ljg-paper-flow
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.
- Installs
- 5.3K
- Last 24h
- —
- Trending rank
- —
- Security
- Warn
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/lijigang/ljg-skills --skill ljg-paper-flow- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads ljg-paper-flow automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
Security audits
Independent scans of the skill's instructions and bundled files.
SKILL.md
The instructions your agent reads when the skill is triggered.
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。
FAQ
What does the ljg-paper-flow skill do?
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.
How do I install ljg-paper-flow?
Run npx skills add https://github.com/lijigang/ljg-skills --skill ljg-paper-flow in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/ljg-paper-flow/ (personal) or .claude/skills/ljg-paper-flow/ (project).
Which AI agents can use ljg-paper-flow?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is ljg-paper-flow safe to install?
Security partners have reviewed it: Gen Agent Trust Hub passed; Socket passed; Snyk flagged items to review; ZeroLeaks passed. As with any skill, read the SKILL.md and bundled scripts before installing.
Who maintains ljg-paper-flow?
It is published by lijigang in lijigang/ljg-skills. It has 5,274 recorded installs.
More from lijigang/ljg-skills
ljg-card
lijigang/ljg-skills
Content caster (铸). Transforms text into PNG through precise HTML typography and, when the mold needs it, generated raster imagery. Four molds: -l (default) long reading card, -f source-faithful full text, -c comic, -w whiteboard. USE WHEN user says '铸', 'cast', '做成图', '做成卡片', '做成海报', '原文排版', '全文卡片', '漫画', or '白板'.
ljg-paper
lijigang/ljg-skills
Explain research papers to readers without a specialist background: what the paper studies, what the authors contribute, how the findings follow, and what the evidence does not establish. USE WHEN the user shares an arXiv link, paper URL, PDF, local paper, or paper title, or asks to read, explain, analyze, or understand a paper. Defaults to a saved Markdown note. NOT FOR reproduction, formal peer review, benchmark tables, or literature surveys.
ljg-roundtable
lijigang/ljg-skills
一个议题，一场圆桌：主持人请来 3-5 位真实人物，定义开场，逐轮交锋， 每轮收一张 ASCII 结构图，用户用指令控节奏（可/止/深入此节/引入新人物）， 散场后全文存入 Markdown 笔记。Use when user says "圆桌讨论", "圆桌", "roundtable", "辩论", or wants to explore a topic through multi-perspective structured debate.
ljg-writes
lijigang/ljg-skills
写作引擎。把一个观点写成可理解、可迁移、经得住反例的 1000-1500 字中文文章。USE WHEN 写文章 OR 优化思想内容 OR 展开观点 OR 改写成逻辑递进的中文。NOT FOR 普通摘要、事实查询或结构风洞（用 ljg-structure）。
ljg-learn
lijigang/ljg-skills
Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, meta-philosophy) and compresses insights into an epiphany. Use when user asks to explain, dissect, or deeply understand a concept, term, or idea. Triggers on '解剖概念', '概念解剖', 'explain concept', 'learn concept', '/ljg-learn'. Produces markdown output.
ljg-plain
lijigang/ljg-skills
Cognitive atom: Plain (白). Rewrites any content so a smart 12-year-old groks it. Structure-free — form follows content. Use when user says '白话说', '说人话', '解释一下', 'plain', 'grok'.
Popular education & science skills
teach
mattpocock/skills
Teach the user a new skill or concept, within this workspace.
scaffold-exercises
mattpocock/skills
Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.
paper-context-resolver
lllllllama/rigorpilot-skills
Rigor Paper Context helper for README-first deep learning repo reproduction. Use only when the README and repository files leave a narrow reproduction-critical gap and the task is to resolve a specific paper detail such as dataset split, preprocessing, evaluation protocol, checkpoint mapping, or runtime assumption from primary paper sources while recording conflicts. Do not use for general paper summary, repo scanning, environment setup, command execution, title-only paper lookup, or replacing README guidance by default.
caveman-learn
juliusbrussee/caveman
Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes returned. Use when asked to lower an agent's token cost, what caveman has saved, to trim a heavy CLAUDE.md, or to offload re-pasted context into cavemem.
gsap-plugins
greensock/gsap-skills
Official GSAP skill for GSAP plugins — registration, ScrollToPlugin, ScrollSmoother, Flip, Draggable, Inertia, Observer, SplitText, ScrambleText, SVG and physics plugins, CustomEase, EasePack, CustomWiggle, CustomBounce, GSDevTools. Use when the user asks about a GSAP plugin, scroll-to, flip animations, draggable, SVG drawing, or plugin registration.
teach-impeccable
pbakaus/impeccable
DEPRECATED: Use /impeccable teach instead. This command has been folded into the impeccable skill.