quote-extractor

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

金句提取器 (Quote Extractor)

Quote Extractor

技能定位 (Skill Positioning)

Skill Positioning

类型:单一功能型 Skill(快捷入口)
核心功能:从文章中提取可直接引用的金句、对比表达、独特观点,建立写作素材库。
与 knowledge_auditor 的区别
  • ❌ 无准入审计(不判断配不配入库)
  • ❌ 无内容加工(不提取认知框架)
  • ✅ 专注于金句提取
  • ✅ 适合快速积累写作素材

Type: Single-function Skill (quick access)
Core Function: Extract directly quotable golden sentences, comparative expressions, and unique viewpoints from articles to build a writing material library.
Differences from knowledge_auditor:
  • ❌ No admission audit (does not judge whether it qualifies for storage)
  • ❌ No content processing (does not extract cognitive frameworks)
  • ✅ Focus on golden sentence extraction
  • ✅ Suitable for quickly accumulating writing materials

激活条件 (When to Use)

When to Use

当出现以下任一情况时,激活此技能:
  1. 用户明确要求"提取金句"、"摘录好句子"、"保存这些表达"
  2. 用户在读文章时说"这句话写得好"、"这个比喻很妙"
  3. 用户输入快捷指令:
    /extract-quotes
    /extract-quotes [文件路径]
不适用场景
  • 如果用户需要整理外部素材并入库 → 使用
    /kn
    (knowledge_auditor)
  • 如果用户想学习文章结构 → 使用
    /analyze-writing
    (writing_analyzer)

Activate this skill when any of the following situations occur:
  1. The user explicitly requests "extract golden sentences", "excerpt good sentences", "save these expressions"
  2. The user says "This sentence is well-written", "This metaphor is brilliant" while reading an article
  3. The user enters the shortcut command:
    /extract-quotes
    or
    /extract-quotes [file path]
Inapplicable Scenarios:
  • If the user needs to organize external materials and store them in the library → Use
    /kn
    (knowledge_auditor)
  • If the user wants to learn the article structure → Use
    /analyze-writing
    (writing_analyzer)

核心工作流 (Workflow)

Core Workflow

Step 1: 读取文章内容

Step 1: Read Article Content

  1. 获取输入
    • 如果用户提供文件路径:直接读取
    • 如果用户粘贴内容:使用粘贴的文本
    • 如果用户未提供:询问用户提供文件路径或粘贴内容
  2. 确认提取标准
    • 问用户:"你想提取什么类型的金句?"
      • 对比金句(A vs B 型表达)
      • 隐喻类比(抽象概念的生动比喻)
      • 反常识观点(颠覆常规认知的表达)
      • 行动号召(激励人心的收尾句)
      • 全部类型(默认)

  1. Obtain Input:
    • If the user provides a file path: Read directly
    • If the user pastes content: Use the pasted text
    • If the user provides neither: Ask the user to provide a file path or paste content
  2. Confirm Extraction Criteria:
    • Ask the user: "What type of golden sentences do you want to extract?"
      • Comparative Golden Sentences (A vs B type expressions)
      • Metaphor & Analogy (vivid metaphors for abstract concepts)
      • Counterintuitive Viewpoints (expressions that subvert conventional cognition)
      • Call to Action (inspiring concluding sentences)
      • All Types (default)

Step 2: 识别金句

Step 2: Identify Golden Sentences

根据以下标准筛选金句:
Screen golden sentences based on the following criteria:

标准1:独特性

Criterion 1: Uniqueness

  • ✅ 不是常见表达(如"要努力奋斗")
  • ✅ 有独特的视角或比喻
  • ✅ 让人眼前一亮
  • ✅ Not a common expression (e.g., "We must work hard")
  • ✅ Has a unique perspective or metaphor
  • ✅ Stands out and impresses

标准2:可引用性

Criterion 2: Quotability

  • ✅ 可以独立成句,脱离原文也能理解
  • ✅ 不需要上下文就能传达完整意思
  • ✅ 适合直接用在自己的文章中
  • ✅ Can stand alone and be understood without the original context
  • ✅ Conveys a complete meaning without context
  • ✅ Suitable for direct use in one's own articles

标准3:情感力量

Criterion 3: Emotional Impact

  • ✅ 有冲击力或共鸣感
  • ✅ 能让读者停下来思考
  • ✅ 有画面感或节奏感
  • ✅ Has impact or resonance
  • ✅ Makes readers pause and think
  • ✅ Has a vivid imagery or rhythmic flow

金句类型清单

Golden Sentence Type List

类型特征示例
对比金句A vs B 结构"考场要的是正确,市场要的是有用"
类比降维抽象→具象"你的精力不是灯泡,而是激光"
负面警示错误做法提醒"用前女友的方式面对现女友,你会倒霉"
行动号召动词开头"不是先学再做,而是先做再学"
反常识颠覆常规"任何不能在下周转化为行动的信息,都是对注意力的绑架"
数字承诺数字+效果"3个方法突破职场困境"

TypeCharacteristicsExample
Comparative Golden SentencesA vs B structure"Exams require correctness, while the market requires usefulness"
Analogy & SimplificationAbstract → Concrete"Your energy is not a light bulb, but a laser"
Negative WarningReminder of wrong practices"Treat your current girlfriend the way you treated your ex, and you'll be in trouble"
Call to ActionStarts with a verb"Don't learn first then act, act first then learn"
CounterintuitiveSubverts conventional wisdom"Any information that cannot be converted into action within a week is a hijacking of your attention"
Numeric CommitmentNumber + Effect"3 methods to break through workplace dilemmas"

Step 3: 提取与分类

Step 3: Extract and Classify

  1. 逐句扫描
    • 读取全文,识别符合标准的句子
    • 保留原始表达(不改写)
    • 标注所在段落位置(便于回溯上下文)
  2. 分类整理
    markdown
    ## 对比金句
    - "考场是既有的答案,要正确;市场是有用,要解决问题"
      [来源:第3段]
    
    ## 类比隐喻
    - "你用前女友的方式面对现女友,结果可想而知"
      [来源:开篇]
    
    ## 行动号召
    - "不是先学再做,而是先做再学"
      [来源:第5段]
  3. 质量筛选
    • 只保留3-10句(避免"囤积")
    • 优先选择最有冲击力的
    • 如果超过10句,询问用户"是否全部保存"

  1. Sentence-by-Sentence Scan:
    • Read the full text, identify sentences that meet the criteria
    • Retain the original expression (no rewriting)
    • Mark the paragraph position (for easy context retrieval)
  2. Classify and Organize:
    markdown
    ## Comparative Golden Sentences
    - "Exams require existing answers and correctness; the market requires usefulness and problem-solving"
      [Source: Paragraph 3]
    
    ## Metaphor & Analogy
    - "Treat your current girlfriend the way you treated your ex, and you can imagine the result"
      [Source: Opening]
    
    ## Call to Action
    - "Don't learn first then act, act first then learn"
      [Source: Paragraph 5]
  3. Quality Screening:
    • Keep only 3-10 sentences (avoid "hoarding")
    • Prioritize the most impactful ones
    • If more than 10 sentences are identified, ask the user "Do you want to save all of them?"

Step 4: 生成素材笔记

Step 4: Generate Material Notes

模板格式
markdown
---
type: 素材
class: 金句库
level: B
summary: [主题]相关金句素材
review_freq: 按需
source: [文章标题 / 来源]
tags: [内容创作, 金句素材, [主题关键词]]
create_date: [今天日期]
aliases: [[主题]金句, [主题]文案]
---
Template Format:
markdown
---
type: Material
class: Golden Sentence Library
level: B
summary: Golden sentence materials related to [Topic]
review_freq: On demand
source: [Article Title / Source]
tags: [Content Creation, Golden Sentence Materials, [Topic Keywords]]
create_date: [Today's Date]
aliases: [[Topic] Golden Sentences, [Topic] Copywriting]
---

使用说明

Usage Instructions

主题:[一句话说明这些金句的主题,如"职场思维转变"、"时间管理"、"知识管理"] 适用场景:[什么时候可以引用这些金句] 注意事项:引用时需注明出处(可标注"改写自XXX")

Topic: [One-sentence description of the topic of these golden sentences, e.g., "Workplace Mindset Shift", "Time Management", "Knowledge Management"] Applicable Scenarios: [When these golden sentences can be quoted] Notes: Indicate the source when quoting (can mark "Rewritten from XXX")

金句列表

Golden Sentence List

对比类

Comparative Category

[金句1]
  • 使用场景:[什么时候用]
  • 来源段落:[原文第X段]
[金句2]
  • 使用场景:[什么时候用]
  • 来源段落:[原文第X段]
[Golden Sentence 1]
  • Applicable Scenario: [When to use]
  • Source Paragraph: [Original Paragraph X]
[Golden Sentence 2]
  • Applicable Scenario: [When to use]
  • Source Paragraph: [Original Paragraph X]

类比隐喻类

Metaphor & Analogy Category

[金句3]
  • 使用场景:[什么时候用]
  • 来源段落:[原文第X段]
[Golden Sentence 3]
  • Applicable Scenario: [When to use]
  • Source Paragraph: [Original Paragraph X]

行动号召类

Call to Action Category

[金句4]
  • 使用场景:[什么时候用]
  • 来源段落:[原文第X段]

[Golden Sentence 4]
  • Applicable Scenario: [When to use]
  • Source Paragraph: [Original Paragraph X]

延伸思考

Extended Thinking

改写方向:[如何基于这些金句延伸出自己的表达] 组合使用:[哪几句可以组合在一起使用]

Rewriting Directions: [How to extend your own expressions based on these golden sentences] Combined Usage: [Which sentences can be used together]

参考来源

Reference Sources

  • 原文:[文章标题]
  • 提取日期:[今天日期]

---
  • Original Text: [Article Title]
  • Extraction Date: [Today's Date]

---

Step 5: 存量检索与去重

Step 5: Inventory Retrieval and Deduplication

  1. 查重:在
    E:\OBData\ObsidianDatas\3通用技能\内容创作\Attachment(素材库)
    目录下检索:
    • 关键词:主题关键词、类似表达
    • 检查是否存在相同主题的金句笔记
  2. 提案
    • 情形 A (追加模式):发现相同主题的金句笔记,建议追加到现有笔记(避免碎片化)
    • 情形 B (新建笔记):未检索到存量,或主题完全不同,新建笔记
  3. 归档位置
    E:\OBData\ObsidianDatas\3通用技能\内容创作\Attachment(素材库)\[主题]金句素材.md

  1. Duplicate Check: Retrieve in the directory
    E:\OBData\ObsidianDatas\3通用技能\内容创作\Attachment(素材库)
    :
    • Keywords: topic keywords, similar expressions
    • Check if there are existing golden sentence notes on the same topic
  2. Proposals:
    • Scenario A (Append Mode): If a golden sentence note on the same topic is found, suggest appending to the existing note (avoid fragmentation)
    • Scenario B (New Note Mode): If no inventory is found or the topic is completely different, create a new note
  3. Archiving Location:
    E:\OBData\ObsidianDatas\3通用技能\内容创作\Attachment(素材库)\[Topic] Golden Sentence Materials.md

Step 6: 执行与交付

Step 6: Execution and Delivery

  1. 询问用户确认
    • 展示提取的金句列表
    • 询问:"这些金句都保留吗?需要删减或补充吗?"
  2. 执行写入
    • 用户确认后,物理写入文件
    • 返回文件路径
  3. 后续建议
    • 提醒用户删除源文件(如果是从外部文章提取)
    • 建议定期回顾金句库(每月一次)

  1. Ask for User Confirmation:
    • Display the extracted golden sentence list
    • Ask: "Do you want to keep all these golden sentences? Do you need to delete or add any?"
  2. Execute Writing:
    • After user confirmation, physically write to the file
    • Return the file path
  3. Follow-up Suggestions:
    • Remind the user to delete the source file (if extracted from an external article)
    • Suggest reviewing the golden sentence library regularly (once a month)

交互风格 (Tone & Rules)

Interaction Style (Tone & Rules)

  1. 克制原则:严格控制数量(3-10句),避免"素材囤积"
  2. 原汁原味:保留原始表达,不改写(除非用户要求)
  3. 场景化:每句金句必须标注"使用场景"
  4. 拒绝嘴炮:必须使用
    Write
    工具物理写入文件

  1. Restraint Principle: Strictly control the quantity (3-10 sentences) to avoid "material hoarding"
  2. Original Flavor: Retain the original expression, no rewriting (unless requested by the user)
  3. Scenario-based: Each golden sentence must be marked with "Applicable Scenario"
  4. No Empty Talk: Must use the
    Write
    tool to physically write to the file

调用示例

Calling Examples

示例1:指定文件路径

Example 1: Specify File Path

/extract-quotes E:\OBData\ObsidianDatas\0收集箱日清\考察思维 vs 市场思维.md
/extract-quotes E:\OBData\ObsidianDatas\0收集箱日清\考察思维 vs 市场思维.md

示例2:粘贴内容

Example 2: Paste Content

/extract-quotes

[用户粘贴文章内容]
/extract-quotes

[User pastes article content]

示例3:实时提取

Example 3: Real-time Extraction

用户:这句话写得好:"你的精力不是灯泡,而是激光"
助手:好的,我帮你提取这句金句。请问这句话来自哪篇文章?主题是什么?

User: This sentence is well-written: "Your energy is not a light bulb, but a laser"
Assistant: Sure, I'll help you extract this golden sentence. May I ask which article this sentence is from? What is the topic?

金句质量自检清单

Golden Sentence Quality Self-Check List

在提取前,对每一句进行快速检查:
  • 独特性:不是常见表达?
  • 可引用性:脱离原文也能理解?
  • 情感力量:有冲击力或共鸣感?
  • 适用性:下周写文章时能用到?
如果4个标准都不满足 → 不提取。

Perform a quick check on each sentence before extraction:
  • Uniqueness: Is it not a common expression?
  • Quotability: Can it be understood without the original context?
  • Emotional Impact: Does it have impact or resonance?
  • Applicability: Can it be used in writing next week?
If none of the 4 criteria are met → Do not extract.

与其他 Skills 的配合

Cooperation with Other Skills

  • knowledge_auditor (
    /kn
    )
    :如果用户需要完整的审计+入库流程,转交给它
  • writing_analyzer (
    /analyze-writing
    )
    :如果用户在提取金句后说"想学习这篇文章的写作结构",推荐使用写作分析器
  • thought-mining (
    /thought-mining
    )
    :如果用户想基于金句写一篇新文章,推荐使用思维挖掘助手

  • knowledge_auditor (
    /kn
    )
    : If the user needs a complete audit + storage process, transfer to it
  • writing_analyzer (
    /analyze-writing
    )
    : If the user says "I want to learn the writing structure of this article" after extracting golden sentences, recommend using the writing analyzer
  • thought-mining (
    /thought-mining
    )
    : If the user wants to write a new article based on the golden sentences, recommend using the thought mining assistant

注意事项

Notes

  1. 版权意识:提醒用户引用时注明出处
  2. 避免囤积:如果用户频繁提取但从不使用,给出警告:"你已经积累了XX条金句,但最近3个月没用过。先用完再提取。"
  3. 定期清理:每季度提醒用户清理"从未被引用过"的金句
  1. Copyright Awareness: Remind the user to indicate the source when quoting
  2. Avoid Hoarding: If the user frequently extracts but never uses, issue a warning: "You have accumulated XX golden sentences, but haven't used any in the last 3 months. Use them up before extracting more."
  3. Regular Cleanup: Remind the user every quarter to clean up golden sentences that "have never been quoted"