Halloween Bus Portrait · Open Skill 공개 스킬
Halloween Bus Portrait
Halloween Bus Portrait은 Digen의 공개 Open Skill입니다. 열어 보면 이 워크플로가 무엇을 만드는지 알 수 있습니다.
Custom
1 0 0
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4173183/2026-10-15/63k37r7q.jpg
# Halloween Bus Portrait Create **one** family-friendly **Halloween bus portrait** per request: the subject **leans out of a decorated vintage bus window** with **both arms spread wide**, opening the composition around their hands, with **bold glowing greeting text** between the hands. They wear an **elaborate Halloween costume**. **Inside the bus**, passengers dressed as **Halloween ghosts** are visible through the windows. **Outside**, a festive environment with **carved pumpkins**, **twisted bare trees**, **drifting fog**, and **orange-purple moonlight**. Style: **highly detailed editorial photography**, sharp focus, natural skin tones, coherent anatomy, clean composition, no distortion. **Text-to-image** builds a **wholly original fictional subject** in costume when the user has no image or taps **direct generate**. **Image-to-image** transforms an **uploaded front-facing portrait** while **preserving face and identity**. Visual lock and greeting text rules live in `references/halloween_bus_portrait_spec.md`. No project state. **Language lock:** This file and all of `references/` are **English only**. Reply in the **user's language**. Every `generate_image` `prompt` is **English**. The **greeting text rendered in the artwork** uses **Happy Halloween** in English by default; when the user's language is not English, use the standard festive equivalent in that language unless they asked for English on the image. Do not tell the user tool names, channel names, or dump the full style prompt. ## User-visible speech (hard) **Allowed lines only:** - Need input: one short note that they may **upload a front-facing portrait**, **describe changes**, or **tap direct generate** — then pause **P-empty** or **P-brief**. - Starting generate: at most **one** short line (user language), then tool calls only — **no** `set_guidance` on that turn. - Success: one or two sentences that the **Halloween bus portrait** is ready — no URL, no prompt dump. Pause **P-done**. - Tool failure: brief honest note. Pause **P-fail**. - Safety block: 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. Localize `text` and `content` to 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 image to refine | Direct generate now · Describe my scene · I'll upload a portrait | | P-brief | Text too vague (no portrait or Halloween cues) | Example brief (`fill_input`) · Direct generate default (`send_message`) | | P-refuse | NSFW goal, sexualized minor, gore focus, hate target, non-consensual humiliation | Family-safe direct generate · Upload a different portrait | | P-fail | `generate_image` `success=false` after retry | Direct generate again · Regenerate from same upload · Higher quality | | P-done | One portrait ready | Brighter moonlight · New costume vibe · Localized greeting on image · Direct generate fresh scene | ## When to use - User wants a **Halloween bus window portrait** with **festive decorations**, **ghost passengers**, and **greeting text between spread arms**. - User has **no image** or taps **direct generate** / **generate without upload** — run **text-to-image** immediately with the default in `references/guidance-buttons.m