Kouzui-HUANG

Elite Animated Film Storyboard Director & AI Cinematography Expert. Translates user-provided visual materials (character sheets, scene designs) and textual instructions into highly descriptive, professional English text-to-image AI prompts optimized for storyboard sequences. Use this skill when the user mentions "分鏡設計", "分鏡建議", "storyboard", "storyboard design", "shot breakdown", or wants to convert a script/plot into a sequence of cinematic AI image prompts.

中文简介正在准备中。当前显示原文说明。

Translates physical toys/figures into breathtaking, cinematic, hyper-realistic image prompts. Use this skill when the user wants to generate high-end AI image prompts (like Midjourney) for toys or action figures, elevating them with dynamic posing, environmental storytelling, and professional garage-kit painting techniques.

中文简介正在准备中。当前显示原文说明。

Chief Voice & Auditory Experience Designer. Generates 3 highly descriptive, literary, and evocative English voice design options based on abstract character settings or emotional needs. Trigger this skill when the user asks for "人聲設計", "聲線設計", "voice design", or wants to design a voice/vocal tone.

中文简介正在准备中。当前显示原文说明。

AI Short-Drama Director & Clip Prompt Architect (AI 短劇導演 × 分鏡 Clip 架構師). Acts as director + storyboard artist in one — turns a theme, logline, story, script or character/scene images into a complete AI short-drama prompt package — 導演意圖 (hook, narrative template, emotion curve, reversals), 資產清單 with locked visual anchors, a 10-column 分鏡總表 mapped to Clips, and one self-contained English YAML video prompt per 4–15 s Clip in the prompt-master-video-continuity YAML style, keeping characters, props and scenes consistent across clip-by-clip generation. Default look is gothic grotesque-cute dark fairy-tale cinema, overridable by any user-named style. Writes prompt TEXT only — never generates images or video and never calls a generation API. Use when the user mentions 「AI短劇」,「AI 短劇」,「微短劇」,「短劇提示詞」,「短劇分鏡」,「導演分鏡」,「導演模式」,「導演意圖」,「分段影片提示詞」,「Clip 提示詞」,「多段影片提示詞」,「暗黑童話」,「黑暗童話」,「哥德暗黑短片」, "AI short drama", "short drama prompt", "director mode", "multi-clip video prompt", "dark fairy tale film", or wants a story longer than one clip broken into consistent multi-clip video prompts. Do NOT trigger for — a single compact YAML video prompt 動態／動態生成／動態提示詞 (→ prompt-master-video-continuity); 文生影／t2v (→ prompt-master-text-to-video); 圖生影／i2v (→ prompt-master-image-to-video); text-to-image storyboard prompts 分鏡設計／分鏡建議 (→ storyboard-director); a Chinese 分鏡腳本 without video prompts (→ shot-script-director); writing a script only (→ screenwriter-architect); 九宮格 (→ prompt-master-9panel-grid); or actual generation with a named model such as seedance (→ seedance-2-0).

中文简介正在准备中。当前显示原文说明。

Cultural Resonance Naming Master (文化共鳴命名大師) — a screenwriting-grade naming & renaming consultant that maps a character (or any narrative entity — faction, place, weapon, project, story title) onto a global mythological archetype and forges a name carrying metaphor, foreshadowing, and historical weight. Reads a character bio / brief, locates its psychological spectrum (chaos↔order · selfish↔altruistic · active↔passive) plus its fatal flaw and likely fate, retrieves candidate archetypes from a 12-culture Global Mythology Matrix (Chinese, Japanese, Hindu, Greco-Roman, Norse, Celtic, Slavic, Abrahamic mysticism, Egyptian, Mesopotamian, Indigenous Americas, Persian), runs an adversarial test to avoid the obvious pick, then delivers each name via naming alchemy (root recombination / concept translation) with a full cultural-resonance breakdown — archetype source, mythic backstory, and mapping logic (surface link / deep resonance with the fatal flaw & fate / cultural tension). Output analysis is in Traditional Chinese. Use when the user mentions 「命名」,「改名」,「取名」,「換名字」,「換個名字」,「角色命名」,「角色取名」,「幫角色取名」,「幫我的角色命名」,「神話命名」,「有寓意的名字」,「有典故的名字」,「賦予名字意義」,「名字的隱喻」, "naming", "rename", "renaming", "name my character", "give this character a name", "meaningful name", "mythological name", "archetypal name", or wants a story character/entity named or renamed with archetypal depth. It ONLY writes naming TEXT and its cultural analysis — it never generates images or calls any generation API. Do NOT trigger for — code identifier / variable / file naming, commercial light-novel-style work-title ideation such as 書名企劃・作品名發想・片名提案 (use lightnovel-title-architect), naming a skill or repo (use skill-creator), or pure brand-slogan / product-copy work with no narrative character behind it; and note it designs the NAME, not the character's full personality/backstory (that is character-architect — pair the two when both are needed).

中文简介正在准备中。当前显示原文说明。

Chief Storyboard Director & Visual Data Architect for 3x3 nine-panel storyboard grids (九宮格). Analyzes user-provided images and optional descriptions to extract core visual features, then designs a 9-panel storyboard grid with cinematic camera variations in strict YAML format. Use this skill ONLY when the user mentions "九宮格", "9宮格", "nine-panel grid", "9-panel grid", or "3x3 storyboard grid". Do NOT trigger on generic "分鏡" or "storyboard" mentions alone—those belong to the storyboard-director skill.

中文简介正在准备中。当前显示原文说明。

Portrait Gender-Transformation Prompt Architect (性別轉換肖像提示詞). A TWO-PHASE skill. Phase 1 — on receiving a portrait it does NOT write a prompt yet: it reads the image, states the detected direction (male→female / female→male / androgynous), and asks ONE compact ABCD confirmation block covering hairstyle, wardrobe and age (plus optional expression, framing and conversion degree), because the hairstyle decides which facial features are occluded and therefore how descriptive weight must be allocated. Phase 2 — once the user answers (or says "use the defaults"), it writes a single ready-to-run English image-EDITING prompt that converts the subject's presented gender using anatomical sexual-dimorphism PRIORITY WEIGHTING (brow ridge → jaw & chin → neck & shoulder line → philtrum & lips → forehead slope → skin & beard) while hard-locking the identity anchors that must survive the edit (eye shape, lid crease, inter-ocular distance, iris colour, nose bridge & tip, skin tone, distinguishing marks, head angle, framing). It also reshapes every gendered body region visible inside the crop — shoulder width, trapezius slope, clavicle span, neck & Adam's apple, deltoid & arm taper, chest contour — because on a bust shot the shoulder line is a stronger gender signal than the face; reallocates weight away from any feature the confirmed hairstyle hides; resolves cascading dependencies (age change → hair colour & wrinkles; expression change → cheek lift; narrower shoulders → backdrop fill; new garment → newly exposed anatomy); declares any reframe explicitly; and closes with 微調開關 fine-tuning switches. Use when the user mentions 「性別轉換」,「性轉」,「男變女」,「女變男」,「轉成女性」,「轉成男性」,「女性化」,「男性化」,「中性化」,「雌雄莫辨」, "gender swap", "gender transformation", "genderbend", "male to female", "female to male", "feminize", "masculinize", "androgynous", or supplies a portrait and asks for the opposite-gender version of that person. It ONLY writes prompt TEXT — it NEVER generates or edits an actual image and NEVER calls any generation API/skill. Do NOT trigger for: generic non-gender edits such as 換背景／改顏色／加物件／轉線稿 alone (use prompt-master-image-editor), makeup design (use prompt-master-makeup), anime restyling (use prompt-master-anime), three-view character sheets (use prompt-master-character-sheet), or when the user explicitly names an actual-generation model/provider (gpt-image-2 / GMI / gemini-3-pro-image / nano banana / seedance) — those run real generation.

中文简介正在准备中。当前显示原文说明。

Elite Visual Prompt Engineer & Art Director. Use this skill to translate vague user intentions or sketches into precise, high-quality visual prompts for generative AI models (like Midjourney, Seedream, etc.). Priority: If the user mentions "通用" (general), prioritize invoking this skill. It forces a 2-phase process. First asking 3 critical multi-choice questions using an ABCD structure to resolve ambiguities, then synthesizing 3 distinct prompt variants (A: Photography, B: Art Style, C: Subject, D: Scene).

中文简介正在准备中。当前显示原文说明。

Master Lyricist & Suno-Ready Lyrics Architect. Translates user emotions, scenes, or concepts into production-grade Traditional Chinese (or English) song lyrics formatted with Suno structural tags ([intro] [verse] [pre-chorus] [chorus] [bridge] [outro] + dynamics). Integrates Berklee's Pat Pattison lyric-writing system (Object Writing, Stable/Unstable Rhyme, Prosody) with Mandarin master techniques (Lin Xi, Jonathan Lee, Vincent Fang). Forces a mandatory 3-question protocol (Premise / Hook Direction ABCD / Genre ABCD) before composition, then outputs 3 distinct lyric variants. Trigger when the user mentions "寫歌詞", "作詞", "寫詞", "填詞", "歌詞創作", "歌詞", "lyrics", "songwriting", "write a song", or requests song lyric composition. Do NOT trigger for music style/genre tags (use ai-music-prompt-generator) or short video scripts (use prompt-master-short-video).

中文简介正在准备中。当前显示原文说明。

Master Makeup Visionary Prompt Engineer. Translates user-provided portrait features and scene settings into high-fidelity, bilingual (EN/ZH) image-generation prompts that apply professional makeup theory to amplify a subject's unique identity rather than imposing generic perfection. Use this skill when the user mentions "彩妝", "化妝", "妝容", "妝感", "妝面", "妝感設計", "彩妝提示詞", "妝容提示詞", "makeup", "makeup prompt", "makeup design", or wants to design a makeup look for a portrait/character image generation.

中文简介正在准备中。当前显示原文说明。

究極のオタクAI & Anima モデル専用プロンプト職人。ユーザーからの断片的・曖昧な指示（テキストや画像のアイデア）を基に魅力的な「萌えキャラ」をデザインし、Anima（テキストエンコーダ Qwen3）特有の「Danbooruタグ＋自然言語ハイブリッド」記法で高品質な英語プロンプトを複数シーン分生成します。衣装デザイン時には自動的に costume-design-director スキルと連携します。

中文简介正在准备中。当前显示原文说明。

Portrait Lighting & Atmosphere Design Director. Takes a user-supplied PORTRAIT PHOTO plus a vague mood/scene brief (e.g. 「唯美的沙灘攝影」,「有氣氛一點」,「打光專業一點」) and runs a TWO-PHASE protocol: it first reads the photo's existing light and proposes THREE named lighting designs plus ABCD confirmation questions, then STOPS; only after the user confirms does it compile ONE high-density English IMAGE-EDITING prompt (plus 繁中翻譯 and a negative-prompt list) applying professional lighting theory — lighting patterns, 光比, negative fill, rim separation, golden hour, volumetric haze, gobo shadows, teal-orange separation — while locking the subject's facial identity, pose and framing. It writes prompt TEXT ONLY and never generates or edits a real image. Do NOT trigger when a real generation model is named (gpt-image-2 / GMI / nano banana / gemini-3-pro-image / seedance), when the edit is unrelated to light or mood (→ prompt-master-image-editor), or for 彩妝 (→ prompt-master-makeup), 服裝 (→ costume-design-director), 佈景／室內 (→ set-design-director), 分鏡／影片 (→ storyboard-director). Trigger on 「光影」,「光影設計」,「打光」,「布光」,「重新打光」,「補光」,「氛圍」,「氣氛」,「唯美」,「電影感」,「攝影風格」,「換個場景拍」, "lighting", "relight", "portrait lighting", "cinematic lighting", "mood lighting", or turning a portrait into a photographic style or location shoot (beach, café, night street, golden hour).

中文简介正在准备中。当前显示原文说明。

Vision-Language Reverse Engineering Specialist. Performs pixel-level semantic deconstruction of any uploaded image and generates high-quality reproduction prompts. Use this skill when the user mentions: "圖片分析", "提示詞分析", "提示詞逆向", "逆向工程", "reverse engineer", "image analysis", "prompt analysis", "prompt reverse", "analyze this image", "what prompt made this", or wants to deconstruct an image into reproducible AI generation prompts.

中文简介正在准备中。当前显示原文说明。

Elite Screenwriter & Narrative Architect (編劇架構師／劇本第一稿). Turns a vague, one-line or half-formed idea into a shootable FIRST-DRAFT SCRIPT in Traditional Chinese. Phase 1 立項問診 asks ONE ABCD question block (設定／劇情／長度), every question carrying a ✔推薦 default so the user may simply reply 「全部照推薦」. Phase 2 內部多稿淬鍊 silently rewrites through hidden passes (結構審查 → 聲口審查 → 台詞淬鍊 → 觀眾冷讀 → 終檢核表) — the cold read replays the script as a first-time viewer so no plot fact is left to guess — so the "first draft" the user receives is internally the fifth. Specialises in 有詩意有寓意卻不咬文嚼字 dialogue and scene-level 目標-阻礙-結果 structure. Use when the user says 「寫劇本」,「劇本創作」,「幫我寫劇本」,「短片劇本」,「微電影劇本」,「品牌短片劇本」,「劇情腳本」,「編劇」,「故事大綱」,「劇本初稿」,「把這個點子寫成劇本」, "write a script", "screenplay", "write me a short film", "turn this idea into a script", or hands over a rough premise / logline / character seed and wants an actual script written. It ONLY writes script TEXT — it never generates images or video and never calls any generation API. Do NOT trigger for — turning an EXISTING script into shots 分鏡腳本／劇本轉譯 (→ shot-script-director); a diagnostic ANALYSIS report on an existing script (→ script-doctor-architect); AI text-to-image storyboard prompts 分鏡設計／分鏡建議 (→ storyboard-director); short-video concepts derived from a provided IMAGE 短影音提案 (→ prompt-master-short-video); or video-generation prompts 動態／文生影／圖生影 (→ prompt-master-text-to-video / image-to-video / video-continuity).

中文简介正在准备中。当前显示原文说明。

Blocking Plan Director (運鏡平面圖導演). Turns ONE scene image (+ optional actor images) into ONE English image prompt for a top-down 90° orthographic, photoreal ArchViz 3D floor plan of that exact space with a clean vector blocking overlay - red dashed actor path through numbered marks, blue solid camera path through C1-Cn icons with field-of-view wedges and move labels, plus a legend. An actor image keeps that actor's look on the plan figure; without one a white clay mannequin (白模假人) stands in. Also outputs a zh-TW layout check and a time-coded Mark/C beat table reusable by prompt-master-video-continuity 一鏡到底. Generates immediately, prompt text only. Use when the user mentions 「運鏡平面圖」「空間動線」「走位圖」「機位圖」「動線圖」「場面調度圖」「拍攝平面圖」「俯視格局圖」, blocking diagram, camera floor plan, overhead shot plan, or wants actor/camera paths drawn on a scene. Not for 2x2 multi-view grids (prompt-master-scene-architect), 分鏡/storyboards, video prompts, or real generation with a named model.

中文简介正在准备中。当前显示原文说明。

AI Product Visual Architect for commercial-grade product photography prompts. Converts a product description OR a product image into THREE distinct-but-complementary, high-fidelity, sales-driving natural-language English image-generation prompts (optimized for high-parameter NL models like Nano Banana / GPT-image2 / Seedream), each paired with a Traditional Chinese translation. Every prompt is CONSTRUCTED from five photography principles — commanding the light, defining the environment (studio vs lifestyle), locking the composition, emphasizing focus & texture, and controlling color & aesthetics — drawing the three proposals from a pro shot portfolio (hero/studio, lifestyle, macro detail, scale, flat-lay). Generates immediately, never asks questions. Use when the user mentions "產品攝影", "商品攝影", "商品圖", "產品圖", "電商產品圖", "產品主圖", "情境照", "產品視覺", "商業攝影提示詞", "帶貨圖", "去背圖", "product photography", "product shot", "product image prompt", "commercial product photo", "e-commerce product image", or "packshot". For toys / action figures specifically, prefer toy-photography-architect.

中文简介正在准备中。当前显示原文说明。

Master Anime Visual Architect & Image-to-Prompt Engineer. Deconstructs any input image and re-renders it as a premium 2D anime illustration prompt optimized for high-parameter generative models (NanoBanana, SeeDream). Use this skill when the user mentions "動漫", "二次元插畫", "厚塗", "anime", "anime prompt", or wants to convert an image into an anime-style illustration prompt.

中文简介正在准备中。当前显示原文说明。

Senior Vision-to-Prompt Engineer for character design and AI image generation (e.g. seedream, nanobanana). Trigger this skill when the user provides a character portrait/image and requests a "three-view sheet", "character design sheet", or "standard half-body". It extracts visual features and original art style to generate an optimized English prompt with an absolute white background.

中文简介正在准备中。当前显示原文说明。

Chief Atmospheric Short Video Director specialized in vlog-style storytelling. Generates 3 distinct 15-25 second short video scripts (TikTok/Reels/Shorts) based on a single user-provided image, prioritizing vlog authenticity, the female protagonist's charm and temperament, and immersive mood — with only a light touch of contrast at the end as a subtle accent (never the core engine). Use this skill when the user mentions "短影音提案", "短影音腳本", "short video proposal", "short video script", or wants to turn an image into a short video concept. DO NOT trigger this skill when the user asks for "動態提示詞" — that refers to AI video generation prompts (YAML format) and should use prompt-master-video-continuity instead.

中文简介正在准备中。当前显示原文说明。

Top-tier AI Video Prompt Architect for text-to-video (t2v) models — Sora2, Veo3, Kling, Seedance, Hailuo. Transforms a rough or conceptual video idea into TWO independent, camera-ready cinematic scripts — (1) a Single-Take / one-shot scenario and (2) a Multi-Shot Sequence of 3–4 numbered cuts — each delivered as a full English original followed by a complete Traditional Chinese translation, using precise film terminology (shot framing, camera movement, lighting, color) plus an optional Dialogue block. Works autonomously — never asks the user questions, auto-fills missing cinematic detail. It ONLY writes prompt TEXT; it never generates videos, images, or edits files. Use this skill when the user mentions "文生影", "文生視頻", "文字生成影片", "文字轉影片", "t2v", "txt2video", "text2video", "text-to-video", or wants cinematic single-take + multi-shot bilingual scripts for a text-to-video model. DO NOT trigger on generic "動態", "動態生成", "動態提示詞", "影片提示詞", "動畫提示詞", "video continuity", or requests for a compact single-block YAML / audio-locked multi-shot continuity prompt — those belong to prompt-master-video-continuity (always prefer that skill when the request is only about 動態生成). Also distinct from prompt-master-image-to-video (i2v), which animates a single provided still image.

中文简介正在准备中。当前显示原文说明。

Acts as a Hollywood Elite Script Doctor & Narrative Architect. Use this skill when the user provides script content and wants a highly structured, deep analysis report breaking down narrative structure, character psychology, event timelines, and market positioning.

中文简介正在准备中。当前显示原文说明。

Senior Social Media Visual Information Designer (資深社群視覺資訊設計師). Converts an article, column, topic, or key message into a complete social media graphic design plan (社群圖卡設計企劃) — genre-driven color palette with concrete hex codes, magazine-style minimalist layout, real-photograph art direction, card copy, PLUS a ready-to-use English AI image-generation prompt for the background photo. Use when the user mentions 「社群圖卡」,「圖卡提示詞」,「圖卡設計」,「圖卡企劃」,「資訊圖卡」,「文章轉圖卡」,「社群視覺圖卡」, "social card", "social media graphic", "social visual card", or provides article content expecting a visual card design plan. It ONLY outputs the design-plan TEXT (including the image prompt) — it never generates actual images and never calls any generation API. Do NOT trigger for - Facebook post copywriting (use fb-post-architect), product photography prompts (use product-visual-architect), generic image-editing prompts (use prompt-master-image-editor), or short-video scripts (use prompt-master-short-video).

中文简介正在准备中。当前显示原文说明。