TypingMindTypingMindThe best frontend for AI
Directing Ambiguity Diagnosis logo

Directing Ambiguity Diagnosis

Community
geegl
directing-ambiguity-diagnosis

模糊/多义/开放性、这里是不是太模糊了、观众能理解吗、要不要解释得更清楚、开放式结局

Overview

Publishergeegl
Repositorydirectorskills
Skill namedirecting-ambiguity-diagnosis
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 Ambiguity Diagnosis 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-ambiguity-diagnosis
  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-ambiguity-diagnosis .claude/skills/directing-ambiguity-diagnosis
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Directing Ambiguity Diagnosis 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 Ambiguity Diagnosis 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 Ambiguity Diagnosis 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.

模棱两可的精确区分

R — 原文 (Reading)

模棱两可不意味着不清晰。当模棱两可包含着多重含义，而每一重含义都清晰时，这种模棱两可会引发观众的兴趣。 — Mackendrick, 第 6 章（编剧墙上的警句）, ~p.31

很多有才华的作家常常被"模糊两可"这个词所迷惑。他们以为"模糊两可"就是"含糊不清"，以为不给出明确的答案就是深刻。其实恰恰相反。 — Mackendrick, 第 4 章

I — 方法论骨架 (Interpretation)

"模糊"和"模棱两可"在日常用语中几乎同义，但麦肯德里克对它们做了严格的区分。"模糊"是无能的遮羞布——创作者自己不知道要说什么，所以用含混来冒充深度。"模棱两可"是高手的精密设计——创作者同时呈现两种或多种同样有力的解读可能性，让观众在理解之间挣扎。

诊断标准只有一个问题：这个场景/作品的多种解读中，每一种是否都足够清晰、有力、站得住脚？ 如果是——这是好的模棱两可，它产生深度。如果不是——这是混乱，它只产生困惑。

操作层面，检验方法是：（1）列出观众可能对这段内容产生的所有解读；（2）逐一检查每种解读是否有足够的文本/画面支撑；（3）如果至少有两种解读都站得住脚，且观众清楚"这里是有意的多义"——这是好作品；如果只有一种勉强站得住脚或没有一种特别有力——这是含糊不清，需要修改。

好模棱两可需要比直白叙述更高超的技巧，因为它要求每一条解读线都清晰。这就像是同时演奏两个旋律，每个旋律都必须完整有力——如果其中一个走调了，整体就变成了噪音而非和声。

A1 — 书中的应用 (Past Application)

案例 1: "模糊两可"的致命诱惑 (ce06)

  • 问题: 初学者把"模糊两可"误解为"含糊不清"，故意不给故事清晰的走向或结局
  • 方法论的使用: 麦肯德里克指出，真正的模糊两可是"同时呈现两种或多种同样有力的解读可能性"。但失败案例中，"同一场戏可以被解读为完全矛盾的含义，但没有一种解读特别有力"——这不是深度，是贫乏
  • 结论: 如果编剧说不出故事的主题，结局的"开放式"感觉是出于回避而非刻意设计，那就不是艺术性的模棱两可，而是能力不足
  • 结果: 被列为反面模式——"含糊不是深刻，精确才是力量"

案例 2: 清晰性优先原则 (f12)

  • 问题: 如何在追求深度的同时保持清晰？
  • 方法论的使用: "清晰就是传递关键信息，过滤非关键信息。要有极大的才智和洞见才能将重要的内容从混乱而过分复杂的材料中分离出来。"模棱两可必须建立在清晰之上——首先让每重含义都清楚表达，然后让它们并存产生深度
  • 结论: 清晰性是模棱两可的前提而非对立面。没有清晰性就没有真正的多义性
  • 结果: "清晰是拍电影最重要的品质，没有之一"——模棱两可是清晰的高级形态

A2 — 触发场景 (Future Trigger) ★

用户会在什么情境下需要这个 skill?

  1. 评估作品中"开放式结局"或"多层含义"是深度还是混乱
  2. 修改作品时被告知"太模糊了"，需要判断是应该更清晰还是保持多义
  3. 为品牌/产品设计故事时需要"有深度但不晦涩"的表达

语言信号

  • "这里是不是太模糊了？"
  • "观众/读者会不会看不懂？"
  • "开放式结局行不行？"
  • "这段很深，但不确定能不能被理解"
  • "主题到底是什么？我也说不清"

与相邻 skill 的区分

  • 与 p25（清晰性优先原则）的区别：p25 是"清晰性"的总原则——一切信息传递都应以清晰为目标；g18 是"模糊性"的诊断工具——当作品看起来"不清晰"时，判断它是"有意的多义"还是"无意的混乱"。p25 说"要清晰"，g18 说"在清晰的基础上，可以有层次"
  • 与 p06（可信的不可能优于不可信的可能）的区别：p06 检验的是"自洽性"——情节在世界观内是否逻辑一致；g18 检验的是"多义性"——情节是否同时承载多种清晰的解读。一个情节可以完全自洽（通过 p06）但只有一种解读（未达到 g18 的多义标准）

E — 可执行步骤 (Execution)

  1. 列出观众可能的解读
    • 完成标准：对被质疑的内容，列出至少 3 种可能的解读方式
    • 判停条件：如果只能列出 1 种解读，说明内容是清晰的（不需要模棱两可诊断）；如果列出 3 种以上，进入下一步
  2. 检验每种解读的文本支撑
    • 完成标准：每种解读是否在文本/画面中有足够的证据支撑？标注强/中/弱
    • 判停条件：如果至少有两种解读的支撑为"强"，这是好的多义性；如果所有解读的支撑都为"弱"，这是含糊不清
  3. 检验"有意 vs 无意"标识
    • 完成标准：作品中是否有信号表明这种多义性是刻意设计的？（如特定的构图、重复的意象、角色的凝视）
    • 判停条件：如果有明确的"有意设计"信号→好的模棱两可；如果没有任何信号暗示多义是刻意的→可能是无意的混乱
  4. 执行"观众共识"测试
    • 完成标准：不同观众是否能从同一内容中读出不同但各自清晰的含义？
    • 判停条件：如果所有人都觉得"看不懂"→混乱；如果一部分人读出 A、另一部分读出 B，且两种解读都令人信服→好的模棱两可

B — 边界 (Boundary) ★

不要在以下情况使用此 skill

  • 当作品的目标是纯粹的信息传递（如技术文档、新闻报道）时，"模棱两可"不是追求的目标，清晰性是唯一标准
  • 当作品刻意追求"不可解读"的效果时（如某些达达主义作品），此诊断标准不适用——这些作品的目的恰恰是挑战"有意义的解读"这一前提

作者在书中警告的失败模式

  • 把"含糊不清"误认为"深刻"（ce06）：初学者最常见的陷阱——故意不给清晰的走向或结局，以为这就是艺术性。结果"观众既没有被震撼也没有被感动，只留下了困惑"
  • 用"我不想把话说得太清楚"来掩盖创作困难：当编剧自己都不知道主题是什么时，"开放式"不是美学选择而是能力不足的遮羞布

作者的盲点 / 时代局限

  • 麦肯德里克的理论基于经典好莱坞叙事传统，其"清晰性"标准隐含了对"观众应该理解故事"的假设。但在后现代艺术和实验电影中，"不被理解"本身可以成为艺术体验的一部分（如大卫·林奇的作品）。此原则在面对这些极端案例时需要灵活运用
  • 他没有充分讨论文化差异对"清晰性"感知的影响——东方叙事传统中的"留白"和"意在言外"可能被视为"好的模糊"，但在他的西方框架中可能被诊断为"含糊不清"
  • "模棱两可"和"清晰"之间的界限在实践中并非总是明确的——同一段内容，对有经验的观众是"好的多义"，对普通观众可能是"看不懂"

容易混淆的邻近方法论

  • "深度 = 晦涩"的误解：g18 恰恰反对这个等式。深度来自"多重清晰含义的并存"，而非"单一含义的遮掩"
  • "留白"技法：留白是"不说"的艺术——故意省略信息让观众自行想象。g18 是"多说"的艺术——同时呈现多种清晰的含义。两者可以并用但本质不同
  • "象征"和"隐喻"：象征/隐喻是"一个东西代表另一个东西"的修辞手法，其目标是"用具体表达抽象"。g18 是"一个东西同时代表多个东西"的结构手法，其目标是"让多种解读共存"

相关 skills

  • depends-on: f12（清晰性优先原则——模棱两可必须建立在清晰性之上）
  • contrasts-with: ce06（"模糊两可"的致命诱惑——反面模式，模棱两可的失败形态）
  • composes-with: p06（可信的不可能优于不可信的可能——每重含义都必须在世界观内自洽）

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 Ambiguity Diagnosis AI skill do?

模糊/多义/开放性、这里是不是太模糊了、观众能理解吗、要不要解释得更清楚、开放式结局

Why use Directing Ambiguity Diagnosis on TypingMind?

Because you install it once and use it with any model. Directing Ambiguity Diagnosis 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 Ambiguity Diagnosis in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/geegl/directorskills/tree/main/output/books/directing-masterclass/directing-ambiguity-diagnosis. 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 Ambiguity Diagnosis?

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 Ambiguity Diagnosis?

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

Is the Directing Ambiguity Diagnosis 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
pytorch logo

Cuda Index Width

pytorch
OrganizationPopular

Choose 32-bit vs 64-bit index math in PyTorch CUDA kernels. Use when fixing large-tensor indexing overflows, deciding whether to use int64_t, canUse32BitIndexMath, CUDA_KERNEL_LOOP_TYPE, or…

31K
103.6K
Instructions
View
ruvnet logo

Plan Change

ruvnet
CommunityPopular

Turn a feature request into a minimal, file-level implementation plan before any code.

12.8K
97.4K
Instructions
View
paperclipai logo

Simplified English

paperclipai
OrganizationPopular

Write user-facing comments, plans, and documents in ASD-STE100 Simplified Technical English — short, unambiguous sentences with approved words and one meaning each — so readers understand them the…

16.2K
95.4K
Instructions
View
tt-a1i logo

Archify Review

tt-a1i
CommunityPopular

Review Archify issues, PRs, or code through value, cost, and impact to support evidence-based maintenance decisions. Use for issue triage, change reviews, and code quality assessments.

5.1K
75.3K
Instructions
View

Set up your own AI workspace now

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