Directing Credible Impossible logo

Directing Credible Impossible

Community
geegl
directing-credible-impossible

可信、这个设定合理吗、观众会信吗、太假了、逻辑不通

Overview

Publishergeegl
Repositorydirectorskills
Skill namedirecting-credible-impossible
Stars
68
Forks
7
Bundled files
1
LicenseMIT
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.

  • 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 Credible Impossible 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-credible-impossible
  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-credible-impossible .claude/skills/directing-credible-impossible
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Directing Credible Impossible 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 Credible Impossible 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 Credible Impossible 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.

可信的不可能优于不可信的可能

R — 原文 (Reading)

在不可信的可能之事和可信的不可能之事二者中,诗人应该选择后者。 — Mackendrick(引述亚里士多德《诗学》),第 2 章, ~p.112

观众可以接受虚构的情境,只要在那个情境中角色的行为合乎逻辑。 — Mackendrick, 第 13 章

I — 方法论骨架 (Interpretation)

这条原则颠覆了大多数人对"可信"的直觉理解。通常人们认为"可信"等于"现实中可能发生",但麦肯德里克(经由亚里士多德)指出:可信度取决于虚构世界内部的逻辑一致性,而非外部现实的准确性。

所谓"可信的不可能",指的是一个在现实中不可能发生、但在虚构世界中完全自洽的情境。比如科幻电影中的时间旅行——物理上不可能,但只要电影自己设定的规则被严格遵守(如每次旅行必须付出某种代价),观众就愿意接受。

所谓"不可信的可能",指的是一个在现实中完全可能发生、但角色行为不符合他所处情境逻辑的情况。比如一部现实主义电影中,一个刚刚失去亲人的角色下一秒就开始讲笑话——这在现实中确实可能发生(人有各种应对悲伤的方式),但如果电影没有为此提供任何铺垫,观众会觉得"太假了"。

这个原则的操作性在于:检验标准不是"这在现实中会不会发生",而是"这个角色在这个世界中按照已建立的规则会不会这样做"。 一旦虚构世界打破了自己设定的规则,观众的信任就瞬间崩塌——这就是所谓的"世界观崩了"。

A1 — 书中的应用 (Past Application)

案例 1: 《维罗纳的爱情》玻璃工厂场景 (c32)

  • 问题: 如何让一个完全不现实的浪漫场景(用心形玻璃弹向心上人)变得令人信服?
  • 方法论的使用: 编剧普莱维尔构建了一个完整的玻璃工厂世界——年轻的匠人整天与玻璃为伴,他的技艺、工具和工作环境都被充分展示。在这个世界里,用钻石刀切心形玻璃不是"不可能的浪漫巧合",而是"一个匠人用他最熟悉的工具表达感情"
  • 结论: 场景在物理上不可能(玻璃不可能那样弹),但在角色的世界中完全可信——因为编剧先建立了规则,再在规则内行动
  • 结果: 这个场景成为"只有电影才能做到的叙事"的标志性案例

案例 2: 所罗门王故事的剧本改编 (c21)

  • 问题: 如何让一个《圣经》故事在现代语境中仍然可信?
  • 方法论的使用: 麦肯德里克没有让演员"披床单念圣经体",而是设计了当代布景,让所罗门王的故事在一个观众能认同的现代环境中上演。角色的行为逻辑完全按照故事内部的规则运作——假冒母亲的恐惧、年轻所罗门的智慧、旁观者的震惊,这些情感反应是跨时代的
  • 结论: 可信度不来自"历史还原",而来自"角色行为在情境内的自洽"
  • 结果: 成为全书最长的综合案例练习

A2 — 触发场景 (Future Trigger) ★

用户会在什么情境下需要这个 skill?

  1. 评估故事设定时:用户说"这个科幻/奇幻设定会不会太离谱"或"观众能接受这个前提吗"
  2. 诊断角色行为时:用户说"这个角色的转变太突兀了"或"观众会觉得这个决定不合理"
  3. 调试世界观一致性时:用户说"我之前设定的规则好像和这个情节矛盾了"

语言信号

  • "观众会信吗?"
  • "这太假了 / 太巧了 / 不合理"
  • "世界观崩了"
  • "角色不会这样做"
  • "这个设定能站得住脚吗?"

与相邻 skill 的区分

  • 与 p15(巧合制造麻烦而非解决困难)的区别:p15 处理的是"巧合"在叙事中的使用规范(只能制造麻烦不能解决困难),p06 处理的是更根本的"可信度"问题——一个设定或行为在虚构世界内是否自洽。一个"可信的不可能"可以包含巧合,只要巧合在世界观内是自洽的
  • 与 g18(模棱两可的精确区分)的区别:g18 处理的是"多义性"问题(一个情节有多种解读是否合理),p06 处理的是"一致性"问题(情节在单一解读下是否自洽)

E — 可执行步骤 (Execution)

  1. 明确虚构世界的规则
    • 完成标准:列出故事/作品已明确或隐含建立的世界观规则(物理法则、社会规范、角色能力边界等)
    • 判停条件:如果无法列出任何规则,说明世界观尚未建立,需要先补建规则再评估
  2. 检验被质疑的设定/行为是否符合规则
    • 完成标准:逐条对照世界观规则,标注该设定/行为是否违反任何已建立的规则
    • 判停条件:如果不违反任何规则→可信;如果违反了→需要修改设定或修改世界观规则
  3. 检验角色行为的内在动机
    • 完成标准:在已建立的角色性格和所处情境下,这个行为是否有足够的动机支撑?
    • 判停条件:如果动机不足→需要增加铺垫场景或修改行为;如果动机充分→行为可信
  4. 执行"观众信任"测试
    • 完成标准:假设一个对该类型作品有基本了解的观众,他是否会在这个节点产生"太假了"的反应?
    • 判停条件:如果预计观众会产生信任断裂→需要修改;如果观众可以接受→通过

B — 边界 (Boundary) ★

不要在以下情况使用此 skill

  • 纪录片或新闻报道:这些类型追求的是"事实准确"而非"虚构自洽",此原则不适用
  • 抽象实验作品:某些先锋电影刻意追求"不可信"的效果来挑战观众预期,用"自洽"来要求它们是范畴错误

作者在书中警告的失败模式

  • 把"现实可能"等同于"故事可信":很多编剧以为只要情节在现实中有可能发生就够了,但观众的信任不建立在"是否真实发生过"上,而建立在"角色在这个世界中是否按逻辑行动"上
  • 世界观规则的自相矛盾:一旦在某个场景中打破了自己设定的规则,整个幻觉就会崩塌。比如一部电影前半段建立了"这个世界没有魔法"的规则,后半段突然出现魔法——除非有充分的铺垫解释,否则观众的信任瞬间瓦解

反模式与常见错误

  • 把"自洽"等同于"无趣"——追求逻辑一致性不意味着放弃惊奇感,"可信的不可能"本身就是惊奇的来源
  • 事后修补世界观规则——为了让一个不合理的情节通过,在后续场景中强行添加新规则,观众会察觉到编剧在"补丁"
  • 混淆"角色自洽"与"角色可预测"——角色按已建立的规则行动不等于观众能猜到他会怎么做,自洽的角色仍然可以做出令观众惊讶但在事后看来合理的决定

作者的盲点 / 时代局限

  • 麦肯德里克的案例全部来自经典好莱坞/英国电影黄金时代,这些电影大多遵循线性叙事和现实主义美学。对于后现代作品(如《杀死比尔》的风格化暴力)、魔幻现实主义(如马尔克斯式的叙事)或游戏中的"规则即世界观"设计,此原则需要扩展——在这些语境中,"风格一致性"可能比"逻辑一致性"更重要
  • 亚里士多德的原始语境是古希腊悲剧,其"可信性"标准隐含了对"神意"的信仰。现代观众对"不可信"的容忍阈值可能因文化背景不同而有差异

容易混淆的邻近方法论

  • "悬置怀疑"的通俗理解("观众愿意相信任何东西"):这不是麦肯德里克的观点。观众的怀疑不是无条件搁置的——只有当虚构世界提供了足够的内部一致性时,观众才愿意搁置怀疑。一致性崩塌的瞬间,怀疑立刻恢复
  • "逻辑硬伤"的批评模式:此原则不等于"挑逻辑漏洞"。一个故事可以在宏观层面完全自洽但在微观细节上有瑕疵(如时间线计算错误),这不影响可信度。检验的核心是"角色行为在情境内的自洽性",而非"每个细节都完美无缺"

相关 skills

  • depends-on: f01("很久很久以前"故事构建框架——用于建立世界观规则)
  • contrasts-with: p15(巧合制造麻烦而非解决困难——巧合的使用必须在可信的世界观内才有效)
  • composes-with: g18(模棱两可的精确区分——多义性必须建立在每重含义都可信的基础上)

审计信息

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

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 Credible Impossible AI skill do?

可信、这个设定合理吗、观众会信吗、太假了、逻辑不通

Why use Directing Credible Impossible on TypingMind?

Because you install it once and use it with any model. Directing Credible Impossible 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 Credible Impossible in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/geegl/directorskills/tree/main/output/books/directing-masterclass/directing-credible-impossible. 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 Credible Impossible?

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 Credible Impossible?

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

Is the Directing Credible Impossible 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.

View all

Set up your own AI workspace now

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