Claude Skill

917Dhj/DeepPaperNote

DeepPaperNote 是一种用于深度阅读单篇论文并生成高质量 Obsidian 风格研究笔记的智能体技能,兼容 Claude Code、Codex、Cursor、Copilot、Gemini CLI 等工具。

概览

Stars464
Forks32
语言Python
最后更新2026-07-02
最近同步2026-07-03
前往 GitHub

仓库信息

拥有者917Dhj
仓库DeepPaperNote
完整名称917Dhj/DeepPaperNote
Repo ID1,188,009,186

安装这个 Skill

npx skills add 917Dhj/DeepPaperNote

Registry 信息

类型mcp_server
质量分80/100
验证状态readme_parsed
最近验证2026-06-18
平台
ClaudeMCPCodexCursor
能力
pdfmemorysearchimageterminalworkflowagent-skillsclaude-codecodexcopilot
识别文件
README.mdREADME.zh-CN.mdSKILL.mdpyproject.tomltests
配置键
URLDEEPPAPERNOTE_SEMANTIC_SCHOLAR_API_KEY
安装方式
  • npx skills add 917Dhj/DeepPaperNote
  • npx skills add 917Dhj/DeepPaperNote -a codex
  • npx skills add 917Dhj/DeepPaperNote -a claude-code
  • git clone https://github.com/917Dhj/DeepPaperNote.git ~/.codex/skills/DeepPaperNote
  • git clone https://github.com/917Dhj/DeepPaperNote.git ~/.claude/skills/DeepPaperNote

项目简介

DeepPaperNote 是一种用于深度阅读单篇学术论文并生成高质量 Obsidian 风格研究笔记的智能体技能。它可与 Claude Code、Codex、Cursor、Copilot、Gemini CLI 等多种 AI 编码助手无缝配合使用。

英文描述

DeepPaperNote is an agent skill for deep-reading a single paper and generating high-quality Obsidian-style research notes. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.

要点

  • 深度阅读单篇论文并生成结构化的 Obsidian 风格笔记
  • 兼容 Claude Code、Codex、Cursor、Copilot、Gemini CLI 等多种工具
  • 输出适合研究笔记的干净 Markdown 格式
  • 可与 Zotero 集成进行引用管理
  • 轻量级基于 Python 的智能体技能

使用场景

  • 快速提取研究论文的关键见解
  • 为文献综述创建可复用的 Obsidian 笔记
  • 借助 AI 编码助手优化论文阅读流程
  • 从学术论文构建个人知识库

README 摘要

<div align="center"> # DeepPaperNote **Turn a complex paper into an Obsidian note you will actually want to keep.** [English](./README.md) | [简体中文](./README.zh-CN.md) [![Homepage](https://img.shields.io/badge/homepage-online-2563eb)](https://917dhj.github.io/DeepPaperNote/) [![Status](https://img.shields.io/badge/status-stable-16a34a)](https://github.com/917Dhj/DeepPaperNote) [![Release](https://img.shields.io/github/v/release/917Dhj/DeepPaperNote?display_name=tag&color=0f766e)](https://github.com/917Dhj/DeepPaperNote/releases/tag/v2.0.0) [![License](https://img.shields.io/badge/license-MIT-c9a227)](./LICENSE) [![Agents](https://img.shields.io/badge/agents-Claude%20Code%20%2B%20Codex-7c3aed)](./SKILL.md) [![Output](https://img.shields.io/badge/output-Obsidian-16a34a)](./references/obsidian-format.md) [![Figures](https://img.shields.io/badge/figures-image--first-f59e0b)](./references/figure-placement.md) [![Writing](https://img.shields.io/badge/writing-model--first-7c3aed)](./references/model-synthesis.md) [![Changelog](https://img.shields.io/badge/changelog-latest-0f766e)](./CHANGELOG.md) </div> [![DeepPaperNote Hero](./assets/hero-academic.svg)](https://917dhj.github.io/DeepPaperNote/) **Do you often run into this situation: you want to study a classic paper carefully, but the hardest part is no longer reading it — it is turning that reading into usable notes?** The real time sink usually looks like this: - jumping back and forth between PDFs, Zotero, web pages, and your note app - manually organizing metadata, abstracts, figures, and the method backbone - understanding part of the paper, but still spending a long time turning that understanding into structured notes - ending up with a note that looks complete but is not something you actually want to revisit l

话题

探索更多

数据来自 GitHub,同步时间:2026-07-03