Spooky Town ID Card · Open Skill 公開スキル
Spooky Town ID Card
Hot pink lip gloss, then a quick change into Spooky Town. That candy-color shift is why I like this one. I put an adult photo into a job costume and make a 3:4 collectible ID card. It sits on a candlelit table beside a glowing jack-o'-lantern. **floor notes:** **tips from me:** - upload one clear photo of an adult, with the face visible - choose a job like witch, potion seller, or candy baker - add the resident name you want on the card - describe the scene or costume details you want Post the Spooky Town ID card you make. I want to see your quick change.
Roleplay
0 0 0
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284952/2026-10-16/ezt2y4vm.webp
# Spooky Town ID Card Become a resident of Spooky Town. Your face appears on an official collectible ID card in a job costume, photographed on a candlelit table beside a glowing jack-o'-lantern. ## When to use - The user wants a Spooky Town resident ID card from their photo (Halloween ID badge, job costume ID on a candlelit table) - A variation on a previous result: Witch 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 | | Description | No | tuned default below | What the user wants; merged into the prompt | | Job | No | `Gravedigger` | Gravedigger, Witch, Lantern Keeper, Potion Seller, Pumpkin Farmer, Bat Keeper, Clock Tower Guard, Candy Baker, or user-described | | Resident name | No | `user-provided name` | user-provided name | | 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='Spooky Town ID Card', 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 spooky town id card is on the canvas. Next I can do Witch." 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: an official Spooky Town Resident ID card photographed as a real collectible lying on a candlelit wooden table next to a glowing jack-o'-lantern: the card shows the same adult person's face in a <job> Halloween costume with a brass occupation seal and playful Mischief/Courage/Luck stats, resident name <name>. <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 job `Gravedigger`, resident name `user-provided name`, 3:4. Reply: "All set. Your spooky town id card is on the canvas." **Variation**: "next variation". Keep the same inputs and change one option (Witch). **Missing input**: no photo was sent.