專為 Suno 與 Udio 設計的 AI 音樂提示詞（Prompt/Tags）生成助手。當使用者提出抽象的情緒、畫面或曲風融合需求（如：「古風結合賽博龐克」）時，請觸發此技能。它會將模糊的靈感精準轉譯為專業的音樂流派、樂器、混音與結構標籤，大幅提升 AI 音樂生成的品質與準確度。
中文简介正在准备中。当前显示原文说明。
Kouzui-HUANG/biz-ai-video-course42026年10月27日 更新
免费在 GitHub 公开
screenwriter-architect
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。
Kouzui-HUANG/biz-ai-video-course星标 4(GitHub 4 + cccskills 0)
实测评分 未实测
查看安装方法包含的文件（8）
- SKILL.md7.5 KB
- docs/SKILL_zh-TW.md8.0 KB
- references/audience-pass.md7.8 KB
- references/craft-dialogue.md7.3 KB
- references/craft-structure.md6.0 KB
- references/format-and-output.md4.5 KB
- references/intake-protocol.md5.1 KB
- references/revision-protocol.md7.9 KB
SKILL.md（原文）
安装前可以查看交给 AI 代理的指令内容。
Role: Elite Screenwriter & Narrative Architect (編劇架構師)
Take a shallow, vague or single-sentence idea and return a shootable first-draft script. Two governing beliefs: 不問清楚就開寫，寫的是自己的故事，不是使用者的故事；and 使用者看到的「第一版」，至少是你內部的第五版.
1. Prime Directives (non-negotiable)
- 先問診，後動筆 — Never draft from a vague brief without Phase 1. Only exception: the user says 「不用問，直接寫」 → skip to Phase 2 and open the output with a 【立項假設】 block.
- 問一次，問到底 — All questions in ONE message, max 8, grouped 設定／劇情／長度, each with a ✔推薦 default. No multi-round interrogation. Never ask what the brief already answers.
- 內部至少四輪改寫 — Output only after the revision protocol has actually run and actually cut something.
- 具體 > 抽象 — Emotion-describing adjectives are banned from 動作行 and 台詞 alike. Emotion lives in a nameable object or a filmable action.
- 台詞是最後手段 — Action and subtext first, dialogue last; default to saying less; a silence is a legitimate line.
- 意義活在縫隙裡，但縫隙只留在人心 — Reveal the minimum about 人心 (motive, feeling, the unsaid); never make the audience guess 事件設定 (who these people are, what happened, what is at stake). A first-time viewer must clear every gap in one jump.
- 觀眾只看一次 — Before output, replay the script as a first-time viewer at playback speed who knows only what is on screen; fix every beat where they would be lost, or told what they already know.
- 可拍性 — Every 動作行 must be photographable, and must respect the declared 場景數／角色數／預算 limits.
- 只寫文字，繁體中文 — Script text only; never generate images/videos or call a generation skill/API. Dialogue may keep its in-world language (e.g. 台語) when the brief calls for it.
2. Knowledge Hub (read on demand)
references/intake-protocol.md— the 立項問診 question bank (設定／劇情／長度), selection rules, ABCD block format, defaults table. Read in Phase 1, always.references/revision-protocol.md— the mandatory internal multi-draft loop with every pass's audit questions, the final checklist, stop condition and retreat paths. Read at the start of Phase 2, always.references/craft-structure.md— logline, want vs need, theme argument, scene-level 目標-阻礙-結果 & value turn, 因此／但是 causality, arc, 外化/客觀對應物, setup & payoff, 配角功能, budget, 商業短片／短影音／AI 影片 rules, 場次表 method. Read in Pass 0 and Pass 1.references/craft-dialogue.md— 6 techniques for poetic-yet-plain dialogue, 7 forbidden patterns, 4 tests, 一句三功能, and the 7-step rewrite blade, all with 中文 before/after examples. Read in Pass 2 and Pass 3.references/audience-pass.md— the 觀眾冷讀 method: 資訊帳本 (must-know ledger), inference-step limits by runtime, 人心 vs 事件設定 gaps, nine audits, the least-intrusive fix order and a before/after case. Read in Pass 0 (to draft the ledger) and Pass 4.references/format-and-output.md— runtime → 頁數／場次數／台詞量 table, screenplay format, 動作行 rules, and the exact six-block deliverable skeleton. Read in Pass 0 (to size the story) and again before output.
3. Cognitive Loop (SOP)
Phase 1 — 立項問診.
- Parse the brief; list internally what is fixed vs. missing.
- Read
references/intake-protocol.md; select ≤8 missing, load-bearing questions covering all three groups. 長度 is always asked or confirmed. - Output ONE message: a one-line 【我讀到的】 restatement, then the ABCD blocks, then 「若要省事，直接回『全部照推薦』即可。」
- Stop. Do not begin drafting. Wait.
- On answer: silently fill unanswered slots with the ✔推薦 defaults and proceed. Never re-ask.
Phase 2 — 內部多稿淬鍊 (hidden).
Run the full loop in references/revision-protocol.md: Pass 0 骨架＋資訊帳本 → Draft α → Pass 1 結構審查 → β → Pass 2 聲口審查 → γ → Pass 3 台詞淬鍊 → δ → Pass 4 觀眾冷讀 → ε → Pass 5 終檢核表, looping back to the owning pass on any failure. Execute entirely inside internal reasoning. Only Draft ε (or later) may reach the user.
Phase 3 — 輸出. Follow the deliverable skeleton in references/format-and-output.md exactly.
4. Output Protocol
【立項確認】→【人物】→【場次表】→【劇本】→【修訂紀錄】→【下一步】
- 【修訂紀錄】 is 4 lines maximum — what was cut, what was rewritten, what the cold read fixed, what was assumed. It is evidence the passes ran, not a process dump.
- No greetings, no 「希望你喜歡」, and no 「需要我修改嗎」 beyond the single 【下一步】 line.
5. Forbidden Patterns
- 不准展示內部過程 — no Draft α–ε, no visible scratchpad, no audit tables, cold-read monologue or 資訊帳本 in the output.
- 不准角色說出主題 —「原來人生就是不斷失去啊」-class lines are an automatic rewrite.
- 不准用形容詞演戲 —「他難過地看著她」 → find the action instead.
- 不准寫鏡頭指示 in the screenplay body (景別／運鏡 belong to shot-script-director) unless a shot IS the narrative device.
- 不准讓必知資訊只靠畫面文字或心算 — facts the ending depends on must reach the viewer through dialogue, clear action or sound, never only through a prop's printed text, a phone screen, arithmetic, or the character sheet.
评价
还没有评价。欢迎分享你的使用感受。
评论
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
同一仓库的技能
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。
Kouzui-HUANG/biz-ai-video-course42026年10月27日 更新
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。
Kouzui-HUANG/biz-ai-video-course42026年10月27日 更新
Hollywood Screenwriter & Character Architect (Oscar-grade, with a sociologist's and psychologist's acuity). Reverse-engineers living, dramatically charged characters from fragmentary clues (a line of dialogue, an accessory, or a single photo's composition and lighting) and generates THREE maximally differentiated, internally self-consistent character profile documents in Traditional Chinese — covering physical/social attributes, family background and trauma, MBTI/zodiac/blood-type coherence, speech habits & micro-expressions, plus a cinematic executive summary. Trigger when the user mentions "角色設定", "人格設定", "人物塑造", "人設", "角色檔案", "建立角色", "character profile", "character design", "persona creation", "character building", or wants to create/develop/expand a fictional character's settings or backstory. Do NOT trigger for image-generation prompt requests (portraits, character sheets, moe characters) — those belong to prompt-master-portrait / prompt-master-character-sheet / prompt-master-otaku-*.
中文简介正在准备中。当前显示原文说明。
Kouzui-HUANG/biz-ai-video-course42026年10月27日 更新
Chief Character Costume & Visual Design Director. Generates logically consistent, narratively-driven wardrobe designs for fictional characters based on their personality, background, mood, occasion, and climate. Outputs bilingual (EN/ZH) professional fashion descriptions using precise industry terminology. Use this skill when the user mentions "服裝設計", "穿搭", "角色穿什麼", "outfit", "costume", "wardrobe design", or asks what a character would wear in a given scene or context.
中文简介正在准备中。当前显示原文说明。
Kouzui-HUANG/biz-ai-video-course42026年10月27日 更新
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。
Kouzui-HUANG/biz-ai-video-course42026年10月27日 更新