list-builder

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

List Builder: Entropy List Curation Skill

列表构建器:熵列表整理技能

You build comprehensive, high-quality lists for creative randomization. These lists feed into entropy tools that inject unpredictability into story development.
你需要为创意随机化构建全面、高质量的列表。这些列表将为熵工具提供数据,为故事开发注入不可预测性。

Core Principle

核心原则

Good entropy lists have three properties:
  1. Size — Large enough (50-200+ items) to feel genuinely random
  2. Variety — Spans the full possibility space, not just obvious examples
  3. Specificity — Concrete enough to spark ideas, not vague categories
LLMs are good at research, categorization, and quality control. Scripts are good at storage and random selection. This skill bridges them.
优质熵列表具备三个特性:
  1. 规模 — 足够大(50-200+个条目),能带来真正的随机感
  2. 多样性 — 覆盖所有可能的范围,而非仅包含常见示例
  3. 具体性 — 足够具象以激发灵感,而非模糊的类别
LLMs擅长研究、分类和质量控制,脚本则擅长存储和随机选择。本技能将二者结合。

Dataset Maturity Levels

数据集成熟度等级

See references/dataset-quality-criteria.md for complete criteria.
LevelSizeStatusUse Case
Starter10-30Quick examplePrototyping, demos
Functional30-75Usable but limitedPersonal projects
Production75-150Ready for regular useClient work, published tools
Comprehensive150+Reference qualityDefinitive resource
Key metrics:
  • Size: Large enough for genuine randomness
  • Variety: Covers all relevant dimensions (see criteria doc)
  • Specificity: Concrete enough to spark ideas (20-60 char average)
  • Freshness: >30% items that surprise (not first-thought)
Current built-in lists are Starter/Functional level. This skill exists to build them up to Production.
完整标准请参考 references/dataset-quality-criteria.md
等级规模状态使用场景
Starter(入门级)10-30快速示例原型制作、演示
Functional(功能级)30-75可用但受限个人项目
Production(生产级)75-150可常规使用客户工作、已发布工具
Comprehensive(全面级)150+参考级质量权威资源
关键指标:
  • 规模: 足够大以实现真正的随机性
  • 多样性: 覆盖所有相关维度(详见标准文档)
  • 具体性: 足够具象以激发灵感(平均长度20-60字符)
  • 新颖性: >30%的条目具备惊喜感(非第一反应想到的内容)
当前内置列表为Starter/Functional级别。 本技能的存在就是为了将它们升级到Production级别。

List Quality Criteria

列表质量标准

What Makes a Good List Item

优质列表条目的特征

Good: "Elevator inspector" (specific, unexpected, sparks questions) Bad: "Office worker" (generic, expected, no hooks)
Good: "Self-storage facility at midnight" (specific time, atmosphere implied) Bad: "Building" (too vague to use)
Good: "They're solving a completely different case that uses same evidence" (specific collision mechanism) Bad: "They get in the way" (no mechanism, just effect)
优质: "电梯检查员"(具体、出人意料、引发疑问) 劣质: "办公室职员"(通用、常见、无吸引力)
优质: "午夜时分的自助仓储设施"(包含具体时间、隐含氛围) 劣质: "建筑物"(过于模糊,无法使用)
优质: "他们在处理另一个使用相同证据的完全不同的案件"(具体的冲突机制) 劣质: "他们碍事了"(仅说明效果,无机制)

Variety Dimensions

多样性维度

When building a list, ensure coverage across relevant dimensions:
Professions:
  • Industries (medical, legal, construction, arts, service, tech)
  • Status levels (entry-level to expert)
  • Visibility (public-facing vs. behind-scenes)
  • Unusual vs. common
  • Historical vs. modern vs. emerging
Locations:
  • Public vs. private
  • Indoor vs. outdoor
  • Urban vs. rural vs. suburban
  • Time of day implications
  • Emotional valence (creepy, mundane, sacred, liminal)
Character traits:
  • Positive vs. negative vs. neutral
  • Visible vs. hidden
  • Self-aware vs. blind spots
  • Stable vs. situational
构建列表时,需确保覆盖所有相关维度:
职业:
  • 行业(医疗、法律、建筑、艺术、服务、科技)
  • 职级(入门级到专家级)
  • 可见度(面向公众 vs 幕后)
  • 罕见性(不常见 vs 常见)
  • 时代性(历史 vs 现代 vs 新兴)
地点:
  • 公共 vs 私人
  • 室内 vs 室外
  • 城市 vs 乡村 vs 郊区
  • 时间暗示
  • 情感倾向(诡异、平淡、神圣、阈限)
人物特质:
  • 正面 vs 负面 vs 中性
  • 显性 vs 隐性
  • 有自知之明 vs 认知盲区
  • 稳定 vs 情境性

Research Process

研究流程

Step 1: Define the List

步骤1:定义列表

  • What category of things?
  • What will it be used for?
  • What makes an item useful vs. useless?
  • Target size (minimum 50, ideally 100+)
  • 列表的类别是什么?
  • 它将用于什么场景?
  • 什么让条目有用或无用?
  • 目标规模(最少50个,理想100+个)

Step 2: Seed with Obvious Examples

步骤2:用常见示例初始化

Start with 10-20 items that come to mind immediately. These are the "available" options—the ones that would occur to anyone. They're valid but not sufficient.
从10-20个第一时间想到的条目开始。这些是“易得”选项——任何人都会想到的内容。它们有效但不够。

Step 3: Research for Variety

步骤3:研究以扩展多样性

Use available sources to expand beyond obvious:
Kiwix/Wikipedia:
  • Category pages (e.g., "Category:Occupations")
  • List articles (e.g., "List of unusual deaths")
  • Related articles that branch into unexpected territory
Pattern: Dimensional expansion
  • Pick a dimension the seed list lacks
  • Research specifically in that dimension
  • Add 10-20 items that fill the gap
利用可用资源突破常见范围:
Kiwix/Wikipedia:
  • 分类页面(如“Category:Occupations”)
  • 列表文章(如“List of unusual deaths”)
  • 能延伸到意外领域的相关文章
模式:维度扩展
  • 找出初始列表缺失的维度
  • 针对性研究该维度
  • 添加10-20个填补空白的条目

Step 4: Filter for Quality

步骤4:过滤以保障质量

Remove items that are:
  • Too vague to be useful
  • Too similar to existing items
  • Culturally specific without being interesting
  • Requiring too much explanation
移除以下条目:
  • 过于模糊无法使用
  • 与现有条目过于相似
  • 具有文化特异性但无吸引力
  • 需要过多解释

Step 5: Format for Use

步骤5:格式化以便使用

Output as JSON array for use with entropy.ts:
json
{
  "list_name": [
    "Item one",
    "Item two",
    "Item three"
  ]
}
输出为JSON数组,供entropy.ts使用:
json
{
  "list_name": [
    "Item one",
    "Item two",
    "Item three"
  ]
}

Available Tools

可用工具

validate-list.ts

validate-list.ts

Analyzes a list for quality and variety.
bash
deno run --allow-read scripts/validate-list.ts list.json
分析列表的质量与多样性。
bash
deno run --allow-read scripts/validate-list.ts list.json

Check specific list in a file

检查文件中的特定列表

deno run --allow-read scripts/validate-list.ts data.json professions

**Reports:**
- Total count
- Duplicate check
- Average item length (too short = vague, too long = unwieldy)
- Variety assessment (if dimensions specified)
deno run --allow-read scripts/validate-list.ts data.json professions

**报告内容:**
- 总条目数
- 重复项检查
- 条目平均长度(过短=模糊,过长=难以使用)
- 多样性评估(若指定维度)

merge-lists.ts

merge-lists.ts

Combines multiple list sources, deduplicates, and formats.
bash
deno run --allow-read scripts/merge-lists.ts source1.json source2.json --output combined.json
合并多个列表来源,去重并格式化。
bash
deno run --allow-read scripts/merge-lists.ts source1.json source2.json --output combined.json

Research Prompts

研究提示词

When you need to research a specific category, use prompts like:
For professions: "Find 20 professions in [industry] that most people don't know exist. Focus on jobs that involve interesting access, specialized knowledge, or unusual working conditions."
For locations: "Find 20 specific locations (not categories) where important conversations might happen. Focus on places with built-in tension, time pressure, or unexpected intimacy."
For character flaws: "Find 20 specific false beliefs people hold about themselves that aren't obvious villain traits. Focus on beliefs that feel protective but are actually limiting."
当你需要研究特定类别时,可使用如下提示词:
针对职业: "找出[行业]中20个大多数人不知道存在的职业。重点关注涉及特殊权限、专业知识或不寻常工作条件的岗位。"
针对地点: "找出20个具体地点(而非类别),适合发生重要对话。重点关注自带张力、时间压力或意外亲密感的场所。"
针对人物缺陷: "找出20个人们对自己持有的非典型反派特质的错误信念。重点关注看似保护性但实际具有局限性的信念。"

Example: Building a Professions List

示例:构建职业列表

Starting Seed (obvious)

初始示例(常见)

  • Doctor, lawyer, teacher, police officer, firefighter...
  • 医生、律师、教师、警察、消防员...

Dimensional Gap Analysis

维度缺口分析

  • Missing: Niche technical jobs
  • Missing: Service jobs with unusual access
  • Missing: Jobs that involve secrets
  • Missing: Jobs most people don't know exist
  • 缺失:小众技术类职业
  • 缺失:拥有特殊权限的服务类职业
  • 缺失:涉及保密内容的职业
  • 缺失:大多数人不知道存在的职业

Research Expansion

研究扩展

Kiwix search: "List of occupations" → Category pages → specific unusual jobs
Add from research:
  • Elevator inspector (access to buildings)
  • Crime scene cleaner (aftermath, not crime)
  • Ethical hacker (knows vulnerabilities)
  • Cult deprogrammer (understands manipulation)
  • Foley artist (creates reality from nothing)
  • Patent examiner (sees innovations before public)
Kiwix搜索:"List of occupations" → 分类页面 → 具体的罕见职业
从研究中添加:
  • 电梯检查员(可进入各类建筑)
  • 犯罪现场清理员(处理事后现场,而非参与犯罪)
  • 道德黑客(知晓系统漏洞)
  • 邪教脱教引导员(了解操控手段)
  • 拟音师(用素材还原真实音效)
  • 专利审查员(比公众更早接触创新成果)

Quality Filter

质量过滤

Remove:
  • "Businessperson" (too vague)
  • "TikTok influencer" (too trendy, will date)
  • "Alchemist" (wrong era unless fantasy)
移除:
  • "商人"(过于模糊)
  • "TikTok网红"(过于潮流,易过时)
  • "炼金术士"(除非是奇幻场景,否则时代不符)

Final Check

最终检查

  • 80+ items? ✓
  • Multiple industries? ✓
  • Mix of status levels? ✓
  • Unexpected options? ✓
  • 条目数80+? ✓
  • 覆盖多个行业? ✓
  • 包含不同职级? ✓
  • 包含意外选项? ✓

Integration with Entropy Tools

与熵工具的集成

Lists built with this skill go into:
  • story-sense/data/
    for fiction-specific lists
  • Can be loaded via
    entropy.ts --file
Naming convention:
  • [category]-[specificity].json
  • Examples:
    professions-unusual.json
    ,
    locations-liminal.json
    ,
    objects-evidence.json
通过本技能构建的列表将被用于:
  • story-sense/data/
    存放小说专用列表
  • 可通过
    entropy.ts --file
    加载
命名规范:
  • [category]-[specificity].json
  • 示例:
    professions-unusual.json
    ,
    locations-liminal.json
    ,
    objects-evidence.json

What You Do

你的工作内容

  1. Clarify what list is needed and how it will be used
  2. Seed with obvious examples
  3. Research to expand variety
  4. Filter for quality
  5. Format as JSON
  6. Validate with tools
  7. Document the list's intended use
  1. 明确所需列表及其使用场景
  2. 用常见示例初始化列表
  3. 研究以扩展多样性
  4. 过滤以保障质量
  5. 格式化为JSON
  6. 用工具验证
  7. 记录列表的预期用途

What You Don't Do

你不需要做的事

  • Generate random items (that's what the entropy script does)
  • Create lists without research (leads to obvious-only items)
  • Include items that require extensive explanation
  • Prioritize quantity over quality (100 good items > 500 mediocre ones)
  • 生成随机条目(这是熵脚本的工作)
  • 无研究直接创建列表(会导致仅包含常见条目)
  • 包含需要大量解释的条目
  • 重数量轻质量(100个优质条目 > 500个平庸条目)

Output Persistence

输出持久化

This skill writes primary output to files so work persists across sessions.
本技能会将主要输出写入文件,确保跨会话保留工作成果。

Output Discovery

输出位置确认

Before doing any other work:
  1. Check for
    context/output-config.md
    in the project
  2. If found, look for this skill's entry
  3. If not found or no entry for this skill, ask the user first:
    • "Where should I save output from this list-builder session?"
    • Suggest:
      data/
      or
      story-sense/data/
      for entropy lists
  4. Store the user's preference:
    • In
      context/output-config.md
      if context network exists
    • In
      .list-builder-output.md
      at project root otherwise
在开展任何工作之前:
  1. 检查项目中是否存在
    context/output-config.md
  2. 若存在,查找本技能的相关配置
  3. 若不存在或无本技能的配置,先询问用户
    • "我应该将本次列表构建会话的输出保存到哪里?"
    • 建议保存位置:
      data/
      story-sense/data/
      (用于熵列表)
  4. 保存用户的偏好:
    • 若存在上下文网络,保存到
      context/output-config.md
    • 否则保存到项目根目录的
      .list-builder-output.md

Primary Output

主要输出

For this skill, persist:
  • The list itself - JSON format for entropy.ts use
  • Research sources - where items came from
  • Dimensional analysis - what variety dimensions are covered
  • Usage documentation - what the list is for
对于本技能,需持久化保存:
  • 列表本身 - 供entropy.ts使用的JSON格式
  • 研究来源 - 条目的获取渠道
  • 维度分析 - 覆盖的多样性维度
  • 使用文档 - 列表的预期用途

Conversation vs. File

对话与文件的分工

Goes to FileStays in Conversation
Final list (JSON)Discussion of list purpose
Research sourcesIteration on items
Quality analysisReal-time feedback
DocumentationCategory refinement
存入文件留在对话中
最终列表(JSON格式)关于列表用途的讨论
研究来源条目的迭代过程
质量分析实时反馈
文档类别的细化

File Naming

文件命名规则

Pattern:
{category}-{specificity}.json
Example:
professions-unusual.json
格式:
{category}-{specificity}.json
示例:
professions-unusual.json