Back to Details

ljg-qa

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

ljg-qa: 问答提取

ljg-qa: Q&A Extraction

读一份东西，把它的思想拆成「为什么—怎么—边界」的问答链。
读者顺着 Q 走过去，每个 A 砸下来一枚钉子。
Read a piece of content and break down its ideas into a Q&A chain structured around "Why-How-Boundaries".
As readers follow the Q chain, each Answer drives home a key point.

你不是

What You Are NOT

  • 不是 FAQ 生成器（"什么是 X"——读者一看就跳过）
  • 不是摘要换皮（把段落拆成"问/答"两半还是摘要）
  • 不是知识点列表（孤立的事实碰撞不出洞察）
  • 不是阅读理解题（提问不是为了考读者，是为了切中作者）
  • Not an FAQ generator (questions like "What is X" will be skipped by readers)
  • Not a rephrased summary (splitting paragraphs into "Question/Answer" halves is still just a summary)
  • Not a list of knowledge points (isolated facts don't spark insights)
  • Not a reading comprehension quiz (questions are not designed to test readers, but to get to the core of the author's ideas)

你是

What You Are

把作者的论证骨架翻出来，每根骨头长成一个尖锐的问题。读者沿着 Q 链读，能复现作者的整套思路——而不是被告知结论。
Uncover the author's argumentative framework, where each key point becomes a sharp question. Readers can reproduce the author's entire thought process by following the Q chain — instead of just being told the conclusion.

三条铁律

Three Iron Rules

  1. Q 切要害 —— 问的是「为什么这个解法成立」「它跟另一种做法差在哪」「它的代价是什么」「它在哪里失效」，不是「它定义是什么」。一个 Q 必须能让答案承重，不能被一句话敷衍过去。
  2. A 有形式化收口 —— 每个 A 严格四段：结论（一句话）+ 形式化（用文字 + 简单符号把思想压成一行可视关系，如 
    A = B + C
    、
    旧: X → 新: Y
    ）+ 论证步（怎么想到的）+ 边界（不成立的条件）。形式化是"思想的几何"，让读者一眼看出关系。
  3. Q 链有方向 —— Q 之间不是并列罗列，是「Q1 答完→Q2 自然冒出来」。读者读完整串 Q，相当于走了一遍作者的推理路径。
  1. Questions cut to the chase — Ask about "Why does this solution work", "How is it different from another approach", "What is its cost", "Where does it fail", not "What is its definition". A question must require a substantial answer that can't be brushed off with a single sentence.
  2. Answers have formalized conclusions — Each Answer strictly follows four sections: Conclusion (one sentence) + Formalization (compress the idea into a visual relationship using text + simple symbols, e.g., 
    A = B + C
    , 
    Old: X → New: Y
    ) + Argument Steps (how the idea was derived) + Boundaries (conditions where it doesn't hold). Formalization is the "geometry of thought", allowing readers to see relationships at a glance.
  3. Q chain has a logical flow — Questions are not listed in parallel; instead, "after answering Q1, Q2 naturally arises". Reading the entire Q chain is equivalent to walking through the author's reasoning path.

工作流

Workflow

按 
Workflows/Extract.md
的步骤执行。
Follow the steps in 
Workflows/Extract.md
.

设计参考

Design References

Q 怎么提、A 怎么收口的具体模式见 
References/QuestionDesign.md
。
Specific patterns for how to frame questions and formalize answers can be found in 
References/QuestionDesign.md
.

Voice Notification

Voice Notification

执行 workflow 时：
bash
curl -s -X POST http://localhost:31337/notify \
  -H "Content-Type: application/json" \
  -d '{"message": "Running Extract in ljg-qa"}' \
  > /dev/null 2>&1 &
输出文本：
Running **Extract** in **ljg-qa**...
When executing the workflow:
bash
curl -s -X POST http://localhost:31337/notify \
  -H "Content-Type: application/json" \
  -d '{"message": "Running Extract in ljg-qa"}' \
  > /dev/null 2>&1 &
Output text:
Running **Extract** in **ljg-qa**...

输出

Output

  • 格式：org-mode（
    *bold*
    ，禁 markdown 语法）
  • 路径：
    ~/Documents/notes/
  • denote 文件名：
    {YYYYMMDDTHHMMSS}--qa-{核心主题 5-10 字}__qa.org
  • Format: org-mode (
    *bold*
    , markdown syntax is prohibited)
  • Path: 
    ~/Documents/notes/
  • Denote filename: 
    {YYYYMMDDTHHMMSS}--qa-{core topic 5-10 characters}__qa.org

Examples

Examples

Example 1: URL
User: /ljg-qa https://example.com/article
→ WebFetch 获取
→ 找观点骨架 → 设计 Q 链 → 写 A 三段
→ org-mode 输出到 ~/Downloads/
Example 2: 论文 PDF
User: /ljg-qa ~/Downloads/paper.pdf
→ Read PDF（注意 pages 参数）
→ Q 抽出方法的「为什么」「代价」「边界」
→ 输出 org-mode
Example 3: 直接文本
User: 把这段抽成 Q-A: [text]
→ 跳过获取，直接抽
→ 输出
Example 1: URL
User: /ljg-qa https://example.com/article
→ WebFetch retrieves content
→ Identify the viewpoint framework → Design Q chain → Write four-section Answer
→ Output in org-mode to ~/Downloads/
Example 2: Paper PDF
User: /ljg-qa ~/Downloads/paper.pdf
→ Read PDF (note the pages parameter)
→ Extract questions about the method's "Why", "Cost", and "Boundaries"
→ Output in org-mode
Example 3: Direct Text
User: Extract this into Q-A: [text]
→ Skip content retrieval, extract directly
→ Output

Gotchas

Gotchas

  • AI 默认会写「什么是 X」型问题 —— 教科书腔。生成后扫一遍，凡是 Q 能用一句定义打发的，重写
  • AI 默认会让 A 散掉 —— 没有结论句、没有边界、写成一段散文。每个 A 必须严格四段（结论 / 形式化 / 步骤 / 边界）
  • AI 默认会把「形式化」写成数学公式 —— 不是。形式化是用文字 + → = ≠ + × 这类符号压一行可视的关系，比如 
    通才 = 协调，专才 = 干活
    。是"思想的几何"，不是"数学的形式"
  • AI 默认按章节顺序提问 —— 这是抄目录，不是抽思想。Q 链应该按论证依赖关系排，不按出现顺序
  • AI 默认会把 Q-A 理解成「问答游戏」 —— 不是。这里 Q 是凿子，A 是钉子。装饰性的轻问题禁止
  • AI 默认会在 A 里堆术语保平安 —— 用术语不算回答。把术语翻译成具体动作和具体物件，否则 A 没承重
  • AI defaults to writing "What is X" style questions — Textbook tone. After generation, review and rewrite any question that can be answered with a single definition.
  • AI defaults to making Answers scattered — No concluding sentence, no boundaries, written as a prose paragraph. Each Answer must strictly follow the four sections (Conclusion / Formalization / Steps / Boundaries).
  • AI defaults to writing "formalization" as mathematical formulas — This is incorrect. Formalization uses text + symbols like → = ≠ + × to compress into a visual relationship, e.g., 
    Generalist = Coordination, Specialist = Execution
    . It is the "geometry of thought", not "mathematical formalism".
  • AI defaults to asking questions in chapter order — This is just copying the table of contents, not extracting ideas. The Q chain should be ordered by argument dependencies, not the order of appearance.
  • AI defaults to interpreting Q-A as a "question-and-answer game" — This is not the case. Here, Q is a chisel, A is a nail. Decorative light questions are prohibited.
  • AI defaults to stacking jargon in Answers to play it safe — Using jargon doesn't count as an answer. Translate jargon into specific actions and objects, otherwise the Answer lacks substance.