Ljg Qa

This turns articles, papers, or books into sequences of sharp questions with structured answers. Instead of summarizing, it extracts the author's core argument as a chain of "why does this work / what's the tradeoff / where does it break" questions. Each answer follows a strict format: one-line conclusion, formalized relationship (like "old: X → new: Y"), reasoning steps, and boundary conditions. It's designed for intellectual reconstruction, not FAQ generation. The questions are supposed to bite into the real substance, and answers are meant to drive stakes into the ground so you can retrace the original logic. Works with URLs, PDFs, or raw text. Outputs to org-mode files.

Install to Claude Code

npx -y skills add lijigang/ljg-skills --skill ljg-qa --agent claude-code