halloween-blindbox

Verified@lengkeman0802/halloween-blindbox
Use it in Cohub

Paste this into your agent's chat — it fetches the skill and follows it.

Use the skill: halloween-blindbox. Run `npx -y @neta-art/neta-search-cli@latest skills use @lengkeman0802/halloween-blindbox --via site` and follow what it prints. Read its complete output, redirecting it to a temporary file first if necessary, and resolve relative paths from the skill directory it prints.
Use in Neta Studio Open it in Neta Studio and see what people made with it.
Install from a terminal
npx -y @neta-art/neta-search-cli@latest skills use @lengkeman0802/halloween-blindbox
Summary

Turn your character into a collectible Halloween blind-box figure card.

  • Makes one image: a chibi version of your character as a glossy vinyl figure inside a windowed blind-box.
  • Comes as a trading-card style image with a box label, a serial number, and a colored card border.
  • Keeps your character recognizable: same hair, eye color, and one signature accessory from your reference.
  • Works best with a character who has a clear look and at least one standout accessory or feature.
  • Delivered instantly as one finished image on your canvas, ready to use or collect.
SKILL.md
# Halloween Blind Box Card

Turn a character into a **chibi collectible figure inside a Halloween blind box**, framed
as a trading card. One image, one pass, no iteration, **no questions**.

## Language

**Always answer in English**, whatever language the user writes in. Card titles, box labels
and every piece of text inside the image are English only. No Chinese characters anywhere.

## Flow

1. **Never ask a question.** Take the character from whatever is available: an uploaded
   image, a character description, or a name in the user's world. If nothing is given,
   invent one adult character and state it in one line.
2. Variant: use the one the user named; if none, default to `pumpkin witch`.
3. Build **one** prompt (template below) and generate **one** image.
4. Deliver the card with one line of copy.

## Prompt template (English)

> Product photo of a Halloween blind-box collectible: a chibi [character] as a
> [variant], roughly 2.5 heads tall, glossy vinyl figure, standing inside an open
> windowed box, box front shows a small `HALLOWEEN BLIND BOX` label and a pumpkin mark.
> Soft studio lighting, warm key from upper right, deep purple backdrop, gentle rim light,
> shallow depth of field, clean product-photography look, no text besides the box label,
> no watermark, no gore.

Composition: box occupies the lower 2/3, card frame border in burnt orange, small
`No.<n>` serial at the top-right corner.

Keep the prompt under 100 words.

## Output contract

- One image, 3:4 portrait (card ratio).
- The character must be recognisable: keep hair colour, hair length, eye colour and one
  signature accessory from the reference.
- Deliver as an image work titled `Halloween Blind Box · <character>`.

## Cost guard

One generation call per turn. Do not generate a set of variants unless asked.
Target: **≤ 1 image per request**.

## Do not

- Do not draw the figure shorter than 2 heads or taller than 3 heads.
- Do not add blood, weapons, or sexualised poses.
- Do not place children characters in the box.
Related skills
pixel-roomVerifiedType one line and get a pixel-art, two-storey cutaway room, like a tiny dollhouse you can look into.