DeepPaperNote skill
A skill that deep-reads a single paper and builds a structured Obsidian-style research note
- 1,350 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Reads local PDFs and fetches papers by link
- Writes note files into the vault
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/deeppapernoteDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Reads local PDFs and fetches papers by link
- Writes note files into the vault
This is third-party code. Review the repository files before installing.
What it does
The skill takes one paper by title, DOI, URL, arXiv ID, Zotero item or a local PDF and turns it into a detailed Markdown note. It breaks the work down by substance: the problem, the method, the evidence and the weak spots, and leaves placeholders for figures. The finished note is saved into the Obsidian vault chosen in the user configuration. A separate paper-glossary skill handles terms. It runs the same way in Claude Code and Codex.
Who it is for. For researchers, graduate students and analysts who keep a personal library of paper notes.
Good fit when
- You want to carefully break down one paper into a ready note
- You want to add a paper analysis to an Obsidian knowledge base
- You want consistent formatting for paper summaries
Not a fit when
- You need a survey of dozens of papers at once rather than a deep read of one
- You do not want an Obsidian and Markdown workflow
Example request
Read this paper by its arXiv ID and build a deep note for my Obsidian vaultLimitations
Reading PDFs requires the PyMuPDF package in the same Python environment the skill uses. Note quality depends on the agent's model. The skill analyzes the paper but does not replace your own verification of its conclusions.
How to disable. Remove the deeppapernote skill from the agent's skills directory or disable the plugin via /plugin.
FAQ
Which agents does it work with?
The same skill targets Claude Code and Codex, and the installer can lay it out for other agents too.
Do I need both skills?
No. deeppapernote is enough; paper-glossary is optional for term work.
Discussion
No questions or reviews yet.
Related
SkillsA skill for deep-reading one scientific paper: six sections, key figures in the text and each claim checked against the source.
A Claude Code skill for scientific literature reviews: an interview, Scopus and OpenAlex search, DOI checks and a final docx file
A skill set for academic papers: deep method analysis, visual slides and a coherent write-up from a paper PDF
paper-reading-skill turns one arXiv AI or robotics paper into a report with each claim tied to evidence in the source.
A Codex skill set for research papers: from research assets to a LaTeX draft with evidence checks and a review simulation.
The paper-spine skill takes a topic, materials and data through a scientific paper: literature, text, figures, review and Word, LaTeX and PDF files
README in short
The README presents a skill for reading exactly one paper at a time and stresses the questions that separate a careful analysis from a retelling. Installation goes through npx skills add with a choice of skills and agents, and PyMuPDF is installed for PDF parsing. The note is saved into an Obsidian vault per the user configuration, with an optional paper-glossary skill. MIT licensed.
README badge
Original SKILL.md
--- name: deeppapernote description: Generate a high-quality deep-reading note for a single paper and write it into an Obsidian-style vault. Use when the user gives a paper title, DOI, URL, arXiv ID, Zotero item, or local PDF and wants a polished Markdown note with strong structure, evidence-based analysis, and figure placeholders. --- # DeepPaperNote Use this skill when the user wants one outcome: - read one paper carefully - generate a high-quality Markdown note - save the note to the workspace or Obsidian target selected by resolved configuration