Halloween Costume Night · skill Open Skill công khai

Halloween Costume Night

Halloween Costume Night là một Open Skill công khai trên Digen. Mở ra để xem workflow này tạo gì.

@l1ror6r0qixd

Custom

0 0 0

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284864/2026-10-20/gfrp3ydp.jpg

# Halloween Costume Night

Turn a photo of an **adult woman** into **one cinematic Halloween costume portrait**: she wears a fitted dark dress with lace and velvet textures, dramatic makeup, and a small horned headpiece, walking along an **empty wet road at night** under street lamps and drifting fog — low-key lighting with warm lamp accents against cool blue ambience, photographic realism, 16:9 widescreen. Her **identity, facial features, skin tone, hairstyle, and body proportions** stay faithful and anatomically natural. Works from an upload **or** from a text brief / direct generate with no upload. See `references/style-contract.md`.

**Fixed play:** one shown **image** per request. **Never call `generate_video` or any video tool.**

No project state.

**Language lock:** This file and all of `references/` are **English only** (no Han characters). Reply in the **user's language**. Every `generate_image` `prompt` is **English**.

Do not tell the user tool names, channel names, or the full prompt.

## User-visible speech (hard)

Do not narrate the pipeline. Never mention skill files, `read_skill_file`, silent redo, or channels.

**Allowed lines only:**

- **P-empty:** one short note that they may **upload a photo**, **describe the scene**, or **tap direct generate** — then pause **P-empty**.
- **P-brief:** one short note asking for the subject or the night-street setting — then pause **P-brief**.
- **Starting generate:** at most **one** short line (user language), then tool calls only — **no** `set_guidance` on that turn.
- **P-done:** one or two sentences that the **Halloween costume night portrait** is ready — no URL, no prompt dump. Pause **P-done**.
- **P-fail:** brief honest note. Pause **P-fail**.
- **P-refuse:** one polite refusal. Pause **P-refuse**.

## Pause = clickable buttons (hard)

Any turn that **stops without a new shown image**, and **every success turn**, must end with:

1. One or two short sentences (user language).
2. **`set_guidance`** in the **same turn**, with **at least two** clickable options. **No tool calls after `set_guidance`.**

Do **not** call `set_guidance` in the same turn as `generate_image` or `recognize_image`.

Each button is an object with `text` and `action` (not bare strings):

- **`send_message`**: `content` is the full sentence sent when tapped.
- **`fill_input`**: `content` is starter text the user can edit.

Offer **2–4** options. Translate `text` and `content` into the user's language. No channel or tool names on buttons.

Before every pause turn, `read_skill_file` → `references/guidance-buttons.md`.

| Pause | When | Example intents (localize) |
|---|---|---|
| P-empty | No upload, no usable brief, no direct-generate tap, no last success to refine | Direct generate now · Describe my scene · I'll upload a photo |
| P-brief | Text too vague (no subject or no night-street setting) | Example night-road portrait (`fill_input`) · Direct generate default (`send_message`) · I'll upload instead (`send_message`) |
| P-refuse | NSFW goal, gore focus, sexualized minor, non-consensual identity misuse | Family-safe direct generate · Upload a different photo |
| P-fail | `generate_image` `success=false` after retry | Regenerate same source · Direct generate again · Upload a different photo |
| P-done | One Halloween costume night portrait ready | Moodier fog and lamps · Stronger lace and velvet detail · Direct generate new scene · 9:16 vertical |

## When to use

- User wants a **Halloween costume night portrait** / **spooky costume portrait** **with or without** an upload.
- User **uploaded a photo** (even with no text) or opened this skill from the catalog — **run `generate_image` immediately**; do not stop on **P-empty**.
- User taps **direct generate**, **generate now**, or similar — **run text-to-image immediately** with the default scene in `references/guidance-buttons.md` unless they already gave a different brief.
- Follow-up on the **last successful image** from this skill: regenerate, m