Basement Pumpkin Carving · skill pública Open Skill

Basement Pumpkin Carving

Q: Ask for a moody Halloween basement scene. A: Get torchlight, stone walls, and two costumed adult friends carving jack-o'-lanterns in an old cellar. Film grain included. Q: Ask for a different cast. A: Get the characters changed through the description while keeping the atmospheric basement setup. Q: Ask what comes out. A: Get a 3:4 portrait. I keep the description short, specific, and after-hours.

@MayaCalloway

Story

0 0 0

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/550336/2026-10-15/pp5tyh3d.webp

# Basement Pumpkin Carving

Torchlight, stone walls and two costumed friends carving jack-o'-lanterns in an old cellar.

## When to use

- The user wants an atmospheric Halloween scene of costumed characters carving pumpkins in an old basement

Not for: Editing an existing photo (use an image-edit skill).

## Inputs and gates

| Input | Required | Default | Gate |
|---|---|---|---|
| Description | No | tuned default below | What the user wants; merged into the prompt |
| Orientation | No | `3:4` portrait | Other ratios on request |

- Fashion, dark and horror themes are fine as stills; refuse explicit sexual content and anything sexualizing minors.

## Steps

1. Expand the user's idea into the brief below. If they gave almost nothing, use the tuned defaults instead of asking.
2. `generate_image(prompt=<PROMPT>, model='t2i.hd', orientation='portrait', aspect_ratio='3:4', name='Basement Pumpkin Carving', entity_type='skill_generation')`.
3. **Self-check, one retry**: if the composition is cluttered or off-brief, regenerate once with a simpler subject and clearer light.
4. Reply in one or two sentences, e.g. "All set. Your basement pumpkin carving is on the canvas. Next I can do a different light or setting." Results appear on the canvas; never paste URLs.

## Prompt templates

**PROMPT**

```text
Subject: <who/what>. Action: <what they do>. Location: <where>. Composition: <shot size, angle, lens>. Style: an atmospheric Halloween scene: two costumed characters carving pumpkins in an old stone basement lit by torchlight, cobwebs, warm flickering light. <user details>. Light: <key light, mood>. No text, no logos.
```

## Failure handling

- `success=false`: say what failed in one sentence; retry once only if transient; never invent links.

## Examples

**Default**: the user says "this one". Use the tuned defaults, 3:4. Reply: "All set. Your basement pumpkin carving is on the canvas."
**Variation**: "next variation". Keep the same inputs and change one option (a different light or setting).
**Thin request**: the user gives one word. Fill the brief from the tuned defaults and generate; do not interrogate.