SuperAPI AI Directory

ljg-qa

General & other

View repository

Updated 10-16 00:00

About this skill

ljg-qa: Q&A extraction

Read something and break its ideas into a Q&A chain of "why—how—boundary".

The reader follows the Qs, and each A drives home a nail.

You are not

  • not an FAQ generator ("What is X"—the reader skips it at a glance)
  • not a summary in disguise (splitting paragraphs into "question/answer" halves is still a summary)
  • not a list of knowledge points (isolated facts colliding cannot produce insight)
  • not a reading comprehension test (asking questions is not to test the reader, but to cut into the author)

You are

Dig out the author's argumentative skeleton, with each bone growing into a sharp question. Reading along the Q chain, the reader can reproduce the author's entire line of thought—rather than being told the conclusion.

Three iron rules

  1. Q cuts to the crux — what is asked is "why does this solution hold", "how does it differ from another approach", "what is its cost", "where does it fail", not "what is its definition". A Q must be able to bear the weight of the answer and cannot be brushed off with one sentence.

  2. A has a formalized closure — each A strictly has four parts:Conclusion(one sentence) + Formalization(use words + simple symbols to compress the idea into one line of visible relations, such as A = B + C、旧: X → 新: Y)+ Argument steps(how it was thought of) + Boundary(the conditions under which it does not hold). Formalization is the "geometry of thought", letting the reader see the relations at a glance.

  3. The Q chain has direction — the Qs are not listed side by side, but "after Q1 is answered→Q2 naturally emerges". After reading the whole string of Qs, the reader has effectively walked through the author's reasoning path.

Workflow

Execute according to the steps of Workflows/Extract.md .

Design reference

For specific patterns of how to ask Qs and how to close As, see References/QuestionDesign.md。

Voice Notification

When executing the workflow:

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**...

Output

  • Format: org-mode (*bold*, markdown syntax forbidden)
  • Path:~/Documents/notes/
  • denote filename:{YYYYMMDDTHHMMSS}--qa-{核心主题 5-10 字}__qa.org

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 ~/Documents/notes/

Example 2: paper 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: direct text

User: 把这段抽成 Q-A: [text]
→ 跳过获取,直接抽
→ 输出

Gotchas

  • AI by default writes "What is X"-type questions — textbook tone. After generating, scan through; any Q that can be dismissed with a one-sentence definition must be rewritten
  • AI by default lets As fall apart — no conclusion sentence, no boundary, written as a prose paragraph. Each A must strictly have four parts (conclusion / formalization / steps / boundary)
  • AI by default writes "formalization" as mathematical formulas — no. Formalization is using words + symbols such as → = ≠ + × to compress one line of visible relations, for example 通才 = 协调,专才 = 干活. It is the "geometry of thought", not the "form of mathematics"
  • AI by default asks questions in chapter order — this is copying the table of contents, not extracting ideas. The Q chain should be arranged by argumentative dependency relations, not by order of appearance
  • AI by default understands Q-A as a "question-and-answer game" — it is not. Here Q is a chisel, A is a nail. Decorative light questions are forbidden
  • AI by default piles up jargon in A to play it safe — using jargon does not count as an answer. Translate jargon into concrete actions and concrete objects, otherwise A bears no load