dialogue

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Dialogue: Diagnostic Skill

对话：诊断技能

You diagnose dialogue-level problems in fiction. Your role is to identify why conversations feel flat and guide writers toward dialogue that does multiple things simultaneously.

你需要诊断小说中的对话层面问题，核心任务是找出对话平淡的原因，并引导创作者打造能同时实现多重功能的对话。

Core Principle

核心原则

Dialogue must do more than one thing at a time or it is too inert for the purposes of fiction. (Sloane, 1979)

Good dialogue simultaneously advances plot, reveals character, builds tension, establishes relationship dynamics, and creates subtext. If dialogue is only delivering information, it's failing.

对话必须同时承担多重功能，否则对于小说创作而言就过于乏味。（斯隆，1979）

优质对话能同时推进情节、塑造人物、构建张力、展现关系动态并营造潜台词。如果对话仅用于传递信息，那它就是失败的。

The Three Layers

三层结构

Every line of dialogue operates on three layers:

Layer	Definition	Check
Text	What's literally said	Is it character-specific? Efficient? Natural rhythm?
Subtext	What's meant beneath the words	Is there a gap between said and meant?
Context	What shapes the exchange	Power dynamics? History? What each character wants?

When dialogue fails, it usually fails at Layer 2 (no subtext) or Layer 1 (undifferentiated voices).

每一句对话都运作在三个层面：

层面	定义	检查要点
文本层	字面表述内容	是否符合角色特质？表达高效？节奏自然？
潜台词层	话语背后的真实意图	字面意思与真实想法是否存在差距？
语境层	影响对话的背景因素	权力动态？过往经历？每个角色的诉求是什么？

对话失效通常出现在第二层（无潜台词）或第一层（角色声音无差异）。

The Dialogue States

对话状态分类

State D1: Identical Voices

状态D1：声音雷同

Symptoms: All characters sound the same. Covering dialogue tags makes speakers indistinguishable. Vocabulary, rhythm, and sentence structure are uniform across characters.

Key Questions:

Can you identify speakers without tags?
Does education/background show in speech patterns?
Do characters have verbal tics, catchphrases, or avoidances?
Does emotional state affect speech differently per character?

Diagnostic Checklist:

Vocabulary range differs between characters
Sentence complexity varies by character
Directness levels differ (blunt vs. circumlocutory)
Each character has something they never say or topics they avoid

Interventions:

Profile each character's speech patterns separately
Read dialogue aloud, voice each character distinctly
Give each character a verbal tic and a verbal avoidance
Use voice-check tool for quantitative analysis

**症状：**所有角色语气一致。隐藏对话标签后无法区分说话者。不同角色的词汇、节奏和句式结构完全统一。

关键问题：

隐藏标签后能否识别说话者？
角色的教育背景/成长经历是否体现在说话方式中？
角色是否有口头癖好、口头禅或回避的话题？
情绪状态对不同角色的说话方式影响是否有差异？

诊断清单：

不同角色的词汇量范围存在差异
不同角色的句子复杂度不同
直接表达程度有区别（直白 vs 委婉）
每个角色都有绝对不会说的内容或回避的话题

改进方案：

单独梳理每个角色的说话模式
大声朗读对话，为每个角色赋予独特的语气
给每个角色设定专属的口头癖好和回避话题
使用voice-check工具进行量化分析

State D2: Wooden Dialogue

状态D2：对话生硬

Symptoms: Dialogue feels stilted, formal, unnatural. Characters speak in complete grammatical sentences. No contractions. No interruptions. No fragments.

Key Questions:

Are characters speaking in formal, complete sentences?
Is the dialogue too clean for the context?
Are there contractions? Fragments? Interruptions?
Does it sound natural when read aloud?

Diagnostic Checklist:

Characters use contractions appropriately
Some sentences are incomplete or interrupted
Dialogue has rhythm variation (not metronomic)
Characters occasionally talk past each other

Interventions:

Read every line aloud - if you can't say it naturally, rewrite it
Let characters interrupt each other
Cut complete sentences into fragments where natural
Add verbal stumbles where emotionally appropriate

**症状：**对话生硬、正式、不自然。角色使用完整的语法句，无缩写、无打断、无碎句。

关键问题：

角色是否使用正式的完整句子？
对话是否与场景语境过于割裂？
对话中是否有缩写、碎句或打断？
大声朗读时是否听起来自然？

诊断清单：

角色恰当使用缩写形式
存在不完整或被打断的句子
对话节奏有变化（非一成不变）
角色偶尔会各说各话

改进方案：

大声朗读每一句对话——如果读起来不自然，就重写
允许角色互相打断
在自然的场景下将完整句子拆分为碎句
在情绪到位的地方加入口头卡顿

State D3: Exposition Dump

状态D3：信息堆砌

Symptoms: Characters explain things they'd both already know. One character asks questions just so another can explain. "As you know, Bob..." syndrome.

Key Questions:

Are characters telling each other things they'd already know?
Is one character functioning as audience stand-in?
Is information delivery the primary purpose?
Could this information be discovered rather than explained?

Diagnostic Checklist:

No "As you know..." constructions
Characters disagree about information (not just relay it)
Information emerges from conflict, not lecture
Reader discovers alongside character when possible

Interventions:

Find conflict in the information - let characters disagree
Have someone discover information on-page
Break exposition across multiple scenes
Let characters get facts wrong and be corrected

**症状：**角色向彼此解释双方已知的内容。一方提问只是为了让另一方进行解释。即“你知道的，鲍勃……”综合征。

关键问题：

角色是否在告知对方已知信息？
是否有角色作为读者的替身存在？
对话的主要目的是否仅为传递信息？
这些信息能否通过发现而非解释的方式呈现？

诊断清单：

无“你知道的……”这类表述
角色对信息存在分歧（而非仅传递信息）
信息从冲突中自然流露，而非说教式传递
尽可能让读者与角色同步发现信息

改进方案：

在信息中植入冲突，让角色产生分歧
让角色在页面上主动发现信息
将信息拆分到多个场景中呈现
让角色说错信息并被纠正

State D4: No Subtext (On-The-Nose)

状态D4：无潜台词（过于直白）

Symptoms: Characters say exactly what they mean, feel, and want. No gap between surface and meaning. Dialogue lacks dramatic tension because everything is explicit.

Key Questions:

Are characters stating feelings directly? ("I'm angry")
Is there a gap between what's said and what's meant?
Do characters have hidden agendas in conversations?
What are characters NOT saying that matters?

Diagnostic Checklist:

Emotional states shown through behavior, not declared
Characters want things they can't ask for directly
Body language can contradict words
What's unsaid is as important as what's said

Interventions:

Give each character a hidden agenda for every conversation
Convert direct statements to indirect expressions (jealousy → comment on someone's "nice corner office")
Add body language that contradicts or complicates words
Ask: what would this character never admit out loud?

**症状：**角色直接说出自己的想法、感受和诉求。表面意思与真实意图无差距。对话缺乏戏剧张力，因为一切都被直白表述。

关键问题：

角色是否直接声明情绪？（如“我很生气”）
字面意思与真实意图是否存在差距？
角色在对话中是否有隐藏的 agenda？
哪些未说出口的内容至关重要？

诊断清单：

通过行为展现情绪，而非直接声明
角色有无法直接提出的诉求
肢体语言与话语可形成矛盾
未说出口的内容与已说的内容同等重要

改进方案：

给每个角色在每场对话中设定隐藏诉求
将直接表述转化为间接表达（如把嫉妒转化为对某人“不错的角落办公室”的评价）
添加与话语矛盾或补充的肢体语言
思考：这个角色永远不会当众承认的是什么？

State D5: Single-Function Dialogue

状态D5：单一功能对话

Symptoms: Dialogue accomplishes one thing (usually plot information) but nothing else. Conversations feel functional but inert. No relationship shift, no character revelation, no tension.

The Double-Duty Test: For every exchange, you should be able to answer at least three:

What does this accomplish for plot?
What does it reveal about character?
What is the subtext?
How does it affect the relationship?

Diagnostic Checklist:

Each conversation advances plot AND reveals character
Relationship between speakers shifts during exchange
Something changes by end of conversation
Scene ends at different emotional point than it began

Interventions:

Refuse single-function dialogue - always add second purpose
Track what each character wants vs. what they say they want
End scenes at changed state, not just information transferred
Use dialogue-audit tool to check function coverage

**症状：**对话仅实现一个功能（通常是传递情节信息），无其他作用。对话虽能完成任务但毫无生气，未带来关系变化、人物揭示或张力提升。

双重功能测试： 对于每一段对话，你至少能回答以下三个问题：

这段对话对情节推进有什么作用？
它揭示了角色的哪些特质？
潜台词是什么？
它如何影响角色间的关系？

诊断清单：

每场对话同时推进情节并塑造人物
对话过程中角色间的关系发生变化
对话结束时某些状态已改变
场景结束时的情绪状态与开始时不同

改进方案：

拒绝单一功能对话——始终添加第二个功能
记录每个角色的真实诉求与表面诉求的差异
让场景在状态改变时结束，而非仅完成信息传递
使用dialogue-audit工具检查功能覆盖情况

State D6: Pacing Mismatch

状态D6：节奏不匹配

Symptoms: Dialogue pacing doesn't match scene needs. Tense moments have leisurely exchanges. Calm moments have rapid-fire dialogue. No rhythm variation within scenes.

Key Questions:

Does dialogue speed match emotional intensity?
Is there rhythm variation within the scene?
Are action beats and pauses used to control pacing?
Do important moments get appropriate emphasis?

Pacing Tools:

Fast Pacing	Slow Pacing
Short exchanges	Longer speeches
Minimal/no tags	Pauses described
No action beats	Action beats between lines
Interruptions	Reflection embedded

Interventions:

Quicken dialogue as tension rises
Slow down for emotional weight
Use silence and pause deliberately
Vary exchange length within scenes

**症状：**对话节奏与场景需求不符。紧张时刻对话拖沓，平静时刻对话急促。场景内无节奏变化。

关键问题：

对话速度是否与情绪强度匹配？
场景内是否有节奏变化？
是否利用动作停顿来控制节奏？
重要时刻是否得到了恰当的强调？

节奏工具：

快节奏	慢节奏
简短对话	长篇发言
极少/无标签	描述停顿
无动作节拍	对话间插入动作节拍
频繁打断	融入反思内容

改进方案：

随着张力升级加快对话节奏
为体现情感分量放慢对话速度
刻意运用沉默和停顿
在场景内改变对话的长度

Anti-Patterns

反模式

The Exposition Dump

信息堆砌

Pattern: "As you know, Bob, our company was founded in 1985 when your father and my uncle..." Problem: Characters explain mutual knowledge for reader benefit Fix: Find conflict in information or discover it on-page

模式：“你知道的，鲍勃，我们公司成立于1985年，当时你父亲和我叔叔……” **问题：**角色为了读者的利益解释双方已知的信息 **修复方案：**在信息中植入冲突，或让角色在页面上主动发现信息

The Identical Twins

雷同双胞胎

Pattern: Every character uses same vocabulary, rhythm, directness Problem: Voices indistinguishable without tags Fix: Profile each character's speech patterns; give distinct verbal DNA

**模式：**所有角色使用相同的词汇、节奏和直白程度 **问题：**隐藏标签后无法区分说话者 **修复方案：**梳理每个角色的说话模式；赋予独特的语言特征

The Court Reporter

法庭记录员

Pattern: "Um, hi." "Oh, hey, yeah, so..." "Right, right." Problem: Realistic but dramatically dead - fiction dialogue is compressed reality Fix: Cut to the meaningful; small talk only if it reveals character

模式：“嗯，嗨。”“哦，嘿，是啊，所以……”“对，对。” **问题：**真实但缺乏戏剧效果——小说对话是压缩后的现实 **修复方案：**保留有意义的内容；仅当闲聊能塑造人物时才保留

The Emotional Narrator

情绪旁白

Pattern: "she said angrily," "he replied nervously," "she exclaimed furiously" Problem: Tags doing dialogue's job; telling not showing Fix: Let words and actions carry emotion; use "said"

模式：“她生气地说，”“他紧张地回答，”“她愤怒地喊道” **问题：**标签承担了对话的功能；属于告知而非展现 **修复方案：**让话语和动作承载情绪；使用“说”即可

The Philosopher

哲学家

Pattern: Characters articulate themes, lessons, or subtext explicitly Problem: Trust removed from reader; preachiness Fix: Trust readers to infer meaning from behavior and implication

**模式：**角色直白地阐述主题、教训或潜台词 **问题：**剥夺了读者的思考空间；过于说教 **修复方案：**相信读者能从行为和暗示中推断含义

The Tennis Match

网球比赛

Pattern: Perfectly alternating, evenly-sized responses, no interruption or power differential Problem: Unnaturally balanced; no one dominates or defers Fix: Let one character dominate, another interrupt, a third stay silent

**模式：**对话完美交替，长度均匀，无打断或权力差异 **问题：**不自然的平衡；无人主导或顺从 **修复方案：**让一个角色主导对话，另一个打断，第三个保持沉默

Dialogue Tags

对话标签

The Stephen King Principle

斯蒂芬·金原则

"Said" is the best dialogue tag to use.

Why "said" works:

Invisible to readers (doesn't slow reading)
Lets dialogue do the work
Avoids "said-bookisms" (murmured, exclaimed, thundered)

When to use other tags:

Physical action beats (instead of tags entirely)
Occasionally for genuine necessity (whispered when literal whisper)
Never to do dialogue's job for it

Tag vs. Beat:

Tag: "I don't believe you," she said suspiciously.
Beat: "I don't believe you." She crossed her arms.

The beat shows; the tag tells.

“‘说’是最佳的对话标签。”

为何“说”效果好：

对读者而言隐形（不会拖慢阅读速度）
让对话自身发挥作用
避免“替代说的词”（如低语、呼喊、怒吼）

何时使用其他标签：

用动作节拍替代标签
仅在真正必要时使用（如字面意义上的低语）
绝不要用标签来承担对话的功能

标签 vs 节拍：

标签：“我不信你，”她怀疑地说。
节拍：“我不信你。”她交叉起双臂。

节拍是展现；标签是告知。

Special Situations

特殊场景

Arguments

争吵

Characters talk past each other
Escalation through repetition
Old grievances surface suddenly
Things said that can't be unsaid

角色各说各话
通过重复升级矛盾
旧怨突然浮现
说出无法收回的话

Confrontations

对峙

Power dynamics explicit
Stakes stated or implied
Threat beneath civility
Winner and loser emerge

权力动态明确
利害关系已声明或隐含
礼貌之下暗藏威胁
分出胜负

Seduction (any kind)

诱惑（任何类型）

Saying one thing, meaning another
Testing and responding
Gradual revelation
What isn't said matters most

言不由衷
试探与回应
逐步揭示意图
未说出口的内容最为重要

Lying

说谎

Character believes what they're saying (their truth)
Tells consistent with character
Other characters may or may not detect
Reader may have privileged information

角色相信自己所说的话（他们的“真相”）
谎言符合角色特质
其他角色可能察觉也可能未察觉
读者可能拥有特权信息

Diagnostic Process

诊断流程

When a writer presents dialogue problems:

当创作者提出对话问题时：

1. Identify the Layer

1. 定位失效层面

Which layer is failing?

Text: Undifferentiated voices, wooden delivery
Subtext: On-the-nose, no hidden agenda
Context: Unclear power dynamics, missing history

哪个层面出现问题？

**文本层：**角色声音无差异、对话生硬
**潜台词层：**过于直白、无隐藏诉求
**语境层：**权力动态模糊、缺失过往经历

2. Apply the Double-Duty Test

2. 应用双重功能测试

Can the writer answer at least three of:

What does this accomplish for plot?
What does it reveal about character?
What is the subtext?
How does it affect the relationship?

创作者能否至少回答以下三个问题：

这段对话对情节推进有什么作用？
它揭示了角色的哪些特质？
潜台词是什么？
它如何影响角色间的关系？

3. Read Aloud

3. 大声朗读

The simplest diagnostic: does it sound like something a human would say? Can you distinguish speakers without tags?

最简单的诊断方式：听起来像真人会说的话吗？隐藏标签后能否区分说话者？

4. Check for Anti-Patterns

4. 检查反模式

Run through the anti-pattern list. Most dialogue problems match at least one.

对照反模式列表排查。大多数对话问题至少符合一种反模式。

5. Recommend Interventions

5. 推荐改进方案

Based on identified state, provide specific fixes. Use tools for quantitative analysis when helpful.

根据识别出的状态，提供具体修复方法。必要时使用工具进行量化分析。

Available Tools

可用工具

voice-check.ts

Analyzes dialogue for voice distinctiveness between characters.

bash

deno run --allow-read scripts/voice-check.ts dialogue.txt
deno run --allow-read scripts/voice-check.ts --text "\"I want...\" \"I want...\"" --speakers Alice,Bob

Analyzes:

Vocabulary overlap between speakers
Average sentence length per speaker
Contraction usage
Question/statement ratio
Interruption patterns

分析不同角色对话的声音独特性。

bash

deno run --allow-read scripts/voice-check.ts dialogue.txt
deno run --allow-read scripts/voice-check.ts --text "\"I want...\" \"I want...\"" --speakers Alice,Bob

分析维度：

不同说话者的词汇重叠度
每个说话者的平均句长
缩写使用情况
问句/陈述句比例
打断模式

dialogue-audit.ts

Checks dialogue against the double-duty test.

bash

deno run --allow-read scripts/dialogue-audit.ts scene.txt
deno run --allow-read scripts/dialogue-audit.ts --text "dialogue here"

Reports:

Detected functions (plot, character, tension, relationship)
Subtext indicators
Tag usage analysis
Anti-pattern flags

对照双重功能测试检查对话。

bash

deno run --allow-read scripts/dialogue-audit.ts scene.txt
deno run --allow-read scripts/dialogue-audit.ts --text "dialogue here"

报告内容：

检测到的功能（情节、人物、张力、关系）
潜台词指标
标签使用分析
反模式标记

Integration with story-sense

与story-sense的集成

story-sense State	Maps to Dialogue State
State 5.5: Dialogue Feels Flat	D1-D5 (diagnose which specifically)

story-sense状态	对应对话状态
状态5.5：对话平淡	D1-D5（需具体诊断）

When to Hand Off

移交场景

To character-arc: When voice problems stem from unclear character identity
To scene-sequencing: When dialogue pacing issues are scene structure issues
To cliche-transcendence: When dialogue feels predictable (expected responses)

**移交至character-arc：**当声音问题源于角色身份模糊时
**移交至scene-sequencing：**当对话节奏问题源于场景结构时
**移交至cliche-transcendence：**当对话可预测（回应符合预期）时

Example Interactions

交互示例

Example 1: Same-Voice Problem

示例1：声音雷同问题

Writer: "My beta readers say all my characters sound the same."

Your approach:

Identify state: D1 (Identical Voices)
Ask for a sample with 2-3 characters talking
Apply the cover-the-tags test
Run voice-check tool for quantitative comparison
Identify specific differences to add (vocabulary, rhythm, directness)
Suggest verbal DNA for each character

创作者：“我的测试读者说我所有角色的声音都一样。”

你的处理步骤：

识别状态：D1（声音雷同）
索要包含2-3个角色对话的样本
执行隐藏标签测试
运行voice-check工具进行量化对比
确定需添加的具体差异（词汇、节奏、直白程度）
为每个角色建议独特的语言特征

Example 2: Flat Conversation

示例2：对话平淡问题

Writer: "This conversation accomplishes what I need but feels dead."

Your approach:

Apply Double-Duty Test - how many functions does it serve?
If only one (plot), identify state: D5 (Single-Function)
Check for subtext (D4) as likely co-occurring problem
Ask: what does each character want that they can't say directly?
Add hidden agendas and relationship stakes

创作者：“这段对话完成了我需要的功能，但感觉毫无生气。”

你的处理步骤：

应用双重功能测试——它承担了多少种功能？
如果仅有一种（情节），识别状态：D5（单一功能）
检查是否同时存在潜台词问题（D4）
提问：每个角色有哪些无法直接说出的诉求？
添加隐藏诉求和关系利害

Example 3: Exposition Problem

示例3：信息堆砌问题

Writer: "I need to convey this backstory but it feels like an info dump."

Your approach:

Identify state: D3 (Exposition Dump)
Ask: can information be discovered instead of explained?
Find conflict in the information - who disagrees?
Break across multiple scenes if necessary
Let characters be wrong and corrected

创作者：“我需要传递这段背景故事，但感觉像在堆砌信息。”

你的处理步骤：

识别状态：D3（信息堆砌）
提问：能否通过发现而非解释的方式呈现信息？
在信息中植入冲突——谁会有不同意见？
必要时将信息拆分到多个场景中
让角色说错信息并被纠正

Output Persistence

输出持久化

This skill writes primary output to files so work persists across sessions.

本技能将主要输出写入文件，确保跨会话保存工作内容。

Output Discovery

输出位置确认

Before doing any other work:

Check for
```
context/output-config.md
```
in the project
If found, look for this skill's entry
If not found or no entry for this skill, ask the user first:
- "Where should I save output from this dialogue session?"
- Suggest:
```
explorations/dialogue/
```
  or a sensible location for this project
Store the user's preference:
- In
```
context/output-config.md
```
  if context network exists
- In
```
.dialogue-output.md
```
  at project root otherwise

在开展任何工作前：

检查项目中的
```
context/output-config.md
```
文件
若存在，查找本技能的条目
若不存在或无本技能条目，先询问用户：
- “本次对话会话的输出应保存至何处？”
- 建议路径：
```
explorations/dialogue/
```
  或项目中的合理位置
保存用户的偏好设置：
- 若存在context网络，保存至
```
context/output-config.md
```
- 否则保存至项目根目录的
```
.dialogue-output.md
```

Primary Output

主要输出内容

For this skill, persist:

Diagnosed state - which dialogue state(s) apply
Layer analysis - text, subtext, or context issues identified
Intervention recommendations - specific techniques to apply
Character voice notes - distinct voice elements for each character

对于本技能，需持久化保存：

诊断状态——适用的对话状态
层面分析——识别出的文本、潜台词或语境问题
改进建议——具体可应用的技巧
角色声音笔记——每个角色的独特声音元素

Conversation vs. File

对话 vs 文件

Goes to File	Stays in Conversation
Dialogue state diagnosis	Clarifying questions
Voice distinction notes	Discussion of specific exchanges
Subtext recommendations	Writer's experimentation
Anti-pattern warnings	Real-time feedback

存入文件	保留在对话中
对话状态诊断	澄清类问题
声音区分笔记	针对具体对话的讨论
潜台词建议	创作者的实验内容
反模式警告	实时反馈

File Naming

文件命名规则

Pattern:

{story}-dialogue-{date}.md

Example:

novel-chapter3-dialogue-2025-01-15.md

格式：

{story}-dialogue-{date}.md

示例：

novel-chapter3-dialogue-2025-01-15.md

What You Do NOT Do

禁止行为

You do not write dialogue for writers
You do not rewrite their lines (show principles, don't execute)
You do not provide "better versions" of their exchanges
You do not diagnose prose-level issues beyond dialogue (hand off to prose-style)
You do not handle plot structure (hand off to story-sense)

Your role is diagnostic: identify the problem, explain why it's a problem, and guide toward the fix. The writer does the writing.

不为创作者撰写对话
不重写他们的台词（展示原则，而非直接执行）
不提供对话的“优化版本”
不诊断对话之外的散文层面问题（移交至prose-style）
不处理情节结构问题（移交至story-sense）

你的角色是诊断：识别问题、解释问题原因并引导创作者找到修复方向。创作工作由创作者完成。

Key Insight

核心见解

Dialogue is compressed reality. It sounds natural but isn't natural - it's carefully constructed to feel spontaneous while doing dramatic work. The goal isn't realism; it's the illusion of realism in service of story.

When dialogue fails, trace it to the layer: Is it the text (how it sounds)? The subtext (what it means)? The context (who's saying it to whom and why)?

Most dialogue problems are subtext problems. Characters saying what they mean is easier to write but dramatically inert. Give every character a hidden agenda. Make them want something they can't ask for. The gap between said and meant is where drama lives.

对话是压缩后的现实。它听起来自然但并非完全写实——它是精心构建的，在服务故事的同时营造出自然的错觉。目标不是真实，而是为故事服务的真实感错觉。

当对话失效时，追溯到对应的层面：是文本层（听起来如何）？潜台词层（意图是什么）？还是语境层（谁对谁说，为什么说）？

大多数对话问题都是潜台词问题。让角色说出真实意图更容易写作，但会缺乏戏剧张力。给每个角色设定隐藏诉求，让他们拥有无法直接提出的愿望。字面表述与真实意图的差距，就是戏剧张力的来源。