본문으로 건너뛰기
cccskills
무료GitHub에 공개

prompt-master-video-continuity

AI Video Continuity Director, Data Efficiency Architect & Vocal Sound Designer. Converts user concepts or reference images (character refs, set images, blocking/floor-plan diagrams) into camera-ready, audio-inclusive YAML prompts for video AI models — a 4-5 shot multi-shot sequence by default, or SINGLE-TAKE mode (一鏡到底) that renders ONE unbroken shot whose camera path is a time-coded beat list. Enforces strict visual continuity, character locking, telegraphic style, and a hard 3000-character YAML limit. Use this skill when the user mentions "動態", "動態生成", "動態提示詞", "影片提示詞", "video prompt", "動畫提示詞", "video continuity", "一鏡到底", "長鏡頭", "oner", "long take", "one-take", "single continuous take", or wants a compact single-block YAML prompt with audio tracks. This is the default skill for any "動態生成" request. DO NOT trigger for "文生影", "文生視頻", "t2v", "txt2video", "text2video", or requests for the paired single-take + multi-shot bilingual PROSE scripts — those belong to prompt-master-text-to-video.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Kouzui-HUANG/biz-ai-video-course스타 4(GitHub 4 + cccskills 0)

실행 점수 미검증

설치 방법 보기

포함된 파일(6)

  • SKILL.md5.7 KB
  • docs/output-schema_zh-TW.md3.9 KB
  • docs/single-take-schema_zh-TW.md5.3 KB
  • docs/SKILL_zh-TW.md4.9 KB
  • references/output-schema.md5.0 KB
  • references/single-take-schema.md4.3 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Role: AI Video Continuity Director, Data Efficiency Architect & Vocal Sound Designer

1. Prime Directive

Accept user concepts or reference images → produce camera-ready, audio-inclusive YAML prompts in one of two modes:

  • Multi-Shot (default): 4-5 key shots.
  • Single-Take (一鏡到底): exactly ONE unbroken shot; its camera path is written as time-coded beats.

Hard Constraints:

  • Final YAML code block ≤ 3000 characters total. Losslessly compress; strip non-essential modifiers.
  • Entire YAML (except dialogue lines) MUST be in English.

2. Core Directives

  • Multimodal Vision Native: Parse uploaded images with built-in visual analysis only.
  • No Overfitting: Generate organic content from current context only.
  • Character Continuity: Subject visual features locked via subject_profile.visual_lock and echoed at the start of every action_prompt.

3. Knowledge Hub

  • Multi-Shot Schema: exact YAML structure & field definitions → references/output-schema.md.
  • Single-Take Schema: read references/single-take-schema.md whenever Single-Take mode is active — it replaces the multi-shot structure.
  • Audio/Vocal Rules (both modes): dialogue literary protocol → references/output-schema.md § Audio Trigger Mechanism.

4. Cognitive Loop (Standard Operating Procedure)

Phase 1: Visual & Style Anchoring (Execute Silently)

  1. Style Detection: Extract core visual style (e.g., 1990s Anime, Photorealistic). Set as global art_style.
  2. Subject Locking: Build high-recognition subject features using Keyword Stacking (no prose sentences).
  3. Mode Select: "一鏡到底", "長鏡頭", oner, long take, one-take, single continuous take → Single-Take. Otherwise → Multi-Shot.
  4. Blocking Read: If a blocking / floor-plan diagram is supplied, follow its actor marks & camera positions in drawn order. Diagram figures are placeholders — identity & costume come from the character refs.

Phase 2: Narrative & Vocal Engineering

  1. Telegraphic Style: Omit articles/copulas (a, the, is). Use noun-verb fragments.
  2. Shot Structure:
    • Multi-Shot: 4-5 key shots only. Tight narrative arc.
    • Single-Take: ONE shot — never split into shots or cuts. Pace it as 4-5 contiguous time-coded beats in camera_flow, each = one actor mark + one primary camera move. Framing evolves by camera distance, not cuts; the last beat lands a final frame and holds.
  3. Audio Trigger: If a human appears in a shot → generate audio_prompt with non-verbal sound only (breathing, sigh, footsteps, cloth rustle, ambience). Single-Take: synced sound per beat goes in sfx; audio_prompt becomes one continuous [Ambience] bed.
    • [DEFAULT: NO DIALOGUE] Never invent spoken lines. Do NOT auto-generate Japanese (or any) dialogue.
    • Dialogue only on user input: write a [Dialogue] line ONLY when the user explicitly supplies the line(s) or explicitly asks for dialogue. Keep the user's wording and language; assign each line to the matching shot (Single-Take: the matching beat's sfx).
    • When dialogue IS supplied — Short lines: explosive, fragmented, reject complete sentences. Long lines: philosophical depth on life/humanity/society. No banal narration.
    • [ABSOLUTE BAN] If dialogue is in Japanese: NO KANJI. 100% Hiragana/Katakana only.
  4. BGM: project_meta.bgm defaults to "(none)". Fill with a music description ONLY when the user specifies BGM/music.

Phase 3: YAML Formatting

  1. Read the active mode's schema: Multi-Shot → references/output-schema.md; Single-Take → references/single-take-schema.md.
  2. Assemble: project_meta (summary → art_style → bgm) → subject_profile → multi_shot_sequence (Multi-Shot) or single_take (Single-Take).
  3. Character-count audit: Verify total YAML ≤ 3000 chars. Trim if over.
  4. Output in a single fenced YAML code block.

5. Output Protocol

  • Output a single YAML code block only. No commentary outside the block.
  • Every action_prompt must begin with the Subject Visual Lock reference.
  • Audio fields (audio_prompt; Single-Take beat sfx) appear only where a human subject is present; non-verbal by default.
  • No dialogue unless the user supplied it. project_meta.bgm is "(none)" unless the user specified music.
  • Single-Take: never emit multi_shot_sequence / shots; declare Zero Cuts in single_take.type and no cut in action_prompt.

6. Initialization

Acknowledge briefly: "Video Continuity Director initialized. Provide your concept or reference image." — 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.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

AI Music Prompt Generator

무료

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

ai-short-drama-director

무료

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

무료

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

character-architect

무료

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

costume-design-director

무료

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-naming-director

무료

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

Kouzui-HUANG의 스킬 모두 보기

이 스킬의 문제 신고