如果你已经用 Zotero 整理本地文献、用 Obsidian 构建知识库

从论文阅读到结构化笔记这一步常常需要自己来回搬运

DeepPaperNote 这条开源链路可以把这两端直接接上

给它输入论文标题、链接或者一份本地 PDF，它就能自动完成证据收集、整理和笔记生成

它会先判断论文是方法论、综述还是实验研究，然后采用不同的阅读策略去抓重点

公式、实验数据、图表上下文都会保留

图片能直接插入 Obsidian 笔记，暂时插不了的也会留好占位说明

输出时直接生成带元数据和目录结构的笔记文件，不需要再手动整理

这个插件可以安装到 Claude Code 或 Codex 上使用

适合想把论文整理过程省下来、更多投入思考的研究者

GitHub http://github.com/917Dhj/DeepPaperNote…

917Dhj/DeepPaperNote

Source: https://github.com/917Dhj/DeepPaperNote

Read one paper deeply. Add one durable page to your academic wiki.

Do you know this situation? You sit down to study an important paper, but the exhausting part is not simply reading it. It is turning what you understood into a note you can still use later. The time usually disappears into work like this:

• switching between the PDF, Zotero, web pages, and your note app
• manually organizing metadata, the abstract, figures, and the method backbone
• understanding part of the paper, then spending even longer turning that understanding into a coherent note
• ending up with something that looks complete but is not a note you actually want to revisit

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:

• What problem is the paper actually solving?
• How does the method, system, or analytical mechanism really work?
• Are the key formulas, experimental conclusions, and figure context preserved?
• Will the result become a useful long-term Obsidian note rather than a disposable summary?

If you already use Obsidian or Zotero, DeepPaperNote automates the most time-consuming and error-prone parts of evidence gathering, organization, and note production.

📰 News

• [2026-07-16] 🧩 Added paper-glossary, an optional companion skill for building reusable Obsidian terminology notes.
• [2026-07-16] 🔌 DeepPaperNote is now distributed as a plugin for multiple agents, with support for selecting multiple skills from the repository. PR #12
• [v2.0.0] 🚀 Released a deeper evidence-first paper-reading workflow with stronger note planning and figure handling. Release notes

News lists only the three most recent user-facing milestones. See the changelog and GitHub Releases for the full history.

🚀 Quick Start

1. Install the plugin

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.

2. Install the core PDF dependency

python3 -m pip install PyMuPDF

DeepPaperNote requires Python 3.10 or newer. PyMuPDF powers the core PDF extraction path.

3. Hand a paper to your agent

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>

DeepPaperNote currently generates Chinese notes by default, and its writing and validation rules are optimized for Chinese output.

🎯 Why DeepPaperNote?

🧩 Skills

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.

You do not need to install every skill. Choose the ones that match your workflow during installation.

✅ Quality Promise

• The result should be a deep-reading note for one paper, not an abstract rewrite.
• Important methods, experimental results, figures, and limitations should be explained rather than merely listed.
• If the available source is not strong enough for a real deep read, the workflow should stop and ask for better material instead of pretending the note is complete.

The canonical execution contract lives in skills/deeppapernote/SKILL.md.

🗂️ Obsidian Setup

To make an Obsidian vault the default save target, set:

export DEEPPAPERNOTE_OBSIDIAN_VAULT="/absolute/path/to/your/vault"

• When a usable vault is configured or provided, DeepPaperNote saves the validated note and its paper-local images/ directory there.
• When no vault is configured, DeepPaperNote asks first. It writes to the current workspace only after you explicitly choose not to use a vault.
• If a configured vault save fails, DeepPaperNote reports the blocked save instead of silently switching to another destination.

🔧 Optional Enhancements

None of these are required for ordinary digital PDFs.

Zotero Local API

The built-in, read-only Zotero Local API integration supports three resolution modes:

• auto (default): prefer a unique local item and retain web fallback
• off: skip Zotero lookup
• required: stop unless Zotero uniquely resolves the reference

An 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.

🧭 Inspirations

DeepPaperNote was influenced by projects that take paper reading, evidence extraction, and note generation seriously, especially:

• heleninsights-dot/phd-deepread-workflow
• juliye2025/evil-read-arxiv

🤝 Contributing

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.

Star History

Thanks for reading, using, and supporting DeepPaperNote. May your paper-reading days be a little clearer, calmer, and more rewarding.

MIT License © 917Dhj