Short Drama Director logo

Short Drama Director

Community
suihe1
short-drama-director

把剧本转成表演、场面调度、镜头覆盖、景别、机位、运镜与剪辑意图,产出可校验导演镜头包。用于导演方案、拍法、镜头诊断和分镜重构;只要求大纲、剧本或资产设定时不触发。

Overview

Publishersuihe1
Repositoryshort-drama-production
Skill nameshort-drama-director
Stars
184
Forks
24
Bundled files
8
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 8 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by suihe1 on GitHub. Read the source before you install it.

Installation

Install the Short Drama Director AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/suihe1/short-drama-production/tree/main/skills/short-drama-director
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/suihe1/short-drama-production.git /tmp/short-drama-production
mkdir -p .claude/skills
cp -r /tmp/short-drama-production/skills/short-drama-director .claude/skills/short-drama-director
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Short Drama Director in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Short Drama Director on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Short Drama Director is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

输入与创作权限

先读用户实际材料与目标,复用已确定的事实和规格;已有剧本、资产或分镜直接进入相关工作,不为流程完整重写上游。未授权的删线、合人、改变人物身份、主题、结局或重要表演意图,先展示原位置、具体方案与得失,再由用户选择;已授权的局部修正直接完成。

下面的类型经验、批次和创作预算是适配起点,不是用户接受过的创作要求。旧校验器可能仍将部分经验规则报为失败:区分实际数据/引用/模型接口错误与创作建议,说明不适用项,保留原稿;不伪造字段、不静默改戏或降低技术投产要求。总控可用时参考其 references/creative-agreement.md;独立任务按本段处理,不强制依赖总控。

Short Drama Director

把剧本中的戏剧行动,翻译成能拍、能剪、能生成的视听方案。先做导演判断,再做镜头;不要把景别词和运镜词随机贴在台词上。

本文件中的 references/... 与 scripts/... 均相对本 skill 目录。执行脚本时把工作目录设为本 skill 目录,输入与输出文件使用绝对路径;不要假设用户项目根目录恰好包含 scripts/。

必读与按需参考

开始导演设计前,完整阅读:

  • references/directing-workflow.md:拆戏、调度、镜头组织和导演复盘。
  • references/visual-grammar.md:景别、机位、镜头运动、轴线、构图、镜头衔接。
  • references/schema.md:director-package.json 的字段与质量门。

现实主义题材涉及交通、医疗、办公、公安司法、政务或工业流程时,同时完整阅读 ../short-drama-production/references/reality-grounding.md。先固定真实设备、空间拓扑和人流,再设计调度;不得用“电影感”填补不懂的现实流程。

只有需要 AI 视频生成提示词、模型适配或投产批次时,再读 references/ai-video-production.md。目标为 MiniMax H3 时必须同时使用官方 h3-prompt-writing skill:导演包提供调度、构图、机位、运镜、声音和参考职责,官方 skill 负责最终模式格式。指定模型与参考文档冲突时,以用户给定模型的官方文档为准,并记录采用的模式与假设。

输入边界

按以下优先级读取输入:

  1. script.json:最佳输入。保留原有集、场、节拍、台词与动作,不改写剧情事实。
  2. 剧本文本:先编号为集、场、源节拍,再进行导演设计。
  3. outline.json 或梗概:可以制作“导演预案”,但要把未落成的台词、动作和连续性标为假设;不要伪装成可直接拍摄的定稿。
  4. 已有分镜:进入诊断/重构模式,保留有效镜头,只改有明确理由的部分。

若缺少画幅、单集时长或生成模型,采用以下默认值并写进 assumptions:优先继承 production.json 和已批准输入;独立任务未指定时采用 16:9、24 fps、按输入目标时长、模型无关。模型无关方案默认后期 TTS;用户明确采用 H3 时,默认 h3-ref2va + h3-native-reference,主要说话角色缺少声音母版就列为缺失资产,不静默改成随机音色。缺失信息不阻断导演设计,除非不同选择会彻底改变叙事或交付形式。

核心工作流

1. 建立源节拍账本

使用脚本将上游 script.json 转成导演骨架:

bash
node scripts/director-kit.mjs seed path/to/script.json > director-package.json

每个源动作或台词生成稳定的 beatId。镜头中的 beatRefs 表示该镜头主要承载的节拍;跨镜继续的台词或声音只放入 audioCarryRefs。不漏拍、不凭空添拍,新增内容放入 inventedBeats 并说明必要性。

2. 先写“戏”,再写“拍法”

逐集明确:本集问题、冷开场承诺、关键转折、高潮、结尾悬念、情绪曲线。

逐场明确:谁想要什么、谁/什么阻碍、场内转折、价值变化、权力变化、可利用的空间关系。把抽象情绪改写成可见行为,例如“忍耐”变成“先把证据扣在掌心,再把手摊开”。

3. 设计场面调度

先定义人物位置、视线、行动路径、道具交接、进出方向、轴线和空间层次,再选择机位。调度必须制造或改变关系;人物没有行动,摄影机通常也不该无理由游动。

每场至少记录:

  • geography:观众需要理解的空间关系。
  • axis:主轴及越轴策略。
  • blocking:动作触发点与落位。
  • continuityIn / continuityOut:姿势、视线、道具、屏幕方向和情绪状态。

现实敏感场景还必须从 reality-audit.json 继承 mustHave、topology、flow 与 peoplePolicy。导演可以选择观看角度,不能把安检、就诊、办事或生产流程改造成另一行业的通用空间;背景人物也必须服从入口—操作—出口方向。

4. 用镜头组织信息与权力

每个镜头先填 dramaticPurpose,只能为了揭示、隐藏、强调、反应、对比、转移权力、建立空间或完成转场而存在。随后决定:

  • 景别与角度:观众离谁更近,谁掌握画面权力。
  • 构图与前后景:关系如何被空间可视化。
  • 镜头运动:由人物、信息或权力变化触发;必须有起点、触发、路径和终点。
  • 画面内运动:与摄影机运动分开设计,明确主体、道具和环境运动的起始状态、触发、发展与落点;静止机位不等于静止画面。
  • 焦段:服务距离感、透视和表演,不把“85mm”“电影感”当装饰词。
  • 切点:切在信息变化、动作峰值、视线转移或反应价值上,而不是平均切碎台词。
  • 节奏:按信息可读性分配停留,不平均分镜。要求提速时先缩短已读懂的建立与重复,不机械倍速,也不优先牺牲转折后的反应。
  • 屏幕/文件信息:先决定观众必须看清什么,再选择环境内观看、插入特写、全屏主观内容或后期合成;关键信息不能只缩在手机或电脑的小屏幕里。

镜头覆盖要围绕冲突设计。不要机械套“全景—中景—近景—特写”,也不要让每条台词自动获得一个正反打。

5. 划分生成片段与镜头

严格区分:

  • 场 scene:一段连续的戏剧行动。
  • 生成片段 clip:一次 AI 视频调用或一个可独立生产的连续片段。
  • 镜头 shot:剪辑中的一次连续观看。

先按戏剧信息与剪辑需要设计 shot 和覆盖关系,再按动作连续性、参考需求和提供方限制打包为 clip。代码使用 clip 容纳 shot 不代表导演先被 API 秒数决定拍法;打包需要改拍法时记录偏差。

6. 写提示词与声音方案

先固定 audioRoute:

  • h3-native-reference:H3 用固定人物声音母版生成新对白;固定角色的默认路线。
  • tts-guided-h3:先用 TTS 生成准确台词音频,再由 H3 复用/参考并生成表演。
  • h3-native-free:H3 自行生成声音,只用于临时样片或无固定身份的声音。
  • tts-post:模型只生成表演与可控环境声,台词交给后期;避免在视频模型提示中重复生成对白。
  • silent:无对白,仅画面或后期音乐设计。

再分别确定环境、拟音和音乐来源;多片段短剧默认后期统一配乐。模型提示词必须从结构化镜头字段派生;不要让提示词反过来成为唯一事实源。使用 H3 时严格遵守 references/ai-video-production.md 的模式合同。

7. 确定性验证与导演复盘

每次交付前运行:

bash
node scripts/director-kit.mjs validate director-package.json
node scripts/director-kit.mjs render director-package.json > director-shotlist.md

先清零结构错误,再处理警告。验证通过不等于导演成立;还需人工回答:

  1. 静音观看时,关系和权力变化是否看得懂?
  2. 去掉所有装饰性运镜后,是否反而更有力?
  3. 每个近景/特写是否留给真正的转折、证据或反应?
  4. 每一切是否改变信息、情绪或观看位置?
  5. 结尾最后一个画面是否把悬念具象化?
  6. 现实功能空间去掉风格词后,设备、岗位与人流是否仍能按真实流程工作,且不会被误认成相邻行业?
  7. 手机、电脑、票据或文件承载的关键信息,静音观看时是否真的看得清;信息镜头后是否有必要且不重复的反应?

若答案是否定的,优先修改调度和镜头目的,不要只加形容词。

交付物

默认交付:

  • director-package.json:唯一结构化事实源。
  • director-shotlist.md:便于导演、分镜师、剪辑和生成操作员评审。
  • 一段简短导演阐述:核心观看策略、最重要的三项选择、已知风险。

用户要求诊断时,不擅自覆盖原文件;输出问题、证据、影响和建议修法。用户要求生产时,才生成或更新上述文件。

制作交接

独立使用时,自检后主动打开当前报告并给绝对路径链接,说明本轮范围、检查重点和下一步;需要锁定内容时在对话中收取通过或修改结论。已有确认覆盖当前版本就不重复询问,打开页面或下载 JSON 不算批准。总控已接管时,由总控统一收取这次结论,不另开重复审批。当前内容、依赖或源图改变后,不因旧文件仍存在就跳过复核;输出新版本并保留原审阅笔记。

本项目的阶段职责、变更记录和交付顺序由 short-drama-production 的 references/company-workflow.md 统一维护;未安装总控时按本 skill 的输入和交付范围独立完成,不将总控变成硬依赖。

每次内容交付运行 validate;只有修改工具代码或遇到疑似工具回归时运行 scripts/selftest.mjs,不要求每次创作重跑开发测试。

涉及尚未授权的创作取舍时,给用户 2–3 个有具体差异的选项,说明收益、损失与推荐,允许保留原稿或自定义。模型先完成阅读、诊断和短样段,不把准备工作推给用户;已经明确授权的范围直接执行。未经用户选择,不把暂定片长预算升级成删词、删情绪段落的理由。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Short Drama Director AI skill do?

把剧本转成表演、场面调度、镜头覆盖、景别、机位、运镜与剪辑意图,产出可校验导演镜头包。用于导演方案、拍法、镜头诊断和分镜重构;只要求大纲、剧本或资产设定时不触发。

Why use Short Drama Director on TypingMind?

Because you install it once and use it with any model. Short Drama Director is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Short Drama Director in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/suihe1/short-drama-production/tree/main/skills/short-drama-director. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Short Drama Director?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Short Drama Director?

As many as you like. As long as a model supports skills, you can use Short Drama Director with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Short Drama Director AI skill free?

Yes. It is published on GitHub by suihe1 under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇