TypingMindTypingMindThe best frontend for AI
Directing Odets Rewrite logo

Directing Odets Rewrite

Community
geegl
directing-odets-rewrite

(1) 两个角色在对话但感觉像聊天而非交锋；(2) 场景中信息是平铺直叙地交代而非在冲突中释放；(3) 需要将二人对话升级为多人互动以增加密度

Overview

Publishergeegl
Repositorydirectorskills
Skill namedirecting-odets-rewrite
Stars
68
Forks
7
Bundled files
1
LicenseMIT
Links
Skill sourceRepository
  • 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.

  • 1 bundled files

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

  • Open source

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

Installation

Install the Directing Odets Rewrite 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/geegl/directorskills/tree/main/output/books/directing-masterclass/directing-odets-rewrite
  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/geegl/directorskills.git /tmp/directorskills
mkdir -p .claude/skills
cp -r /tmp/directorskills/output/books/directing-masterclass/directing-odets-rewrite .claude/skills/directing-odets-rewrite
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Directing Odets Rewrite 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 Directing Odets Rewrite 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 Directing Odets Rewrite 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.

编剧修改的奥德兹法则

R — 原文 (Reading)

在人物交锋的场景里，要确保每个人物都带上足够的弹药。聪明的人物在交锋前通常会在脑海中演练若干攻防方案，他们不仅会考虑自己要说什么，还会考虑对方听到后可能会作何反应。 — Mackendrick, 第14章, ~p.118

I — 方法论骨架 (Interpretation)

奥德兹法则的核心思想是：好的交锋场景应该像一盘棋局，每个参与者都不是空手上场的。每个角色进入场景时都必须"带着弹药"——他们知道一些对方不知道的信息（脑子里有主意），拥有对方需要的资源（口袋里有钱），并且已经预判了对方可能的反应。

这个法则包含三个可操作的层面：

弹药准备：为每个角色设计至少一条独有的信息底牌。角色不是在"为说而说"，而是在带着目的交锋——他有对方想要的、不知道的、或害怕的东西。这些底牌不需要在场景开头就亮出，而是在交锋的精确时刻释放。

亮王牌（trump card）：当一方暂时占上风时，另一方释放出一个此前未露面的关键信息，形成突转。这个王牌必须是角色早已拥有、但一直在等待正确时机才使用的——它不能是"刚好想起"的巧合。

三角关系（triangulation）：将二人对话升级为三方或多方互动。引入"反衬人物"（foil）——一个第三方角色，他的存在使简单的正反对比变成更复杂的多方角力。参议员、经纪人、女伴——这些"配角"在场景中的功能不是"出场"，而是折射和放大主角之间的张力。

关键诊断标准：如果删掉场景中的某一方，另一方的行为是否毫无变化？如果是，说明"弹药"不够，交锋只是表面的。

A1 — 书中的应用 (Past Application)

案例 1: 《成功的滋味》二十一俱乐部场景的两版对比

  • 问题: 莱曼初稿中西德尼被饭店接待员拒于门外——冲突发生在弱者和无名小卒之间，张力有限。
  • 方法论的使用: 奥德兹修改版做了三层改造：(1) 让亨塞克本人（而非接待员）来完成拒绝——冲突双方的力量对比更悬殊；(2) 引入参议员、女孩和经纪人作为"反衬人物"，从不同角度折射亨塞克的权势（有效背景交代）；(3) 让西德尼被客户韦尔登当场解雇，增加绝望感——弹药从"被拒绝"升级为"被公开羞辱"。
  • 结论: 弹药越充足、三角关系越复杂、王牌释放越精准，场景的结构密度越高。
  • 结果: 从"对白驱动"到"结构驱动"的编剧升级路径——奥德兹版本的每个角色都带着各自的"弹药"进入场景。

案例 2: 制片人的背景交代建议被嵌入交锋

  • 问题: 制片人需要向观众解释新闻经纪人和专栏作家的权力关系——如何在不中断戏剧的情况下传递这些信息？
  • 方法论的使用: 奥德兹没有安排一段平淡的对话来解释关系，而是将这些信息嵌入西德尼与亨塞克的言语交锋中——亨塞克对经纪人的恶语相向自然地揭示了权力关系，同时又推进了戏剧张力。信息不是被"交代"的，而是在冲突中被"释放"的。
  • 结论: "弹药"的概念也包括背景信息——关键是你在什么时机、以什么方式打出来。
  • 结果: 成为"有效背景交代"方法论的核心教学案例。

A2 — 触发场景 (Future Trigger)

用户会在什么情境下需要这个 skill?

  1. 编剧写了一场对话场景但读起来像"信息交换"而非"交锋"，需要增加冲突升级感
  2. 创业者准备投资路演，需要预判投资人可能的质疑并设计应对策略（弹药准备）
  3. 产品经理设计用户与系统的"对抗"流程（如游戏对战、谈判模拟），需要让双方都有策略深度

语言信号

  • "这场戏太平了" "对话不像在交锋"
  • "角色好像在'交代'信息而非'争夺'什么"
  • "怎么让两人对话更有层次"

与相邻 skill 的区分

  • 与 f04（戏剧反讽操控法）的区别：f04 用的是"观众知道角色不知道的信息"制造张力，是单向的信息差。奥德兹法则制造的是"角色之间的信息差"——每个角色都带着对方不知道的底牌上场，是双向的
  • 与 f01（故事构建框架）的区别：f01 处理的是故事整体的逐步构建，奥德兹法则聚焦于单个交锋场景的内部结构增强

E — 可执行步骤 (Execution)

  1. 弹药盘点：为场景中的每个角色列出至少一条"独有信息"或"独有资源"

    • 完成标准：每个参与交锋的角色至少有一项对方不知道、需要、或害怕的东西
    • 判停条件：如果某个角色没有任何"弹药"，这个角色要么不应出现在场景中，要么需要被赋予底牌

  2. 王牌设计：为至少一个角色设计一个"精确时刻释放的王牌"

    • 完成标准：明确王牌的内容（什么信息）、释放时机（在对方自以为占上风时）、效果（制造突转）
    • 判停条件：王牌必须是角色"早已拥有"的，不能是场景中临时获得的——否则就是巧合而非策略

  3. 三角化：评估是否需要引入"反衬人物"

    • 完成标准：如果当前是纯二人对话且密度不足，引入至少一个第三方角色，该角色的存在必须改变原二人之间的力量对比或信息格局
    • 判停条件：第三方角色有独立的立场和动机，不是二人对话的"道具"

  4. 删减检验：尝试删掉每个角色，检查剩余角色的行为是否受影响

    • 完成标准：删掉任何一方后，剩余角色的行为会发生可见变化——说明每个角色在场景中不可替代
    • 判停条件：如果删掉某个角色后场景毫无变化，该角色要么需要更多弹药，要么需要被移除

B — 边界 (Boundary)

不要在以下情况使用此 skill

  • 独白场景或内心戏：这些场景的张力来自角色与自己的冲突，不涉及多方交锋
  • 纯粹的信息传递场景（如教学、新闻播报）：这些场景的目的是"告知"而非"争夺"，强行注入交锋结构会导致内容失真

作者在书中警告的失败模式

  • 反例 ce11（反派角色缺乏"冲突张力系统"）：设置了反派但反派与主角之间没有建立具体的、持续升级的冲突关系。反派只是一个"坏人"而非一个"带着弹药上场的对手"。
  • 反例 ce03（"为说而说"的背景交代）：当背景信息没有被嵌入冲突中、而是以平淡对话直接交代时，观众会意识到"作者在告诉我一些事情"，产生心理距离。

作者的盲点 / 时代局限

  • 奥德兹法则高度依赖角色之间的对话交锋，这在对白驱动的经典好莱坞中有效，但在视觉叙事优先的当代电影（如动作片、科幻片）中可能需要变形——将"弹药"从语言层面转化为视觉层面的策略对抗
  • 麦肯德里克没有讨论"弱势方如何用有限弹药对抗强势方"的策略——他的案例多为权力对等或弱者失败的场景

容易混淆的邻近方法论

  • "冲突设计"（ce11 语境下的三足鼎立冲突系统）：冲突系统是故事级别的结构设计，奥德兹法则是单个场景级别的执行工具
  • "活动 vs 动作"（f02）：f02 判断的是场景中有没有戏剧结果，奥德兹法则在"已有戏剧结果"的基础上增强其密度和升级感

相关 skills

  • depends-on: f19（主角濒危判断法——判断谁"最濒危"有助于确定谁的弹药最紧张、王牌释放最急迫）
  • contrasts-with: f07（期待与不确定的张力公式——f07 是微观张力诊断，f18 是场景结构增强工具）
  • composes-with: f16（背景故事当前化呈现法——奥德兹法则的核心应用之一就是将背景信息嵌入交锋而非独立交代）

审计信息

  • 验证通过: V1 ✓ / V2 ✓ / V3 ✓
  • 蒸馏时间: 2026-06-07

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 Directing Odets Rewrite AI skill do?

(1) 两个角色在对话但感觉像聊天而非交锋；(2) 场景中信息是平铺直叙地交代而非在冲突中释放；(3) 需要将二人对话升级为多人互动以增加密度

Why use Directing Odets Rewrite on TypingMind?

Because you install it once and use it with any model. Directing Odets Rewrite 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 Directing Odets Rewrite in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/geegl/directorskills/tree/main/output/books/directing-masterclass/directing-odets-rewrite. 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 Directing Odets Rewrite?

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 Directing Odets Rewrite?

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

Is the Directing Odets Rewrite AI skill free?

Yes. It is published on GitHub by geegl under the MIT 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.

Related AI Skills

View all
ruvnet logo

Wasm Gallery

ruvnet
CommunityPopular

Browse, publish, and install WASM agents from the community gallery

8.6K
72.7K
Instructions
View
ruvnet logo

Browser Extract

ruvnet
CommunityPopular

Extract structured data via stored browser-templates or one-shot DOM queries, with mandatory AIDefence PII + prompt-injection gates before content reaches the model

8.6K
72.7K
Instructions
View
ruvnet logo

Browser Record

ruvnet
CommunityPopular

Open a named, traced browser session into an RVF cognitive container with a ruvector trajectory recording every action

8.6K
72.7K
Instructions
View
ruvnet logo

Init Project

ruvnet
CommunityPopular

Initialize a new Ruflo project with MCP tools, hooks, and agent configuration. Use when setting up Ruflo in a fresh repo, or when the user says "init ruflo", "set up ruflo", or asks how to bootstrap…

8.6K
72.7K
Instructions
View

Set up your own AI workspace now

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