **`asset_id`**, or **`key`** (`outfit_reference`); the platform resolves and presigns it.
- If `outfit_reference` is **missing**, tell the user the preset asset is not bound yet; they may attach the same flat-lay reference image in chat for this session only, and use that URL/`asset_id` as the outfit reference instead.

Do **not** embed binary images inside the skill zip; the flat-lay lives only in preset assets (or user attachment as fallback).

## Outfit specification (use in every generation prompt)

Summarize the following in the **`generate_image` `prompt`** (English). For full wording, call `read_skill_file(name='clothes-2', path='references/outfit_spec.md')` once before the first generation.

**Set:** four coordinated pieces — triangle halter top, string bikini bottom, fingerless arm warmers, oversized bow on a thin black band (headband/choker).

**Materials & palette:** high-gloss **bright orange satin** vs **matte black** fabric; sharp geometric color blocks; playful Halloween “cute bat / succubus” costume aesthetic.

**Top:** triangle cups in orange satin with thick black borders; two small black bat-wing cutouts at the inner lower cup edges meeting at the sternum; thin black halter neck tie and back tie.

**Bottom:** low-rise string bikini, V-cut front; upper panel solid black with a small centered diamond cutout; lower panel orange satin; **jagged zigzag** boundary between black and orange (stylized mouth / bat-wing line); two small upright black “horn” points at the front waistband; thin black side strings.

**Arm warmers:** long fingerless sleeves, black from elbow downward transition via **dramatic zigzag** to orange satin at the wrists; slight gather at wrists; thin black tie strings at the upper opening.

**Bow accessory:** large bow on a thin black ribbon/band — black upper loops, wide flared **orange satin** tails.

**Fit intent:** costume sits on the subject’s existing body naturally; proportions look believable (no extreme hourglass morph unless already in the source photo); straps and ties follow anatomy; satin highlights consistent with the reference.

## Workflow

1. **Subject photo** — User must supply one clear photo of the person (full-body or three-quarter preferred). If unclear, use `recognize_image` to confirm a visible person and note framing; ask for a better upload only if no person is detectable.
2. **Orientation** — Match the subject photo: infer landscape / portrait / square from the upload; pass the same `orientation` to `generate_image` unless the user explicitly requests otherwise.
3. **Model choic