market-research

DeepPaperNote: Fast Research Notes

Name: DeepPaperNote: Fast Research Notes
Author: 917Dhj

Generate high-quality research notes with DeepPaperNote. For founders researching with paper-intensive workflows.

1,165 stars+22★ this week80 forksPythonGuide quality 8/10 · reviewed Jul 30Updated 10/7/2026100% free · open source

What it does

DeepPaperNote generates high-quality Obsidian-style research notes by deep-reading a single paper, integrating with various AI tools like Claude Code and Codex.

When to use it

•You need to summarize complex research papers efficiently
•You're looking to organize notes from a paper in a structured, Obsidian-compatible format
•You want to leverage AI for in-depth paper analysis without manually processing the content

Ready-to-paste prompt

To generate notes for a paper named `example_paper.pdf`, you could use a command like `python deep_paper_note.py -i example_paper.pdf -o example_notes.md --agent ClaudeCode`

Heads up: Ensure you have Python installed and properly configured on your system, as DeepPaperNote is a Python script and relies on Python to run successfully

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

⚡ Runs out of the box

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/deeppapernote && curl -fsSL https://workflowstacks.com/api/skills/deeppapernote/claude-skill -o ~/.claude/skills/deeppapernote/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How DeepPaperNote: Fast Research Notes works

Codeflow

Free to inspect

DeepPaperNote: Fast Research Notes is a large Python project (~20k lines across 38 code files, plus 34 test files). You install it into your AI tool with one command; there is nothing to run yourself. Last commit this month, MIT license, has a test suite.

Size

Large codebase

~20k lines · 38 code files · ~3 h to skim

Setup

Install as a skill / plugin

Add it to Claude Code (or your AI tool) with one command — 2 skills inside. Nothing to run yourself.

Runs on

Inside your AI tool

Helper scripts use Python

Python 100%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
AGENTS.md
The instructions the AI actually follows
3
skills/deeppapernote/SKILL.md
Inside skills/ — an example of what the AI is told to do

What's in each folder

skills/Prompts, skills & agent definitions66 files

evals/Evaluations & benchmarks4 files

.claude-plugin/Plugin manifest — what gets installed2 files

.codex-plugin/Plugin manifest — what gets installed1 files

scripts/Helper scripts1 files

tests/Tests — proof it works26 files

assets/Images & static assets5 files

.github/CI / automation (GitHub Actions)3 files

READMEHas testsDocumentedCI checksMIT licenseUpdated this month

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

⚡ Runs out of the box

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/deeppapernote && curl -fsSL https://workflowstacks.com/api/skills/deeppapernote/claude-skill -o ~/.claude/skills/deeppapernote/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

917Dhj

Language

Python