This is a production-grade workflow that converts academic papers into deep-dive HTML articles with enforced six-round execution: fetch full text from arXiv or PDFs, clone and analyze GitHub repos to map code to methods, perform internal analysis, ask the user to pick a writing style (storytelling, academic, or concise), generate a complete HTML page with KaTeX formulas and Mermaid diagrams, then self-audit against hard requirements like word counts and citation counts. The academic style demands 4000+ words with at least five formulas and three figure references. The storytelling style requires vivid analogies and a hook opening. Use this when you need a shareable, publication-ready breakdown of a paper that's more readable than the original, with actual code cross-references if the repo exists.

skills.sh installs
1.2K
GitHub stars
1.5K
last updated
Aug 21, 2026

Install

$ npx -y skills add zsyggg/paper-craft-skills --skill paper-analyzer --agent claude-code

Installs into .claude/skills of the current project.

Files

Paper Analyzer — 学术论文深度解析

⚠️ 这是生产级指令。你的唯一任务:产出一篇让读者觉得"比我读论文还清楚"的深度HTML长文。

快速使用

/paper-analyzer https://arxiv.org/abs/2605.07363
/paper-analyzer /path/to/paper.pdf
/paper-analyzer  粘贴文本

强制工作流(每一步必须执行,不可跳过)

Round 1:获取论文全文 ⛔

输入执行
arxiv URL同时读 arxiv.org/abs/(摘要)和 arxiv.org/html/(全文HTML)
PDF路径用PDF读取工具读全文。分多次直到全部获取
文本全部使用

自检:有没有完整内容?没有 → 换方式继续。

Round 2:搜索开源代码 ⛔

  1. 从论文中提取代码仓库链接(通常在页脚或 Introduction 末)
  2. 没有则用论文标题+作者名搜索 GitHub
  3. 克隆:git clone --depth 1 <url> /tmp/paper_code
  4. 阅读 README → 核心源码文件 → 配置文件

根据代码状态分支处理:

状态处理文章体现
✅ 已发布读核心文件,找 ≥2 处论文方法↔源码对应贴代码段(≤30行),标注 文件路径:行号
⏳ 待发布检查 README/Release 标记标注状态+仓库链接
❌ 无代码搜索替代实现/相关项目注明"本文未提供公开代码"

Round 3:深度分析 ⛔ 内部完成,不展示过程

  1. 核心创新:论文做了什么别人没做的?(1-3个,每个一句话提炼)
  2. 方法细节:输入→处理→输出→为什么更好(每个创新画清楚这条线)
  3. 关键实验:哪个结果最有说服力?为什么?
  4. 论文弱点:作者自述 + 你的判断
  5. 代码对应:每个 component 对应哪个文件/函数

Round 4:询问用户 ⛔

必须问风格选择,用户未回则默认 academic。

Round 5:写作输出HTML ⛔

按选定风格的要求写,输出完整HTML。模板见下文。

Round 6:自我审查 ⛔

逐项检查,不通过则修改直到通过。


三风格详细要求


storytelling(故事型)— 像一篇公众号爆文

Sponsors

Details

Repository
github.com/zsyggg/paper-craft-skills
Category
Frontend Development
First seen
Jun 3, 2026

More from zsyggg/paper-craft-skills

All 2
1index-how avatarvocabularyindex-how/vocabularyThe precise design and UI vocabulary used on index.how/to/articulate — covering typography, color, iconography, layout, interaction, motion, accessibility, info1.2Kskills.sh installs
2mcollina avatarlinting-neostandard-eslint9mcollina/skillsConfigures ESLint v9 flat config and neostandard for JavaScript and TypeScript projects, including migrating from legacy `.eslintrc*` files or the `standard` pa1.2Kskills.sh installs
3vtex avatarvtex-io-session-appsvtex/skillsApply when building or debugging a VTEX IO session transform app (vtex.session integration). Covers namespace ownership, input-vs-output fields, transform order1.2Kskills.sh installs
4mindrally avatarnextauth-authenticationmindrally/skillsGuidelines for implementing NextAuth.js (Auth.js v5) authentication in Next.js applications with session management and security best practices1.2Kskills.sh installs
5capawesome-team avatarcapacitor-plugin-developmentcapawesome-team/skillsGuides the agent through creating and maintaining Capacitor plugins from scratch. Covers scaffolding a new plugin project, designing the TypeScript API, impleme1.2Kskills.sh installs
6pproenca avatarplaywrightpproenca/dot-skillsPlaywright testing best practices for Next.js applications (formerly test-playwright). This skill should be used when writing, reviewing, or debugging E2E tests1.2Kskills.sh installs