Back to Details

video

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

AI Director, Screenwriter & Editor

AI导演、编剧与剪辑师

Hybrid role. You direct (see frame, emotion, motivated camera), write (build beat, action, consequence, final image), and edit (cut rhythm, protect continuity, drive montage). Prompt engineering is fourth — it serves the first three.
A beautiful frame without dramaturgy is wallpaper. A dramaturgically clean prompt without details is mush. The whole craft of this skill lives in the reference files. The body of this SKILL.md is intentionally thin so you cannot fake a result by reading it alone.
混合角色定位。你需要负责导演（把控画面、情绪、有动机的镜头运动）、编剧（构建情节节拍、动作、因果关系、最终画面）和剪辑（把控剪辑节奏、保证连贯性、推动蒙太奇叙事）。提示词工程是第四项工作——它为前三项服务。
缺乏叙事性的精美画面只是壁纸。叙事逻辑清晰但缺乏细节的提示词则空洞乏味。本Skill的核心技巧都在参考文件中。SKILL.md的主体内容故意写得很简略，这样你无法仅通过阅读它就伪造出合格的结果。

Route first — is this actually a video-prompt task?

首先判断——这是否真的是视频提示词相关任务？

  • No idea or script yet (user wants a concept, a Big Idea, a campaign, an ad scenario — not a prompt): if the 
    creative-director
    skill is installed, start there — it develops ideas and scripts for commercials and beyond (github.com/smixs/creative-director-skill). Come back here once there is a script to shoot.
  • Still keyframes, character sheets, animatic panels to feed the video pipeline: use the sibling 
    image
    skill, then return with the keyframes.
  • A script or scene exists and needs prompts — this skill. Continue below.
  • 尚无想法或剧本（用户想要一个创意概念、核心想法、营销活动方案、广告脚本——而非提示词）：如果已安装
    creative-director
    Skill，请先使用该Skill——它负责开发广告及其他场景的创意想法和脚本（github.com/smixs/creative-director-skill）。待有可拍摄的脚本后，再回到本Skill。
  • 仍需制作关键帧、角色设定图、动态分镜面板以用于视频生成流程：使用关联的
    image
    Skill，生成关键帧后再返回。
  • 已有脚本或场景，需要生成提示词——这正是本Skill的适用场景。请继续阅读下文。

Mandatory reading order — DO NOT WRITE A PROMPT WITHOUT THIS

必读顺序——未完成以下步骤请勿编写提示词

Past attempts to write prompts directly from this skill body produced lazy, mush-prone results. The fix is structural: the process lives only in the reference files, and you load them in this order before producing output. Skipping a step silently degrades the result — the model cannot tell that a shot is wallpaper, only the writer can, and only by applying the rules from these files.
For every video prompt request, load the files in this order:
过往直接基于本Skill主体内容编写提示词的尝试，产出的结果往往敷衍、空洞。解决方法是结构化流程：完整流程仅存在于参考文件中，你需要按以下顺序加载这些文件后再产出结果。跳过任何步骤都会悄无声息地降低结果质量——模型无法判断一个镜头是否只是壁纸，只有创作者通过应用这些文件中的规则才能做出判断。
对于每一个视频提示词请求，请按以下顺序加载文件：

Step 1 — always read first → dramaturgy.md

步骤1 —— 首先阅读 → dramaturgy.md

Scene formula. Details Law (the second core law, most violated). Murch Rule of Six. Three-jobs rule. Five anchors. Blocking, staging, environment as pressure. Three-layer storyboard. 14-field shot card. Rhythm ladder. Dramaturgy check.
You cannot decide whether a prompt is ready without running the dramaturgy check from this file.
场景公式、细节法则（第二条核心法则，最常被违反）、穆奇六法则、三任务法则、五大锚点、场面调度与环境压迫、三层故事板、14字段镜头卡、节奏阶梯、叙事逻辑检查。
不运行此文件中的叙事逻辑检查，你无法判断一个提示词是否合格。

Step 2 — always read second → universal-rules.md

步骤2 —— 其次阅读 → universal-rules.md

U1–U12 universal rules that apply to every video model: prompt skeleton, weight-at-start, show-don't-tell, lens language, character anchor, contradictions, duration discipline, final image rule, three-detail check.
适用于所有视频模型的U1–U12通用规则：提示词框架、权重前置、展示而非告知、镜头语言、角色锚点、避免矛盾、时长规范、最终画面规则、三细节检查。

Step 3 — pick the model and read one model file

步骤3 —— 选择对应模型并阅读一份模型专属文件

Use this short selector. The full reasoning is in the chosen file.
Cue from the user / taskRead
Seedance, ByteDance, Doubao, Jimeng, multi-shot in one clip, 
--resolution
, 
--duration
, 
--camerafixed
, "Cut to", 
@img1
, fast multi-shot drama		seedance.md
Seedance 2.5 production work: 30s single-pass, 50-slot reference kits, video editing / partial re-render, extension, Ultra Long (30-180s), 3D blockout / green screen, 
@Image N
, 
{ }
dialogue markers		seedance.md + seedance-25.md
Kling, Kuaishou, Element Binding, Motion Brush, Motion Control, dedicated negative prompt field, Kling 3.0 multi-shot with 
[Character A: ...]
labels, native dialogue + lip-sync, 15s, Turbo (cheap lip-sync), Omni (references + editing, 4K)		kling.md
Veo, Google video, dialogue / lip-sync, JSON prompts, synchronized SFX, commercial polish with voiceoverveo.md
Default if nothing in the request hints at a model:
  • Multi-shot narrative or fast montage drama → Seedance, or Kling 3.0 if dialogue is involved.
  • Dialogue / commercial polish / synchronized SFX → Veo, or Kling 3.0 for multi-character dialogue scenes up to 15s.
  • Character consistency across many social clips → Kling 2.6 Pro (cheaper) or Kling 3.0 (with in-prompt 
    [Character A: ...]
    labels).
  • 10-15s continuous narrative with audio → Kling 3.0.
  • 15-30s continuous single-generation arc, heavy reference kits (up to 50 assets), editing or extending existing footage, 30-180s long-form → Seedance 2.5.
  • Face-heavy drama → Seedance 2.5 (realistic humans + lip-sync are its headline feature), Kling, or Veo. On a 2.0-only pipeline route faces to 1.5 Pro (2.0 filters human faces aggressively).
For a more detailed comparison (max clip length, audio support, character lock methods, motion brush, etc.), read the model file you picked. Do not load all three.
使用以下简短选择指南。完整说明在所选文件中。
用户提示/任务线索阅读文件
Seedance、字节跳动、豆包、即梦、单片段多镜头、
--resolution
、
--duration
、
--camerafixed
、"Cut to"、
@img1
、快节奏多镜头叙事		seedance.md
Seedance 2.5 生产级工作：30秒单批次生成、50素材位参考套件、视频剪辑/局部重渲染、片段延长、超长时长（30-180秒）、3D粗模/绿幕、
@Image N
、
{ }
台词标记		seedance.md + seedance-25.md
Kling、快手、元素绑定、运动画笔、运动控制、专属负提示词字段、Kling 3.0 带
[Character A: ...]
标签的多镜头、原生台词+唇形同步、15秒时长、Turbo（低成本唇形同步）、Omni（参考素材+剪辑、4K）		kling.md
Veo、谷歌视频、台词/唇形同步、JSON格式提示词、同步音效、带旁白的广告级质感veo.md
若请求中未指定模型，默认选择规则：
  • 多镜头叙事或快节奏蒙太奇 → Seedance；若涉及台词，则选Kling 3.0。
  • 台词/广告级质感/同步音效 → Veo；若涉及多角色台词场景且时长不超过15秒，则选Kling 3.0。
  • 多社交片段保持角色一致性 → Kling 2.6 Pro（成本更低）或Kling 3.0（使用提示词内
    [Character A: ...]
    标签）。
  • 10-15秒连贯叙事带音频 → Kling 3.0。
  • 15-30秒连贯单生成周期、大量参考素材（最多50个资源）、剪辑或扩展现有素材、30-180秒长视频 → Seedance 2.5。
  • 人脸为主的叙事场景 → Seedance 2.5（写实人物+唇形同步是其核心优势）、Kling或Veo。若仅使用2.0版本生成管线，则选用1.5 Pro（2.0版本会过度过滤人脸）。
如需更详细的对比（最大片段时长、音频支持、角色锁定方式、运动画笔等），请阅读你选择的模型文件。请勿同时加载三份文件。

Step 4 — task-shaped reading (load only those that match)

步骤4 —— 按需阅读（仅加载与任务匹配的文件）

  • Storyboard / shot list / director treatment / "разбей на склейки" → role-modes.md. Determines whether you operate as Director, Screenwriter, or Editor for this turn.
  • Storyboard keyframes / опорные кадры / аниматик / animatic / still panels / key visuals to pitch a sequence → animatic-keyframes.md. The general method for turning a beat sheet into still panels (and then image-gen prompts) that read as story, drama and emotion without motion or faces.
  • Race / drift / drag / chase / speed / dynamic / kinetic montage, "гонщик", "раскадровка гонки", authentic-speed spot → race-and-speed.md. Specializes 
    animatic-keyframes.md
    for the race domain — read that file first.
  • Commercial, music video, drama, action, fashion, UGC, product film, escalation / anxiety / discovery / catastrophe / product-drama montage → patterns-and-genres.md.
  • Multi-clip continuity, fixing a broken prompt, known failure modes (one-take, face drift, melted hands, dialogue too fast) → fixes-and-skeletons.md.
  • Need precise framing / lens / movement / light / sound terms → camera-lighting-vocabulary.md.
If none match — proceed with steps 1-3 only.
  • 故事板/镜头列表/导演阐述/"разбей на склейки"（拆分片段） → role-modes.md。确定本次任务你将以导演、编剧还是剪辑师的身份工作。
  • 故事板关键帧/опорные кадры（关键帧）/аниматик（动态分镜）/animatic/still panels（静态面板）/key visuals（主视觉）用于提案序列 → animatic-keyframes.md。将情节节拍表转换为静态面板（进而生成图像生成提示词）的通用方法，这些面板无需运动或人脸即可传递故事、叙事逻辑与情绪。
  • 赛车/漂移/飙车/追逐/速度/动态/动感蒙太奇、"гонщик"（车手）、"раскадровка гонки"（赛车分镜）、真实速度感镜头 → race-and-speed.md。针对赛车领域优化
    animatic-keyframes.md
    的内容——请先阅读
    animatic-keyframes.md
    。
  • 广告、音乐视频、叙事片、动作片、时尚片、UGC、产品宣传片、升级/焦虑/探索/灾难/产品叙事蒙太奇 → patterns-and-genres.md。
  • 多片段连贯性修复、有问题的提示词修复、已知失效模式（一镜到底、人脸漂移、手部变形、台词过快） → fixes-and-skeletons.md。
  • 需要精确的取景/镜头/运动/灯光/音效术语 → camera-lighting-vocabulary.md。
若没有匹配的文件——仅完成步骤1-3即可。

Step 5 — apply the dramaturgy check and the three-detail check

步骤5 —— 执行叙事逻辑检查与三细节检查

Before returning anything, run both checks:
  • Dramaturgy check (
    dramaturgy.md
    §15): scene formula complete, three-detail check on every shot, three-jobs rule on every shot, motivated camera, readable geometry, five anchors named.
  • Three-detail audit (
    universal-rules.md
    §13): each shot owns environmental pressure + physical micro-action + sound or visual motif.
If any shot fails, fix before sending. This is the step the user has had to enforce repeatedly. Do not skip it.
在返回任何结果前，需执行两项检查：
  • 叙事逻辑检查（
    dramaturgy.md
    §15）：场景公式完整、每个镜头都通过三细节检查、每个镜头遵循三任务法则、镜头运动有动机、画面几何结构清晰可辨、五大锚点明确。
  • 三细节审核（
    universal-rules.md
    §13）：每个镜头都包含环境压迫+物理微动作+声音或视觉母题。
若任何镜头未通过检查，请先修正再发送结果。这一步是用户反复要求必须执行的，请勿跳过。

Output

输出格式

Choose the format the request actually asks for. Default to A if unclear.
  • A. Single prompt. One ready-to-copy prompt for one generation. Lead with model name + parameters in a short header.
  • B. Multi-clip prompts. Sequence of self-contained prompts, each repeating the full identity / style / continuity block (see 
    universal-rules.md
    U7).
  • C. Storyboard. Table — Time, Shot, Function, Action, Camera, Light, Sound, Emotion. Every row is a 14-field shot card from 
    dramaturgy.md
    §11, compressed.
  • D. Prompt audit. Given a user prompt, return: What works, What breaks generation, Missing direction, Continuity risks, Model-specific mismatches, Stronger version (rewritten prompt).
  • E. Director treatment. Core idea, Emotional arc, Visual motif, Rhythm, Camera language, Lighting, Sound, Ending image. (Treatment ≠ prompt.)
  • F. JSON (Veo only). Structured scene-by-scene continuity. See 
    veo.md
    .
Default output language follows the user. The final AI prompt itself goes in English unless the user asks otherwise — Seedance, Kling, and Veo all perform better in English.
选择与请求匹配的格式。若请求不明确，默认选择A。
  • A. 单一提示词。一个可直接复制使用的单镜头生成提示词。开头简短标注模型名称+参数。
  • B. 多片段提示词。一系列独立完整的提示词，每个提示词都重复完整的角色身份/风格/连贯性模块（详见
    universal-rules.md
    U7）。
  • C. 故事板。表格形式——时间、镜头、功能、动作、镜头调度、灯光、音效、情绪。每一行都是
    dramaturgy.md
    §11中14字段镜头卡的精简版。
  • D. 提示词审核。针对用户提供的提示词，返回：有效部分、影响生成的问题、缺失的指导、连贯性风险、模型不匹配点、优化后的提示词。
  • E. 导演阐述。核心创意、情感弧线、视觉母题、节奏、镜头语言、灯光设计、音效、最终画面。（导演阐述≠提示词）
  • F. JSON格式（仅Veo适用）。结构化的逐场景连贯性内容。详见
    veo.md
    。
默认输出语言遵循用户使用的语言。最终的AI提示词本身使用英文，除非用户另有要求——Seedance、Kling和Veo在英文提示词下表现更优。

Final response style

最终回复风格

Prefer: ready-to-copy prompts, clear section labels, production language, motivated camera and light direction, strict continuity blocks, model-specific syntax, direct fixes.
Avoid: long theory unless asked, academic lectures, vague inspiration, decorative jargon, "cinematic masterpiece" filler, prompts without camera and light, prompts without continuity, stacking more than two director references, abstract emotions without physical translation.
When in doubt about a model-specific detail — re-read the model file before writing the final prompt. It costs nothing and prevents bad output.
Author: Serge Shima (t.me/aimastersme · sergeshima.com · aimasters.me) · License: CC BY 4.0 — attribution required · Source: smixs/visual-skills
优先选择：可直接复制的提示词、清晰的章节标签、专业制作术语、有动机的镜头与灯光调度、严格的连贯性模块、模型专属语法、直接的修复方案。
避免：冗长的理论（除非用户要求）、学术式讲解、模糊的灵感描述、装饰性行话、“电影级杰作”这类空洞填充词、无镜头与灯光说明的提示词、无连贯性的提示词、堆叠超过两个导演参考、无具体动作支撑的抽象情绪描述。
若对模型专属细节存疑——在编写最终提示词前重新阅读模型文件。这不会花费任何成本，却能避免产出不合格的结果。
作者：Serge Shima (t.me/aimastersme · sergeshima.com · aimasters.me) · 许可证：CC BY 4.0 —— 需注明出处 · 来源：smixs/visual-skills