Paper Deep Reader

为单篇学术论文生成来源可追溯、图文交错、零背景可进入且具博士级技术深度的中文或英文解读。默认按“一句话总结、背景与动机、核心方法、实验与结果、贡献与影响、结论”六部分成稿，首次出现即解释关键术语，用最小例子讲通机制，并截图、嵌入、逐一解读所有关键图表；兼容有视觉与纯文本环境。用户提供 PDF、URL、DOI、预印本标识、标题或全文并要求论文解读、精读、讲清楚、逐关键图表、方法/公式/实验解释时使用。只问局部问题时可定向回答；不用于全文逐句翻译或多论文综述。

108 stars 4 forksResearch & Science

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add Linwei-Chen/paper-deep-reader-skill --skill paper-deep-reader

Manual install

git clone --depth 1 https://github.com/Linwei-Chen/paper-deep-reader-skill.git /tmp/paper-deep-reader-skill
mkdir -p ~/.claude/skills
cp -r /tmp/paper-deep-reader-skill/. ~/.claude/skills/paper-deep-reader

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Paper Deep Reader

把单篇论文写成一份真正能教会人的图文报告。默认报告必须同时满足两件事：

1. **零背景可进入**：不假设读者懂目标学科；关键术语、缩写、指标和前置概念首次出现时立即讲清。
2. **技术上限足够高**：不止复述结论；重建机制、公式、创新差分、实验设计、证据强度与适用边界。

核心顺序是：

```text
先让人知道在解决什么 → 补齐必要概念 → 用例子走通机制
→ 回到精确定义与公式 → 用关键图表验证 → 判断贡献、影响与边界
```

## 1. 路由交付模式

默认画像：

```yaml
domain: auto
audience: broad-to-expert
goal: understand
depth: deep
delivery: explain
language: auto
visual_mode: auto
```

按“本次要求 → `.paper-reader.yaml` → 已确认偏好 → 自动识别 → 默认值”解析。只有歧义会实质改变结果时才提问。

| `delivery` | 触发 | 交付要求 |
|---|---|---|
| `brief` | “快速看懂、速览、值不值得读” | 一屏主线；0–1 个最必要视觉对象；明确未完成完整深读 |
| `explain` | “解读、精读、详细讲解、讲清楚”；**默认** | 完整六部分报告；解释全部承重机制、公式和所有关键图表 |
| `audit` | “逐个编号图表、审稿、复现、完整证据审计” | 六部分报告 + 所需审计附录；附录覆盖全部编号对象或复现/审稿账本 |
| `targeted` | 只问某个公式、图表、结论或步骤 | 直接回答局部问题，仍补必要术语、来源和边界 |

不要把“精读”自动压缩成摘要，也不要把“详细”误解为机械倾倒账本。`explain` 的长度由理解障碍和关键证据决定；压缩重复内容，不删背景桥梁、核心机制、关键图表或证据边界。

没有论文或可定位标题时，只问一个问题，请用户提供 PDF、URL、DOI、预印本标识、标题或全文。全文翻译交给翻译类技能，多论文综述交给综述类技能。

## 2. 按需加载参考材料

1. 先读 [references/visual-capability.md](references/visual-capability.md)，确定 `visual` 或 `text-only`。
2. 读 [references/audience-profiles.md](references/audience-profiles.md)，解析“理解入口”和“技术上限”。
3. 读 [references/reading-protocol.md](references/reading-protocol.md)，执行来源核对、深读与教学重构。
4. 写作前读 [references/report-template.md](references/report-template.md)。
5. 只加载 [references/paper-type-lenses.md](references/paper-type-lenses.md) 中对应论文类型，以及 [references/domain-lenses.md](references/domain-lenses.md) 中一个主领域、必要时一个次领域。

Read the full skill on GitHub

Details

Skill name: paper-deep-reader
Repository: Linwei-Chen/paper-deep-reader-skill
License: MIT
Repo updated: 15 August 2026

FAQ

What does the Paper Deep Reader skill do?

How do I install the Paper Deep Reader skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add Linwei-Chen/paper-deep-reader-skill --skill paper-deep-reader. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Paper Deep Reader popular?

It lives in Linwei-Chen/paper-deep-reader-skill, which has 108 GitHub stars and 4 forks.

Related skills

Luo Ming Color Science

Ayueh0102/Ronnier-skill

回答色彩科學／色度學問題時使用。涵蓋 CIE 色度學、XYZ 三刺激值、光源與色溫、色彩量測儀器與不確定度、色視覺與對立色理論、心理物理學實驗設計、色序系統（Munsell／NCS／Ostwald／DIN）、色差公式（CIELAB／CMC／CIE94／CIEDE2000）、影像色差與 S-CIELAB、同色異譜、色貌模型（CIECAM02／CAM16）、色適應變換（CAT02）、演色性（CRI／Rf／Rg）。觸發語如「色差公式」「CIEDE2000」「CIECAM02」「Munsell」「NCS」「色貌」「色適應」「演色性」「同色異譜」「亮度跟明度差在哪」「幫我複習色彩學」，或提到羅明（Ming Ronnier Luo）教授的色彩學課程。

Research & Science

Philosopher

103

frypan05/philosopher-OKF

Turns any topic or question into one self-contained, white, research-paper-style HTML study page with diagrams drawn in HTML/CSS, a concept map, and linked references. Use this whenever the user wants to learn, understand, study, revise, or have something explained, in any field (technology, engineering, medicine, science, maths, finance, economics, business, law, humanities, social science, or a specific research paper), at any level from school student to PhD, even if they never say "HTML" or "page".

Research & Science

Paper Format Agent

zxyasfas/paper_format_agent

Use this skill when a user needs to inspect, score, repair, or regression-test academic paper formatting in DOCX files, especially thesis, journal, or conference documents with a separate format specification. The skill guides Codex through local-first document handling, rule extraction, formatting repair, report review, and contribution-safe validation.

Research & Science

Biomedical Paper Reader

148

Gaoyuan-0423/biomedical-paper-reader

为单篇生物医学研究论文生成中文精读报告：逐图解释实验为什么这样设计、方法与结果如何支持结论、证据边界在哪里，并提炼可借鉴的研究设计；支持速读筛选与指定图／方法专题解析，英文或中英双语按需提供。输入可为 PDF、DOI、链接或正文。Deep-read, figure-by-figure analysis, quick screening, or focused figure/method analysis of one biomedical paper (PDF, DOI, link, or full text). 全文翻译、系统综述与多篇比较不是默认任务。

Research & Science

Research Idea and Battle

100

Punktheory/research-idea-and-battle

Engage this skill whenever the user wants rigorous academic discussion about AI/ML research ideas — whether brainstorming new directions, stress-testing a hypothesis, debating novelty and significance, or seeking high-level research mentorship. Trigger on: 'I have a research idea', 'let's battle this', 'is this novel enough', 'what would reviewers think', 'help me think through this direction', 'I want to explore X as a research problem', 'critique my idea', 'what's the contribution here', 'how do I position this', 'is this worth pursuing', 'what are the weaknesses', 'what's happening in this

Research & Science

Paper Glance

106

Diaugeia/paper-glance-skill

论文全能处理工具。每当用户上传论文 PDF、粘贴论文文本/摘要，或提到"论文"、"paper"、"文献"、"arxiv"时必须使用此 skill。功能包括：深度分析报告、思维导图、审稿意见、宣传推广脚本、播客音频生成。即使用户只说"帮我看这篇论文"或直接上传 PDF 也必须触发。

Research & Science

Browse the most popular Claude skills, all research & science skills, or write your own with the skills generator.