Midnight Ghost Client · সর্বজনীন Open Skill

Midnight Ghost Client

Midnight Ghost Client Digen-এ একটি সর্বজনীন Open Skill। খুলে দেখুন এই ওয়ার্কফ্লো কী তৈরি করে।

@NateSullivan

Story

0 0 1

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284959/2026-10-17/ukj6ummt.gif

# Midnight Ghost Client

Midnight strikes, the hands spin backward twelve times, and the empty chair is no longer empty. A polite little ghost in a waistcoat tips its hat and slides over a candy as your fee.

## When to use

- The user wants a spooky-cute fortune-teller video where a clock strikes midnight and a polite ghost in a waistcoat appears across the table and pays them in candy (midnight ghost visitor clip, fortune-teller ghost client video)
- Another take with a different length or orientation

Not for: Still images only.

## 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 |
| Duration | No | `6 s` | 6 s (default), or 10 s |
| Mood | No | `amused and mysterious` | amused and mysterious (default), startled then charmed, deadpan, or user-described |
| Orientation | No | `9:16` 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.
- Video does not allow NSFW content: keep wardrobe fully covering and refuse sexual requests. Suggestive fashion looks stay as still images.

## Steps

1. Read `references/video-motion.md`.
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. **Keyframe**: `generate_image(prompt=<KEYFRAME>, input_urls=[photo], model='i2i.hd', orientation='portrait', aspect_ratio='9:16', name='Midnight Ghost Client keyframe', entity_type='work_in_progress')`. If the face drifts, regenerate once.
4. **Video**: `generate_video(prompt=<MOTION>, input_urls=[keyframe], model='i2v', orientation='portrait', aspect_ratio='9:16', duration=<d>, name='Midnight Ghost Client', entity_type='final_videos')`. Pass only the keyframe, never the original upload.
5. Reply in one or two sentences, e.g. "Done! Here's your midnight ghost client. I can also try 10 s if you like." Results appear on the canvas; never paste URLs.

## Prompt templates

**KEYFRAME**

```text
The same adult from the reference: <identity line>. Same face structure, eyes, skin tone and recognizable likeness; no beautification or face reshaping. Opening frame of this scene: the same adult sits as a fortune-teller at a velvet-draped table in a candlelit parlor; a moon-faced wall clock strikes midnight and its hands spin backward, the shadow on the empty chair opposite gathers into a polite translucent ghost in a tiny waistcoat and top hat, it doffs its hat in greeting and slides a wrapped candy across the table, the person raises an amused eyebrow and accepts it; warm candlelight, deep plum shadows, faint blue ghost glow, fully clothed in a fringed fortune-teller shawl. Posed for motion, clear subject, cinematic light. Nothing from the original photo's background remains.
```

**MOTION** (motion only; the frame already shows the look)

```text
Starting from this exact frame: <one clear motion arc for this concept: the same adult sits as a fortune-teller at a velvet-draped table in a candlelit parlor; a moon-faced wall clock strikes midnight and its hands spin backward, the shadow on the empty chair opposite gathers into a polite translucent ghost in a tiny waistcoat and top hat, it doffs its hat in greeting and slides a wrapped candy across the table, the person raises an amused eyebrow and accepts it; warm candlelight, deep plum shadows, faint blue ghost glow, fully clothed in a fringed fortune-teller shawl>, beginning, peak and settle in one continuous shot. Camera: <one move: slow push-in, gentle orbit, or static>. The same face and outfit throughout. Cinematic, no text.
```

## Failure handling

- `success=false`: say