deep-paper-reading

Analyze academic papers and generate structured Chinese Markdown reports with external verification.

Updated May 27, 2026

Search Tags:#evidence #critique #literature-review #deep-reading #markdown-report #paper-analysis #academic-papers

Ready to run

npx skills add https://github.com/ZhengYanXU/Deep-Paper-Reading --skill deep-paper-reading

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: deep-paper-reading
Source: https://github.com/ZhengYanXU/Deep-Paper-Reading/tree/main
Command: npx skills add https://github.com/ZhengYanXU/Deep-Paper-Reading --skill deep-paper-reading

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pymupdf, and includes scripts (resource) and references (resource) components.

What problem does it solve?

本技能帮助研究人员把论文转化为结构化、有证据支撑的深度论文阅读报告，超越简单摘要，结合论文内部内容与外部信息进行综合分析，输出高质量的中文 Markdown 报告。

Core Features & Use Cases

结构化报告：输出包含文献总览、背景信息、方法详解、实验与结果、局限性与未来方向等章节的完整中文 Markdown 报告。
证据支撑：对论文元数据、作者背景、代码/权重/数据集可用性等信息进行外部核验，并在报告中明确标注来源。
图像与资产整合：尽量保留论文原图并插入分析段落，生成对应的资产文件夹保存原图以便引用。

Quick Start

请提供要深度阅读的论文的 PDF、arXiv URL、DOI 或标题，系统将生成并保存一份完整的中文深度阅读报告。

Frequently Asked Questions about deep-paper-reading

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I generate a structured literature review from an academic paper PDF?▼

The system extracts paper content and external metadata to produce a structured Chinese Markdown report that includes background, methodology, experiments, and evidence-grounded critique sections.

Can I analyze arXiv articles and extract original figures for a markdown report?▼

Yes, the system preserves original figures from arXiv articles and technical reports, inserting them into the analysis paragraphs and saving original images in a generated asset folder for reference.

How does external verification work for paper analysis metadata and datasets?▼

External verification for paper analysis works by performing lookups to validate author backgrounds, code availability, and dataset sources, explicitly annotating these external sources in the final Markdown report.

Does this deep reading tool require pymupdf to process conference and journal papers?▼

Yes, this deep reading tool requires the pymupdf dependency to process conference and journal papers, relying on this library to access and parse the internal content of the provided PDF documents.

What is the best way to critique technical reports with evidence-based markdown output?▼

The best way to critique technical reports with evidence-based markdown output is to provide a PDF, DOI, or URL, allowing the system to combine internal content with external checks to deliver a grounded Markdown critique file.

What are the limitations of automated paper analysis for external code availability checks?▼

A limitation of automated paper analysis for external code availability checks is that it depends on external lookups, meaning it can only verify and report metadata that is publicly discoverable and accessible online.