Dialogue Gaze Mapping

Community

geegl

dialogue-gaze-mapping

(1) 三人以上群戏需要交代空间关系；(2) 不能或不想用全景/建立镜头；(3) 多人对话场景中角色位置混乱

Overview

Publisher	geegl
Repository	`directorskills`
Skill name	`dialogue-gaze-mapping`
Stars	68
Forks	7
Bundled files	1
License	MIT
Links	Skill source Repository

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 Dialogue Gaze Mapping AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/geegl/directorskills/tree/main/output/books/master-shots-v2/dialogue-gaze-mapping
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/geegl/directorskills/tree/main/output/books/master-shots-v2/dialogue-gaze-mapping

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

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/master-shots-v2/dialogue-gaze-mapping .claude/skills/dialogue-gaze-mapping

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dialogue Gaze Mapping 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 Dialogue Gaze Mapping 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 Dialogue Gaze Mapping 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.

目光方向空间映射框架

R — 原文 (Reading)

克鲁尼目光望向一个方向，而房间里的其他人的目光都望向他。正是这些目光的方向让观众了解了每个人在房间中的位置。演员这种身体和目光的角度绝对不是无意而为之的。 — Kenworthy, 第4章 §4.2, p.g_0020

I — 方法论骨架 (Interpretation)

多人对话场景中最常见的问题不是"怎么切镜头"，而是"观众根本不知道谁在哪里"。传统的全景建立镜头可以解决这个问题，但它打断节奏、暴露空间、破坏紧张感。目光方向空间映射提供了一种更优雅的替代方案：用角色自己的目光方向作为观众的"GPS导航"。

核心机制很简单——主角望向房间（建立他是焦点），其他所有人望向他（通过视线汇聚告诉观众主角在哪里，以及其他人围绕他分布）。当一个新角色插话时，其他角色转身看他——这个转身动作同时交代了新说话者的位置和之前其他人的位置。

关键设计要点：(1) 目光方向必须是有意设计的，不能随演员自由发挥；(2) 有些角色的脸在画面中央，但目光偏向一侧——这种"偏斜注视"比正面注视更能突出凝视方向；(3) 身体和头的倾斜角度应与目光方向一致，形成"身体→目光→空间"的三重信息传递。

这个框架适用于所有多人对话场景，从三人到十人以上群戏都有效。它不仅能交代位置，还能暗示权力关系（谁被所有人注视=谁是焦点）和情感关系（谁在回避谁的目光）。

A1 — 书中的应用 (Past Application)

案例 1: 《十一罗汉》十人群戏的空间清晰化

问题: 超过10人参与的会话场景，需要让观众看清楚每个角色的方位
方法: 乔治·克鲁尼背对墙站着，目光望向屋子——暗示他是焦点。所有其他演员的目光都指向克鲁尼，有些角色的脸在画面中央但目光偏向一侧，更突出凝视方向。低角度仰拍两名演员，他们头的倾斜角度一致，证明他们都在听克鲁尼讲话
结果: 不需要全景镜头，观众就清楚地知道每个人的位置和对话流向

案例 2: 《十一罗汉》转身现人交代新说话者

问题: 马特·达蒙一开始在背景中未说话，观众不清楚他的位置。他突然插话时，观众不知道他在跟谁说
方法: 导演切到相反角度，让其他演员转身看达蒙——克鲁尼与达蒙有眼神交流，其他演员调整姿势看他。这既交代了达蒙的位置，也显示了其他人的位置
结果: 每个人的反应都能看到，相互位置很清晰，对话双方的眼神交流也明确了

A2 — 触发场景 (Future Trigger)

用户会在什么情境下需要这个 skill?

拍摄多人对话场景时不知道怎么交代角色空间关系
导演不想用全景镜头但需要让观众理解"谁在看谁"
群戏场景中某个角色突然插话，需要让观众快速定位此人
想在不打断对话节奏的前提下建立空间清晰度

语言信号

"群戏太乱了，观众不知道谁在哪"
"不想切全景，但需要交代位置"
"多人对话拍得像一堆人在聊天，没有层次"
"突然插话的角色，观众反应不过来"
"谁在看谁交代不清楚"

与相邻 skill 的区分

与 v06（摄影机高度即立场）的区别：v08 管理"空间位置信息"，v06 管理"观众认同哪一方"。两者可叠加：用目光方向交代位置（v08），用摄影机高度选择认同方（v06）

E — 可执行步骤 (Execution)

设计焦点角色与目光网络
- 确定场景中的焦点角色（通常是主角或当前说话者）
- 画出所有角色的目光方向线，确保它们汇聚于焦点角色
- 完成标准：每个角色的目光方向都指向焦点角色或正在说话的人
编排转身动作交代新说话者
- 当新角色开始说话时，让至少一个其他角色转身看他
- 转身应同时显示转身者的原位置和新说话者的位置
- 完成标准：观众能在不切全景的情况下，通过转身动作知道新说话者在房间的哪个方位
用偏斜目光强化方向信息
- 部分角色的脸可放在画面中央，但目光偏向一侧
- 头和身体的倾斜方向应与目光方向一致
- 完成标准：观众能通过目光方向（而非角色位置）推断出所有人在房间中的空间关系
- 🔴 判停条件: 若观众仍无法通过目光方向推断出所有人的空间关系，或转身动作未能同时交代转身者和新说话者的位置，回到步骤1重新设计目光网络

B — 边界 (Boundary)

不要在以下情况使用此 skill

两人对话场景：空间关系简单，不需要目光映射，过肩镜头或双人镜头就够了
悬疑片中故意隐藏某人位置：如果剧本要求观众不知道某角色在哪里，就不应该用目光方向暴露
角色正在隐藏情绪的场景：如果角色需要"面无表情"或"假装没看见"，强制设计目光方向会破坏表演的真实感

作者在书中警告的失败模式

反例：如果只用全景和每人近景的切换方式，"会让整个情节变得很无趣"，而且"会让观众搞不清楚谁在看着谁说话"（§4.1）
反例：当对话已经进行了一会儿，有人突然插话，如果"先前没有交代这个人的位置，观众就会被搞迷糊了"（§4.1）

作者的盲点 / 时代局限

Kenworthy 的案例全部来自好莱坞主流叙事电影，对非写实风格（如韦斯·安德森的对称构图）中的空间映射策略未做讨论
书中假设所有场景都需要"让观众知道谁在哪里"，但某些实验电影或艺术电影可能故意制造空间迷失感（如戈达尔后期作品），此时此框架不适用
目光方向设计在动画片中容易实现（角色完全可控），但在真人实拍中需要演员的高度配合，书中未讨论排练方法

容易混淆的邻近方法论

"转身现人"（§4.1）和"目光示人"（§4.2）是同一框架的两种子技巧：转身用于交代新说话者，目光方向用于持续交代所有人的位置
全景建立镜头是传统的替代方案，但会打断节奏并暴露空间——此框架正是为了避免这种打断而设计的

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.

test-prompts.json2 KB

Frequently asked questions

What does the Dialogue Gaze Mapping AI skill do?

(1) 三人以上群戏需要交代空间关系；(2) 不能或不想用全景/建立镜头；(3) 多人对话场景中角色位置混乱

Why use Dialogue Gaze Mapping on TypingMind?

Because you install it once and use it with any model. Dialogue Gaze Mapping 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 Dialogue Gaze Mapping in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/geegl/directorskills/tree/main/output/books/master-shots-v2/dialogue-gaze-mapping. 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 Dialogue Gaze Mapping?

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 Dialogue Gaze Mapping?

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

Is the Dialogue Gaze Mapping 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

React Sync

vercel

OrganizationPopular

Build local React changes in the bundle variants consumed by Next.js, sync them into a local Next.js checkout, and test the resulting integration. Use when working on React changes that need…

Add Uint Support

Add unsigned integer (uint) type support to PyTorch operators by updating AT_DISPATCH macros. Use when adding support for uint16, uint32, uint64 types to operators, kernels, or when user mentions…

Cuda Index Width

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…

Plan Change

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

Dialogue Gaze Mapping

Overview