| name | reading-notes |
| description | Extract text from papers, summarize them, and create reading notes. Use when reading or summarizing a paper, and automatically after downloading one. |
Reading Notes
Reading notes are objective (what does the paper say?) — create them automatically, no approval needed. One note per paper in notes/.
When the user asks you to read or summarize a paper
make extract-text PDF="sources/filename.pdf" to get the text- Read it and provide your own summary
- Always create a reading note automatically. File name:
YYYY-MM-DD-authorlastname-year---short-title.md (e.g., 2026-03-08-smith-2024---cognitive-offloading.md)
- YAML frontmatter:
---
title: "Author Year - Short Title"
date: YYYY-MM-DD
tags: [relevant, topic, tags]
doi: "10.xxxx/..."
---
- Fill every section of
templates/note.md: Summary, Key Findings, Methodology, Relevance to This Work, Questions & Follow-ups, plus one key quote the user can paste into the manuscript
- Tell the user: "I've saved a reading note in
notes/."
- Mark the corresponding search-queue entry done
- Check whether enough related notes have accumulated to propose a section draft (see the drafting skill)
Commands
make extract-text PDF="sources/paper.pdf" — extract one PDFmake extract-all — extract every PDF in sources/make new-note TITLE="Paper Title" — create a note from the templatemake search-notes QUERY="keyword" — search across all notes
Precision requirements
Notes feed section drafts, and drafts must trace every claim to its source in under 30 seconds. Capture in the note:
- Direct quotes with page or section:
"exact words" (p. 12)
- Specific numbers: not "large sample" but "N=217", "d=0.43"
- Where things live: "Table 2, p. 8", "Discussion section"
