ljg-qa Question Chain Extractor

What it does

When your agent uses it

• Extracting an article's core argument as a chain of questions and answers
• Studying a paper by questioning its method, cost and limits
• Turning a book chapter into reusable org-mode notes

Example prompts

• “/ljg-qa on the article at https://example.com/post about caching strategies.”
• “Extract Q&A from ~/Downloads/paper.pdf, focusing on why the method works and where it fails.”
• “Turn this pasted text into a question chain with conclusions and boundaries.”

Requirements

• A notes folder at ~/Documents/notes for the output

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

1. 1Q 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. 2A 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. 3Q 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。

What it can do on your machine

Read from SKILL.md and the folder at commit 9e75497. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • curl

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

ljg-qa Question Chain Extractor loads about 590 tokens when it runs, and up to ~2k if it reads all its reference files. Until then it costs about 118 tokens; SKILL.md has 129 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~118

When it runs · the whole SKILL.md, loaded when a task matches

~590

With references · SKILL.md plus every file in references/, read only if the agent opens them

~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from lijigang/ljg-skills at commit 9e75497, republished under its MIT licence (© lijigang). 129 words, ~590 tokens.

name

ljg-qa

description

信息提问机。给一篇文章/论文/书，把核心观点抽成 Q-A 对——Question 切要害，不教科书；Answer 简洁清晰，有形式化收口，逻辑链完整。读者顺 Q 链走过，每个 A 砸下一枚钉子，复现作者整套推理。Use when user says '问答', 'Q&A', 'QA', '提问', '抽取问题', '/ljg-qa', or shares an article/paper/book and asks for Q-A extraction. Triggers when the user wants ideas extracted not as a summary but as a sequence of incisive questions with answered. NOT FOR FAQ generation, glossary creation, or comprehension quizzes — this is intellectual scaffolding, not study aids.

user_invocable

true

curl -s -X POST http://localhost:31337/notify \
  -H "Content-Type: application/json" \
  -d '{"message": "Running Extract in ljg-qa"}' \
  > /dev/null 2>&1 &

Running **Extract** in **ljg-qa**...

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/

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

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

© lijigang, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in skills/ljg-qa of lijigang/ljg-skills.

• SKILL.md
• References/QuestionDesign.md
• Workflows/Extract.md

Open the folder on GitHubat commit 9e75497