DeepPaperNote reads one paper at a time and builds a note you can keep in Obsidian. It gathers paper material, organizes the structure, and preserves the research question, method, evidence, results, and figure context.
Builders who want their agent to turn a paper into a reusable Obsidian note instead of a disposable summary.
You can keep one paper as a durable, linkable research note without redoing the structure by hand.
Reads a single paper deeply instead of rewriting the abstract.
Produces a structured note meant to live in an Obsidian vault.
Keeps figures, formulas, results, and evidence context in the final note.
Uses local Zotero records and attachments when available before falling back to web lookup.
Adds `paper-glossary` for creating reusable terminology notes from paper artifacts.
Includes note-quality rubrics and regression workflows to judge output quality.
npx skills add 917Dhj/DeepPaperNote
python3 -m pip install PyMuPDF
uv pip install PyMuPDF
Generate a deep-reading note for this paper: <title, DOI, URL, arXiv ID, or local PDF> Turn this paper into an Obsidian note: <paper>
Turn one complex paper into an Obsidian note you will actually want to keep.
Read one paper deeply. Add one durable page to your academic wiki.
You sit down to study an important paper. The hard part is not reading it—it is turning what you understood into a note you can still use later. The time usually disappears into work like this:
DeepPaperNote takes over that repetitive, mechanical, and surprisingly expensive layer of paper reading. It gathers the material, builds the structure, places figures in context, and shapes the final note so you can keep your attention on the paper's real ideas.
In other words, you can think of DeepPaperNote as the single-paper ingestion layer for an LLM-maintained academic wiki: it reads one paper deeply and turns its research question, methods, evidence, results, and figures into a durable page that people can read and agents can reuse. Obsidian is where those pages live, connect, and grow; DeepPaperNote is how a paper reliably enters the wiki.
DeepPaperNote is an agent skill for reading one paper at a time. The same core skill runs in Claude Code and Codex, and it focuses on the questions that distinguish a deep-reading note from an abstract rewrite:
[!tip] If you already use Obsidian or Zotero, DeepPaperNote automates the most time-consuming and error-prone parts of evidence gathering, organization, and note production.
paper-glossary, an optional companion skill for building reusable Obsidian terminology notes.News lists only the three most recent user-facing milestones. See the changelog and GitHub Releases for the full history.
npx skills add 917Dhj/DeepPaperNote
The installer lets you choose which skills to install and which agents should receive them. For most users, start with deeppapernote; add paper-glossary only if you want reusable terminology notes.
python3 -m pip install PyMuPDF
If you use uv, install PyMuPDF into the same Python environment that DeepPaperNote will use:
uv pip install PyMuPDF
DeepPaperNote requires Python 3.10 or newer. PyMuPDF powers the core PDF extraction path.
A title, DOI, URL, arXiv ID, or local PDF all work. Zotero items are also supported when a compatible integration is available.
Generate a deep-reading note for this paper: <title, DOI, URL, arXiv ID, or local PDF>
Turn this paper into an Obsidian note: <paper>
| You may be dealing with... | DeepPaperNote helps by... |
|---|---|
| 📄 You finished the paper, but your notes are still a pile of fragments | Rebuilding the research question, method chain, central experiments, and limitations into one note you can actually read again |
| 🧠 You do not want another polished-looking AI summary | Preserving the formulas, numbers, figure context, and evidence boundaries that make the paper worth understanding |
| 🗂️ You keep reading papers, but they never become your academic wiki | Turning each paper into a searchable, linkable, reusable Obsidian knowledge page so your academic wiki grows one paper at a time |
| 📚 The paper is already in Zotero, and you do not want to match or download it again | Preferring local records and attachments when available, reducing repeated work and paper mismatches |
DeepPaperNote remains the main product. The repository also includes an optional companion skill that works from DeepPaperNote's saved paper artifacts without taking over or rerunning the paper-reading workflow.
| Skill | Role | When to use it |
|---|---|---|
deeppapernote | Core product · recommended | Read one paper deeply and produce a structured, evidence-based Obsidian note with figures, results, and limitations |
paper-glossary | Optional companion | Select terms from existing paper artifacts, create reusable Obsidian glossary notes, and optionally link them back to the paper note |
You do not need to install every skill. Choose the ones that match your workflow during installation.
The canonical execution contract lives in skills/deeppapernote/SKILL.md.
The first time you hand a paper to your Agent, DeepPaperNote helps you choose:
Once confirmed, these preferences are saved on your device and reused for future papers. You can still request a different language or save target for any individual run without changing your defaults.
DeepPaperNote never silently overwrites an existing note or switches save destinations when a save is blocked.
For advanced environment-variable and CLI configuration, see User Configuration.
None of these are required for ordinary digital PDFs.
| Enhancement | What it helps with |
|---|---|
| Zotero integration | Reuses local paper records and PDF attachments before searching online |
| Semantic Scholar API | Improves metadata lookup for papers that are difficult to resolve |
| OCR tooling | Recovers page text from scanned or low-quality PDFs |
The built-in, read-only Zotero Local API integration supports three resolution modes:
auto (default): prefer a unique local item and retain web fallbackoff: skip Zotero lookuprequired: stop unless Zotero uniquely resolves the referenceAn ambiguous local match always fails closed instead of selecting an arbitrary item. Compatible agent-runtime or MCP integrations remain optional alternatives.
When one of these capabilities is needed, ask your agent to inspect the current environment and guide the setup for that machine.
DeepPaperNote was influenced by projects that take paper reading, evidence extraction, and note generation seriously, especially:
Pull requests should target develop, not main. Changes that may affect final note quality should be evaluated with evals/regression-workflow.md and evals/note-quality-rubric.md.
Thanks for reading, using, and supporting DeepPaperNote. May your paper-reading days be a little clearer, calmer, and more rewarding.
Sign in to join the discussion.
No comments yet. Be the first to say what this is good for.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
Topic in, narrated explainer video out. A Claude Code / Codex skill that turns any topic into a black-canvas motion-graphics explainer video with TTS voiceover, subtitles and a chapter progress bar. Chinese or English; every frame drawn in code with Remotion.
Public repository for Agent Skills
Open-source AI job search: scan job portals, evaluate listings into a structured A-H report with a global 1-5 score, tailor your CV, track applications — runs locally in your AI coding CLI (Claude Code, Codex, OpenCode, Antigravity…)
Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.
A skill to stop your coding agent from burying the answer. ADHD-friendly output.