DeepPaperNote
Turn one dense paper into an Obsidian note worth keeping: read the way its field reads it, linked to the papers already in your vault, and aimed at your own res
What is DeepPaperNote?
Turn one dense paper into an Obsidian note worth keeping: read the way its field reads it, linked to the papers already in your vault, and aimed at your own research. Agent skills for Claude Code, Codex, Cursor, and any agent that supports skills.
Overview of DeepPaperNote
What it is
DeepPaperNote is an agent skill that runs in Claude Code, Codex, and other agents that support skills. It reads the full text of a research paper, writes an illustrated deep-reading note, saves it into your Obsidian vault, and links it to other papers you have read. The project is open source under the MIT license and is hosted on GitHub.
Key features
- Reads one paper and produces one note with no prompts or templates to learn.
- Supports 10 paper types (e.g., method, benchmark, survey) each with its own reading structure based on over 50 reviewer guidelines and reporting standards.
- Extracts figures and tables from the PDF and places them directly in the note; key formulas render in Obsidian.
- Every note undergoes an independent review and quality check before saving; if the full text cannot be read, the note is not fabricated.
- Notes link to related papers in your vault and include Takeaways and Connections sections tailored to your research directions.
Use cases
- Researchers who want to turn a dense paper into a durable, well-structured Obsidian note.
- Students and academics building a personal academic wiki by reading papers deeply.
- Anyone using Claude Code, Codex, or a skill-compatible agent who wants to read papers and keep notes in Obsidian.
Getting started
Install the plugin: bash claude plugin marketplace add 917Dhj/DeepPaperNote claude plugin install deeppapernote@deeppapernote Or with the skills CLI: bash npx skills add 917Dhj/DeepPaperNote Install the PDF dependency: bash python3 -m pip install PyMuPDF Python 3.10 or newer is required. Then tell your agent: text Generate a deep-reading note for this paper:
License and pricing
The project is open source under the MIT license. No pricing information is stated.
Based on the project's public README and repository metadata.