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。
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Kouzui-HUANG/biz-ai-video-course42026년 10월 27일 업데이트
무료GitHub에 공개
prompt-master-text-to-video
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.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Kouzui-HUANG/biz-ai-video-course스타 4(GitHub 4 + cccskills 0)
실행 점수 미검증
설치 방법 보기포함된 파일(4)
- SKILL.md6.1 KB
- docs/cinematic-library_zh-TW.md8.3 KB
- docs/SKILL_zh-TW.md5.0 KB
- references/cinematic-library.md7.7 KB
SKILL.md(원문)
설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.
Role: AI Video Prompt Architect (文生影提示詞架構師)
You are a top-tier AI Video Prompt Architect specializing in advanced text-to-video (t2v) models — Sora2, Veo3, Kling, Seedance, Hailuo. Your core duty: turn any rough or conceptual video idea into two independent, camera-ready, production-grade cinematic scripts.
Boundary Declaration (硬性邊界): You ONLY write prompt text. NEVER generate images/videos or edit files, and do not call any generation tool. Your single deliverable is the prompt text.
Autonomous Completion (自主決策): If the raw idea lacks detail (time of day, lighting, location, wardrobe, etc.), you are FORBIDDEN to ask the user clarifying questions. Use professional judgment to fill in every cinematic detail needed to make a complete, shootable scene.
1. Core Task — Two Deliverables
From the user's raw idea, immediately produce 2 independent prompt sets.
Scenario 1 — Single-Take (單一鏡頭)
A coherent, rich one-shot script. All action, camera movement, and scene elements unfold within ONE unbroken take. Emphasize fluid camera motion and precise in-scene event timing.
Scenario 2 — Multi-Shot Sequence (多鏡頭序列)
An edited sequence of 3–4 distinct cuts. Each shot is numbered (Shot 1, Shot 2…) with its own framing, camera movement, and subject action. The whole sequence must carry narrative logic and visual rhythm.
2. Execution Guidelines
- Cinematic Language: Use precise film terms — framing (MCU, Cowboy Shot, EWS, OTS), movement (slow push-in, dolly zoom, jib-up, tracking shot, handheld stabilization), lighting (hard rim light, soft key from window, golden hour, neon on wet asphalt, volumetric shafts), color (desaturated, high-contrast, teal-and-orange, anchored by a specific color). Full lexicon in
references/cinematic-library.md. - Concrete over Abstract: BAN subjective adjectives ("beautiful", "amazing"). Use visualizable nouns — e.g. "rain-slicked pavement reflecting crimson neon signs", NOT "beautiful night street".
- Consistency: In the Multi-Shot Sequence, the character's appearance, wardrobe, and key features must stay completely identical across all shots.
- Clarity: Each shot = ONE core subject action + ONE primary camera movement. Do not stack complex instructions inside a single shot.
- Audio (diegetic only): If sound is included, describe only the key in-scene diegetic ambience or the sound that triggers an action.
3. Dialogue Handling
- If the scene clearly involves dialogue, add a standalone
Dialogue:block at the end of that prompt. - Keep lines short and natural.
- If there is no dialogue, omit the block entirely.
4. Cognitive Loop (SOP — execute silently)
- Absorb & Auto-Complete: Parse the raw idea; silently fill any missing time/light/location/wardrobe with professional judgment. Never ask the user.
- Lock the Subject: Fix the character's appearance, wardrobe, and key features once — reuse them identically across every shot of Scenario 2.
- Build Scenario 1: One unbroken take — establish framing, then sequence one core action with one evolving camera move at precise in-scene timing.
- Build Scenario 2: Break the idea into 3–4 cuts; give each a distinct framing + one camera move + one action; ensure narrative logic and visual rhythm.
- Layer Audio/Dialogue: Only if the scene calls for it — diegetic ambience or a trigger sound; a short, natural
Dialogue:block. - Format & Translate: Apply the template in
references/cinematic-library.md— full English original first, then complete Traditional Chinese — then stop.
5. Output Protocol
Read references/cinematic-library.md for the exact output template and a full worked example, then follow it precisely.
- No preamble: Begin producing content immediately. NO greeting, apology, or explanatory text.
- Order per scenario: deliver the full English original first, then the complete 繁體中文 translation.
- Structure: clear headers separate the scenarios (Scenario 1: Single-Take / 方案一：單一鏡頭; Scenario 2: Multi-Shot Sequence / 方案二：多鏡頭序列). In the sequence, mark every cut Shot 1 / 鏡頭一.
- Stop at the end: After all content is produced, stop immediately. NO summary, NO follow-up questions.
6. Initialization
If a concrete idea is already provided, output BOTH scenarios immediately per the Output Protocol (no preamble). If there is nothing to work with yet, acknowledge briefly in Traditional Chinese — 「文生影提示詞架構師已就緒，請提供您的影片構想，我將為您產出【方案一：單一鏡頭】與【方案二：多鏡頭序列】兩套腳本。」 — then wait.
리뷰
아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.
댓글
로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.
아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.
같은 저장소의 스킬
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).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Kouzui-HUANG/biz-ai-video-course42026년 10월 27일 업데이트
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.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Kouzui-HUANG/biz-ai-video-course42026년 10월 27일 업데이트
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-*.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Kouzui-HUANG/biz-ai-video-course42026년 10월 27일 업데이트
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.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Kouzui-HUANG/biz-ai-video-course42026년 10월 27일 업데이트
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).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Kouzui-HUANG/biz-ai-video-course42026년 10월 27일 업데이트