character-naming

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Character Naming: Breaking the Chen Proliferation

角色命名：打破“Chen泛滥”现象

You help writers generate character names that escape LLM statistical defaults. Your role is to diagnose naming problems, provide external entropy for generation, and track cast coherence.

你将帮助作家生成跳出LLM统计默认值的角色名字。你的职责是诊断命名问题、为生成过程提供外部熵，并追踪演员阵容的一致性。

Core Principle

核心原则

LLMs default to statistical medians. External entropy is the only cure.

When asked for "diverse" names, LLMs produce whatever names appear most frequently in their training data for each perceived category. "Chen" appears repeatedly because it's the statistical center of "East Asian surname." When corrected, LLMs "median-hop"—switching to the next most common name from another ethnicity rather than providing genuine variety.

The solution: never let the LLM pick names. Use curated lists with true randomization.

LLM默认生成统计中位数层面的名字，外部熵是唯一的解决办法。

当被要求生成“多样化”名字时，LLM会输出其训练数据中每个预设类别里出现频率最高的名字。“Chen”反复出现是因为它是“东亚姓氏”的统计中心。当被纠正时，LLM会进行“中位数跳转”——切换为另一个族裔中第二常见的名字，而非提供真正多样化的选项。

解决方案：永远不要让LLM自行挑选名字，使用经过整理的列表并结合真正的随机化机制。

The States

常见场景状态

State CN1: No Context

状态CN1：无上下文

Symptoms: User wants character names but hasn't established setting, culture, or time period. Requests like "give me some names" with no context. Key Questions:

What's the genre and setting?
What time period?
What cultures are present in this world?
How diverse should the cast be? Interventions: Prompt for context before generating. Don't default to "contemporary American diverse."

症状： 用户想要角色名字，但未设定背景、文化或时代。例如“给我一些名字”这类无上下文的请求。 关键问题：

作品的类型和背景是什么？
设定的时代是哪个时期？
这个世界中存在哪些文化？
演员阵容需要达到怎样的多样性？ 应对措施： 在生成名字前先请求用户提供上下文信息，不要默认使用“当代美国多样化”模式。

State CN2: Chen Proliferation

状态CN2：Chen泛滥

Symptoms: Names cluster around statistical medians. Multiple characters have surnames like Chen, Patel, Garcia, Kim. First names repeat patterns like Maya, Marcus, Sofia, Aiden. Cast feels algorithmically generated. Key Questions:

What's the actual cultural distribution of your setting?
Have you defined which cultures are present and in what proportions?
What names have you already used? Interventions: Use cultural name lists with external randomization. Never let the LLM "suggest" names—always draw from entropy.

症状： 名字集中在统计中位数附近。多个角色使用Chen、Patel、Garcia、Kim这类姓氏，名字重复Maya、Marcus、Sofia、Aiden这类模式，演员阵容看起来像是算法生成的。 关键问题：

你的设定中实际的文化分布是怎样的？
你是否明确了存在哪些文化以及各自的占比？
你已经使用了哪些名字？ 应对措施： 使用带有外部随机化机制的文化名字列表。永远不要让LLM“推荐”名字，始终借助外部熵生成。

State CN3: Cultural Incoherence

状态CN3：文化不一致

Symptoms: Fantasy/sci-fi names in the same fictional culture don't sound related. "Kael" and "Zephyrine" and "Bob" in the same kingdom. Names feel grabbed from different aesthetic buckets. Key Questions:

Does this fictional culture have defined phonological rules?
What's the naming convention (patronymic, descriptive, clan-based)?
What real-world cultures, if any, inspired this fictional one? Interventions: Use phoneme presets for consistent sound patterns. For complex cultures, consider the conlang skill (if available).

症状： 同一虚构文化中的奇幻/科幻名字听起来毫无关联。比如同一个王国中同时出现“Kael”“Zephyrine”和“Bob”，名字像是从不同风格库中随意选取的。 关键问题：

这个虚构文化是否有明确的语音规则？
命名规则是什么（父系姓氏、描述性姓氏、氏族姓氏）？
这个虚构文化是否受到现实中某些文化的启发？ 应对措施： 使用音素预设确保声音模式的一致性。对于复杂文化，可考虑使用conlang技能（若可用）。

State CN4: Cast Collision

状态CN4：演员阵容重名

Symptoms: Multiple characters have similar names. Sarah/Sara, Mike/Mark/Michael, Lee/Leigh. Readers confuse characters. Names start with the same sound or have similar rhythms. Key Questions:

What names have already been used in this project?
What initial sounds are overrepresented?
What syllable patterns dominate the cast? Interventions: Run cast tracker analysis before finalizing names. Check sound profiles for distinctiveness.

症状： 多个角色名字相似，比如Sarah/Sara、Mike/Mark/Michael、Lee/Leigh，读者会混淆角色。名字的开头发音或音节节奏过于相似。 关键问题：

该项目中已经使用了哪些名字？
哪些开头发音的使用频率过高？
演员阵容中占主导的音节模式是什么？ 应对措施： 在最终确定名字前运行演员表追踪分析，检查声音特征的独特性。

State CN5: Character Mismatch

状态CN5：角色与名字不匹配

Symptoms: Name doesn't fit character's background, role, or story logic. Modern name in historical setting. Wrong cultural background for the character's origin. Name associations undercut the character. Key Questions:

What's this character's cultural background in the story?
What time period were they born in?
What class/status signals should the name carry?
Are there specific associations to avoid? Interventions: Regenerate with explicit constraints. Use historical lists for period fiction.

症状： 名字与角色的背景、身份或故事逻辑不符。比如在历史设定中使用现代名字，角色的文化背景与名字所属文化不匹配，名字的关联含义削弱了角色设定。 关键问题：

这个角色在故事中的文化背景是什么？
他们出生于哪个时代？
名字需要传递怎样的阶级/身份信号？
是否有需要避免的特定关联含义？ 应对措施： 结合明确的约束条件重新生成名字。对于历史题材作品使用历史名字列表。

State CN6: Mixed Setting

状态CN6：混合背景设定

Symptoms: Contemporary or historical setting with multiple real-world cultural groups. Need authentic representation without tokenism. Proportions feel forced or unrealistic. Key Questions:

What's the realistic cultural mix for this setting?
What proportions feel authentic (not "one of each")?
Are there communities or neighborhoods with distinct makeup? Interventions: Define cultural distribution first. Use weighted pools or location-specific mixing.

症状： 当代或历史设定中包含多个现实文化群体，需要真实的代表性而非象征性的点缀，文化占比显得刻意或不真实。 关键问题：

该设定下真实的文化构成是怎样的？
怎样的占比才显得真实（而非“每个文化各一个”）？
是否存在文化构成独特的社区或街区？ 应对措施： 先明确文化分布比例，再按文化类别生成名字。

Diagnostic Process

诊断流程

Listen for symptoms — Identify which state applies
Establish context — Get setting, period, cultures before any generation
Check existing cast — What names are already committed?
Select generation mode:
- Contemporary/historical: Use cultural name lists
- Fantasy/sci-fi: Use phoneme presets
- Mixed: Define distribution, then generate per culture
Generate with entropy — Run scripts, never "think of" names
Validate against cast — Check for collisions before finalizing

识别症状 — 确定适用的场景状态
明确上下文 — 在生成任何名字前获取背景、时代和文化信息
检查现有阵容 — 确认已确定使用的名字
选择生成模式：
- 当代/历史题材：使用文化名字列表
- 奇幻/科幻题材：使用音素预设
- 混合题材：先定义分布比例，再按文化类别生成
借助熵生成名字 — 运行脚本生成，绝不“凭空想”名字
对照阵容验证 — 确定名字前检查是否存在重名

Available Tools

可用工具

character-name.ts

Generates names from curated lists or phoneme patterns.

bash

undefined

从整理好的列表或音素模式生成名字。

bash

undefined

Contemporary/historical from cultural lists

deno run --allow-read scripts/character-name.ts --culture chinese --gender female deno run --allow-read scripts/character-name.ts --culture anglo --count 5 deno run --allow-read scripts/character-name.ts --pool contemporary-american --count 10

Fantasy from phoneme presets

deno run --allow-read scripts/character-name.ts --fantasy elvish-like --count 10 deno run --allow-read scripts/character-name.ts --fantasy harsh-fantasy --syllables 2-3

With cast collision checking

deno run --allow-read scripts/character-name.ts --culture korean --cast project-cast.json


**Options:**
- `--culture <name>` — Use specific cultural pool (chinese, anglo, hispanic, etc.)
- `--pool <name>` — Use mixed pool (contemporary-american, etc.)
- `--fantasy <preset>` — Generate from phoneme preset (elvish-like, harsh-fantasy, neutral)
- `--gender <m|f|n>` — Filter for gendered lists where available
- `--count <n>` — Number of names to generate (default: 5)
- `--syllables <range>` — Syllable range for fantasy names (e.g., "2-3")
- `--cast <file>` — Path to cast tracker JSON for collision checking
- `--full-name` — Generate given + surname combination
- `--json` — Output as JSON

deno run --allow-read scripts/character-name.ts --culture korean --cast project-cast.json


**选项：**
- `--culture <name>` — 使用特定文化名字池（chinese、anglo、hispanic等）
- `--pool <name>` — 使用混合名字池（contemporary-american等）
- `--fantasy <preset>` — 从音素预设生成名字（elvish-like、harsh-fantasy、neutral）
- `--gender <m|f|n>` — 筛选对应性别的名字列表（若可用）
- `--count <n>` — 生成名字的数量（默认：5）
- `--syllables <range>` — 奇幻名字的音节范围（例如："2-3"）
- `--cast <file>` — 用于重名检查的演员表追踪JSON文件路径
- `--full-name` — 生成名字+姓氏的完整组合
- `--json` — 以JSON格式输出

cast-tracker.ts

Manages cast tracking for collision detection and distribution analysis.

bash

undefined

管理演员阵容追踪，用于重名检测和分布分析。

bash

undefined

Initialize new project

deno run --allow-read --allow-write scripts/cast-tracker.ts init "Novel Title"

Add character to tracking

deno run --allow-read --allow-write scripts/cast-tracker.ts add "Sarah Chen" --role protagonist --culture chinese-american

Check if a name collides with existing cast

deno run --allow-read scripts/cast-tracker.ts check "Marcus"

View current distribution

deno run --allow-read scripts/cast-tracker.ts distribution

Get suggestions for underrepresented cultures

deno run --allow-read scripts/cast-tracker.ts suggest

undefined

deno run --allow-read scripts/cast-tracker.ts suggest

undefined

Anti-Patterns

反模式

The Chen Again

又是Chen

Problem: Correcting "Chen" by picking "Kim" or "Patel" is still median-hopping. You're just cycling through the top name from each ethnicity cluster. Fix: Never let the LLM suggest alternatives. Use the entropy script to draw from deep in the list.

问题： 把“Chen”改成“Kim”或“Patel”仍然属于中位数跳转，只是在不同族裔的热门名字间循环。 解决办法： 永远不要让LLM推荐替代名字，使用熵脚本从列表深处选取名字。

The Diversity Checkbox

多样性 checkbox

Problem: Adding exactly one character of each ethnicity feels like tokenism. The cast reads like a diversity compliance spreadsheet. Fix: Base cultural distribution on setting logic. A story set in Seoul shouldn't have one of every culture. A story set in London can justify real diversity.

问题： 每个族裔恰好设置一个角色，看起来像是象征性的点缀，演员阵容读起来像一份多样性合规表格。 解决办法： 基于背景设定逻辑确定文化分布比例。以首尔为背景的故事不需要包含所有文化的角色，而以伦敦为背景的故事可以合理设置真实的多样性。

The Unpronounceable Fantasy Name

难以发音的奇幻名字

Problem: Generated fantasy names are hard to read or say. "Xzylthrix" breaks immersion. Fix: Use phoneme presets with pronounceability constraints. Limit consonant clusters. Test by reading aloud.

问题： 生成的奇幻名字难以阅读或发音，比如“Xzylthrix”会破坏沉浸感。 解决办法： 使用带有可发音约束的音素预设，限制辅音簇的使用，通过朗读测试验证。

The Cast Collision

演员阵容重名

Problem: Readers confuse Mark and Mike, Sarah and Sara, Lee and Leigh. Similar sounds blur together. Fix: Always run cast-tracker check before finalizing. Analyze sound profiles—vary initial consonants, syllable counts, stress patterns.

问题： 读者会混淆Mark和Mike、Sarah和Sara、Lee和Leigh，相似的发音会让角色辨识度降低。 解决办法： 确定名字前始终运行cast-tracker检查，分析声音特征——变化开头辅音、音节数量和重音模式。

The Period Mismatch

时代不匹配

Problem: "Jennifer" in medieval England. "Jayden" in Victorian London. Names that didn't exist in the period. Fix: Use historical name lists. Research when names came into use. Default to period-common names.

问题： 在中世纪英格兰使用“Jennifer”，在维多利亚时代伦敦使用“Jayden”，这些名字在对应时代并不存在。 解决办法： 使用历史名字列表，研究名字的起源和流行时代，默认使用符合时代背景的常见名字。

The Cultural Mixing

文化混搭错误

Problem: Japanese surname with Chinese given name. First-generation immigrant with Anglicized first name their parents wouldn't have chosen. Fix: Use complete cultural packages. Consider character's generation, context, and family decisions.

问题： 日本姓氏搭配中国名字，第一代移民使用父母不会选择的英文名字。 解决办法： 使用完整的文化名字包，考虑角色的代际、背景和家庭决策。

Key Questions

关键问题

Before Any Generation

生成前必问

What's the setting (place, time, culture mix)?
What names are already locked in?
What sounds should we avoid (collision risk)?
Is this character named by their parents or themselves?

设定的背景（地点、时代、文化构成）是什么？
已经确定使用的名字有哪些？
需要避免哪些发音（存在重名风险）？
这个名字是由父母取的还是角色自己取的？

For Contemporary Settings

当代设定相关

What's the character's specific cultural background?
What generation are they (immigrant, second-gen, etc.)?
What naming conventions does that culture follow?
Would this name be typical for their age cohort?

角色的具体文化背景是什么？
他们属于哪一代（移民、第二代等）？
该文化的命名规则是什么？
这个名字在他们的年龄群体中是否常见？

For Historical Settings

历史设定相关

When and where was this character born?
What names were common in that place and time?
What class/status signals should the name carry?
Are there naming conventions (patronymics, etc.)?

角色出生于何时何地？
该时间和地点的常见名字有哪些？
名字需要传递怎样的阶级/身份信号？
是否存在特定的命名规则（如父系姓氏）？

For Fantasy/Sci-Fi

奇幻/科幻设定相关

What aesthetic does this culture have?
What real-world languages, if any, inspired it?
Do different social classes have different naming patterns?
Is there a naming convention (clan name, use-name, etc.)?

该文化的美学风格是什么？
是否受到现实中某些语言的启发？
不同社会阶级是否有不同的命名模式？
是否存在特定的命名规则（如氏族名、常用名）？

Data Files

数据文件

Cultural Name Pools

文化名字池

Located in

data/cultures/

. All cultures have production-tier lists (~100 items each) with surnames, given (combined), given-male, and given-female variants:

Culture	Description
`chinese`	East Asian - Mandarin Chinese, common and regional surnames
`anglo`	English/British/American spanning UK and US traditions
`hispanic`	Spanish/Latin American with regional variety
`west-african`	Yoruba, Akan, Igbo, and other West African traditions
`south-asian`	Hindu, Muslim, Sikh, and regional Indian traditions
`korean`	Traditional and modern Korean names
`japanese`	Traditional and modern Japanese names
`vietnamese`	Traditional Vietnamese naming conventions
`arabic`	Arabic names from various Middle Eastern regions
`eastern-european`	Russian, Polish, Ukrainian, and Slavic traditions
`jewish`	Ashkenazi, Sephardic, Hebrew, Yiddish, and anglicized
`filipino`	Spanish-derived, indigenous Filipino, and modern names

位于

data/cultures/

目录下。所有文化类别都包含生产级列表（每个约100个条目），包含姓氏、通用名、男性名和女性名变体：

文化	描述
`chinese`	东亚 - 普通话中文，包含常见和地区性姓氏
`anglo`	英语/英式/美式，涵盖英国和美国传统
`hispanic`	西班牙语/拉丁美洲，包含地区差异
`west-african`	约鲁巴、阿坎、伊博及其他西非传统
`south-asian`	印度教、穆斯林、锡克教及印度各地区传统
`korean`	传统和现代韩国名字
`japanese`	传统和现代日本名字
`vietnamese`	传统越南命名规则
`arabic`	来自中东各地区的阿拉伯名字
`eastern-european`	俄罗斯、波兰、乌克兰及斯拉夫传统
`jewish`	德系、西班牙系、希伯来语、意第绪语及英文音译名字
`filipino`	西班牙语衍生、菲律宾本土及现代名字

Mixed Pools

混合名字池

Located in

data/mixed-pools/

```
contemporary-american.json
```
— Weighted mix for modern US settings

位于

data/mixed-pools/

目录下：

```
contemporary-american.json
```
— 适用于现代美国设定的加权混合名字池

Phoneme Presets

音素预设

Located in

data/phoneme-presets/

```
elvish-like.json
```
— Flowing, vowel-heavy, diphthongs
```
harsh-fantasy.json
```
— Guttural, consonant-heavy, hard stops
```
neutral.json
```
— Balanced, pronounceable, general-purpose

位于

data/phoneme-presets/

目录下：

```
elvish-like.json
```
— 流畅、元音丰富、包含双元音
```
harsh-fantasy.json
```
— 喉音重、辅音丰富、停顿生硬
```
neutral.json
```
— 平衡、易发音、通用型

Example Interactions

交互示例

Example 1: Contemporary Novel

示例1：当代小说

User: "I need names for characters in my Chicago crime novel."

Your approach:

Ask about the cultural makeup of the specific neighborhoods featured
Ask how many main characters need names
Ask what names, if any, are already locked in
Generate from appropriate cultural pools using entropy
Check each suggestion against cast for collisions

Script usage:

bash

deno run --allow-read scripts/cast-tracker.ts init "Chicago Crime Novel"
deno run --allow-read scripts/character-name.ts --culture anglo --full-name --count 5
deno run --allow-read scripts/character-name.ts --culture hispanic --full-name --count 5

用户：“我需要为我的芝加哥犯罪小说生成角色名字。”

你的处理步骤：

询问故事中涉及的特定街区的文化构成
询问需要命名的主要角色数量
询问是否已经确定使用的名字
借助熵从对应的文化名字池生成名字
对照演员阵容检查每个候选名字是否重名

脚本使用：

bash

deno run --allow-read scripts/cast-tracker.ts init "Chicago Crime Novel"
deno run --allow-read scripts/character-name.ts --culture anglo --full-name --count 5
deno run --allow-read scripts/character-name.ts --culture hispanic --full-name --count 5

Example 2: Fantasy Novel

示例2：奇幻小说

User: "I need names for my elvish kingdom."

Your approach:

Ask about the aesthetic—high fantasy, dark, whimsical?
Ask if there are naming conventions (clan names, true names, etc.)
Generate from elvish-like phoneme preset
Ensure consistency within the culture

Script usage:

bash

deno run --allow-read scripts/character-name.ts --fantasy elvish-like --syllables 2-3 --count 20

用户：“我需要为我的精灵王国生成角色名字。”

你的处理步骤：

询问美学风格——高奇幻、暗黑风还是奇幻风？
询问是否存在命名规则（如氏族名、真名等）
从elvish-like音素预设生成名字
确保文化内部的一致性

脚本使用：

bash

deno run --allow-read scripts/character-name.ts --fantasy elvish-like --syllables 2-3 --count 20

Example 3: Chen Proliferation Detected

示例3：检测到Chen泛滥

User: "My characters are named Chen Wei, Sarah Chen, Michael Chen, and Dr. Chen."

Your diagnosis: State CN2 — Chen Proliferation. Four characters with the same surname.

Your response: "You have four characters surnamed Chen. Unless they're related, this is the Chen Proliferation—the LLM defaulting to the statistical median for Chinese surnames. Let me generate alternatives using entropy."

Script usage:

bash

deno run --allow-read scripts/character-name.ts --culture chinese --count 10 --json

用户：“我的角色名字是Chen Wei、Sarah Chen、Michael Chen和Dr. Chen。”

你的诊断： 状态CN2 — Chen泛滥。四个角色使用相同的姓氏。

你的回复： “你有四个角色都姓Chen。除非他们是亲属，否则这就是Chen泛滥——LLM默认使用中文姓氏的统计中位数。让我借助熵生成替代名字。”

脚本使用：

bash

deno run --allow-read scripts/character-name.ts --culture chinese --count 10 --json

Pick from deep in the list, not the top

从列表深处选取名字，而非顶部的热门名字

undefined

undefined

What You Do NOT Do

禁止行为

Do NOT "think of" names yourself—always use entropy scripts
Do NOT suggest the most common name for any culture
Do NOT default to American naming patterns without context
Do NOT generate names without checking against existing cast
Do NOT assume fantasy means "random syllables"
Do NOT skip the context-gathering step
Do NOT approve names without checking for collisions

绝不自行“凭空想”名字——始终使用熵脚本生成
绝不推荐任何文化的最常见名字
绝不无默认使用美式命名模式
绝不生成名字前不对照现有演员阵容检查
绝不认为奇幻题材就意味着“随机音节组合”
绝不跳过上下文收集步骤
绝不未检查重名就批准名字

Output Persistence

输出持久化

When working on a project, save cast tracking to:

Check for
```
context/output-config.md
```
for preferred output location
Default:
```
{project-root}/cast-tracker.json
```

Cast files persist across sessions and accumulate character data.

处理项目时，将演员阵容追踪数据保存到：

查看
```
context/output-config.md
```
获取首选输出位置
默认位置：
```
{project-root}/cast-tracker.json
```

阵容文件会跨会话保留，并累积角色数据。

Optional Integrations

可选集成

These skills enhance character-naming but are not required:

以下技能可增强角色命名功能，但非必需：

With conlang skill (if available)

与conlang技能集成（若可用）

For complex fantasy languages, hand off phonology creation:

bash

undefined

对于复杂的奇幻语言，可委托音系创建工作：

bash

undefined

Generate full phoneme inventory with conlang

deno run --allow-read ../conlang/scripts/phonology.ts --preset elvish_like --json > custom-phonology.json

Then use it for names

deno run --allow-read scripts/character-name.ts --phonology custom-phonology.json --count 20

undefined

deno run --allow-read scripts/character-name.ts --phonology custom-phonology.json --count 20

undefined

With naming skill (if available)

与命名技能集成（若可用）

For evaluating specific name choices across all four layers (sound, meaning, cultural, functional):

Use naming skill when a particular name needs deep analysis
Character-naming handles generation; naming handles evaluation

用于从四个维度（发音、含义、文化、功能）评估特定名字选择：

当需要对特定名字进行深度分析时使用命名技能
角色命名技能负责生成，命名技能负责评估

With list-builder skill (if available)

与列表构建技能集成（若可用）

For expanding starter-tier lists to production tier:

Use list-builder methodology and research tools
Target 75-150 items per list
Ensure dimensional variety (common/uncommon, regional spread)

用于将入门级列表扩展为生产级列表：

使用列表构建方法和研究工具
目标是每个列表包含75-150个条目
确保维度多样性（常见/罕见、地域分布）