Halloween Portrait · Open Skill 公開技能
Halloween Portrait
Halloween Portrait 是 Digen 上的公開 Open Skill。開啟後即可了解此工作流能製作什麼。
Custom
0 0 0
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4173183/2026-10-15/qncz3qed.jpg
# Halloween Portrait Create **one** family-friendly **festive Halloween portrait** per request: **dramatic spooky atmosphere**, **moody low-key lighting**, **warm candlelight** against **deep cool shadows**, **subtle orange and purple accent tones**, **atmospheric mist**, and **jack-o'-lantern glow** in the background. Finish with **rich cinematic color grading**, **crisp facial detail**, and **natural skin rendering** — a **high-quality portrait** look. **Text-to-image** builds a **wholly original fictional subject** in the same Halloween portrait treatment when the user has no image or taps **direct generate**. **Image-to-image** applies the look to an **uploaded portrait** while **preserving the subject's face and identity**. Visual lock and prompt rules live in `references/halloween_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**. 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 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 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 portrait · I'll upload a photo | | P-brief | Text too vague (no portrait or mood 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 | More mist and pumpkins · Warmer candlelight · Portrait / landscape · Direct generate fresh portrait | ## When to use - User wants a **festive Halloween portrait** with **cinematic spooky lighting**, **seasonal color**, and **jack-o'-lantern atmosphere**. - User has **no image** or taps **direct generate** / **generate without upload** — run **text-to-image** immediately with the default in `references/guidance-buttons.md` unless they already gave a different brief in the same message. - User uploads a **portrait photo** for a **face-preserving Halloween transform**. - User asks to **retry**, change **orientation**, **lighting warmth**, **mist density**, **orange/purple balance**, or **costume/props** while keeping the festive Halloween portrait mood. **Do not use:** unrelated non-portrait genres, graphic gore focus, or video (this skill is **one still image** per default request)