ljg-paper-flow
lijigang/ljg-skills
Process multiple papers end-to-end: generate analysis + create 取景框 library card PNGs in parallel.
What is ljg-paper-flow?
Paper workflow that automates reading papers and generating visual library cards. Takes arxiv links, paper URLs, PDFs, or paper names, runs ljg-paper for analysis then ljg-library to create 取景框 library card PNGs. Use when processing multiple papers that need both detailed analysis and visual card representations.
- Extracts paper sources from user input (arxiv URLs, PDF paths, paper names)
- Runs ljg-paper on each paper to generate org-format analysis
- Runs ljg-library on the analysis to create 取景框 library card PNGs
- Processes multiple papers in parallel while maintaining serial execution per paper
- Generates summary report with paths to analysis files and card images
- Handles arxiv-specific metadata (author, arXiv ID, year) for paper cards
How to install ljg-paper-flow
npx skills add https://github.com/lijigang/ljg-skills --skill ljg-paper-flow- ljg-paper skill installed
- ljg-library skill installed
How to use ljg-paper-flow
- 1.Provide one or more paper sources (arxiv URLs, PDF paths, or paper names)
- 2.The skill extracts all papers from your input
- 3.For each paper, ljg-paper generates an org-format analysis
- 4.The analysis is passed to ljg-library to create a 取景框 library card PNG
- 5.All papers are processed in parallel (each paper's steps run sequentially)
- 6.Review the summary report showing analysis and card file paths for each paper
Use cases
- Reading a batch of research papers and creating visual reference cards for each
- Building a collection of paper insights with accompanying visual library cards
- Processing multiple arxiv papers to extract key ideas and distill them into visual formats
- Creating 取景框 cards from papers that have already been analyzed
- Automating the workflow from paper discovery to visual knowledge card creation
- Researchers managing multiple papers
- Students building paper collections with visual summaries
- Knowledge workers creating visual reference libraries from academic papers
- Teams needing parallel processing of paper analysis and card generation
ljg-paper-flow FAQ
Yes. The skill processes multiple papers in parallel, with each paper's ljg-paper and ljg-library steps running sequentially.
ArXiv URLs, direct paper URLs, local PDF file paths, and paper names/titles.
For each paper: an org-format analysis file from ljg-paper and a 取景框 library card PNG from ljg-library.
For arxiv papers, it uses arxiv metadata (author, arXiv ID, year) instead of weread covers and wikipedia avatars. The core value comes from the 取景框 visual and Feynman explanation.
No. For each paper, ljg-paper must complete first, then ljg-library runs on its output. However, different papers are processed in parallel.
Full instructions (SKILL.md)
Source of truth, from lijigang/ljg-skills.
name: ljg-paper-flow description: "Paper workflow: read papers + cast 取景框 library cards in one go. Takes one or more arxiv links, paper URLs, PDFs, or paper names. For each paper, runs ljg-paper (generates org analysis) then ljg-library (distills the paper's 取景框 into a 2050 library card PNG). Use when user says '论文流', 'paper flow', '读论文并做卡片', '论文卡片', or provides multiple papers wanting both analysis and cards." user_invocable: true version: "1.1.0"
ljg-paper-flow: 论文流
一条命令完成:读论文 → 生成解读 → 铸成取景框借书卡。支持多篇并行。
模式
强制 NATIVE 模式。 本 workflow 是纯 skill 管道(ljg-paper → ljg-library),不需要 Algorithm 的七步流程。直接按下方执行步骤调用 skill,不走 OBSERVE/THINK/PLAN/BUILD/EXECUTE/VERIFY/LEARN。
参数
无 flag。论文来源从对话或命令里取(arxiv URL、PDF 路径、论文名)。每篇论文走 ljg-paper → ljg-library,卡片类型固定为取景框借书卡——ljg-library 只产这一种卡,没有 ljg-card 那套 -l/-i/-c/-v 模具可选。
执行
1. 收集论文列表
从用户消息中提取所有论文来源(arxiv URL、PDF 路径、论文名称等)。
2. 并行处理每篇论文
对每篇论文,启动一个 Agent subagent,每个 subagent 按顺序执行两步:
步骤 A — 读论文(ljg-paper):
调用 Skill tool 执行 ljg-paper,传入该论文的来源。等待完成,获得生成的 org 文件路径。
步骤 B — 铸取景框卡(ljg-library):
读取步骤 A 生成的 org 文件——里面已经把这篇论文的命题、内核、它带来的新看世界方式拆透了,这正是 ljg-library 要的「已想透的取景框思想」。把这份思想连同论文标题 / 作者 / arxiv 信息交给 Skill tool 执行 ljg-library:走它的输入弹性路径(给了思想就只校验 + 画图,跳过从零提炼),产出取景框借书卡 PNG。等待完成,获得 PNG 路径。
3. 汇总报告
所有论文处理完成后,汇总输出:
════ 论文流完成 ═══════════════════════
📄 {论文标题1}
📝 解读: {org 文件路径}
🃏 取景框卡: {PNG 文件路径}
📄 {论文标题2}
📝 解读: {org 文件路径}
🃏 取景框卡: {PNG 文件路径}
...
关键约束
- 每篇论文的两步必须串行(先 paper 后 library),但多篇论文之间并行
- ljg-paper 和 ljg-library 各自的质量标准、红线、品味准则不变
- 卡片的取景框来自生成的 org 文件(已拆透的命题 + 内核),不是原始论文
- 论文 ≠ 书,素材降级:ljg-library 的封面(weread)/ 作者头像(维基)/ 出版社字段是为书设计的。论文走 arxiv:weread 多半搜不到 → 封面落 CSS 占位;arxiv 作者多半不在维基 → 头像省略;书目行改用 arxiv 元数据(作者 · arXiv:ID · 年份)。卡的命在取景框意向画面 + 费曼讲解 + 手绘图,这部分论文完全适配,封面 / 头像缺位不伤核心。
- 并行隔离 /tmp 竞争:ljg-library 默认把封面 / 头像写死在
/tmp/lib_cover.jpg、/tmp/lib_avatar.jpg;多篇并行会互相串图。每个 subagent 必须用唯一路径(如/tmp/lib_cover_{slug}.jpg),渲染后亲眼验图确认没串。
Related skills
More from lijigang/ljg-skills and the wider catalog.
ljg-travel
Deep cultural travel research: auto-generate structured org-mode documents and reference cards for museums and ancient architecture.
ljg-card
Transform content into styled PNG visuals with seven layout molds—long cards, infographics, comics, sketchnotes, whiteboards, and more.
ljg-roundtable
Structured roundtable discussion framework with truth-seeking moderator and representative figures for multi-perspective debate.
ljg-paper
Reads research papers as continuous stories, extracting core propositions through narrative structure for non-academics.
ljg-plain
Rewrite any content so a smart 12-year-old understands it—plain language, no jargon.
ljg-learn
Deep concept anatomist that deconstructs ideas through 8 exploration dimensions and compresses insights into epiphany.