ljg-paper-flow

Convert research papers into markdown interpretations and reading card PNGs.

Updated Jul 11, 2022
One-click install
npx skills add https://github.com/zhengfran/dotconfig --skill ljg-paper-flow-zhengfran
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ljg-paper-flow
Source: https://github.com/zhengfran/dotconfig/tree/main/tools/ai/agents/skills/ljg-paper-flow
Command: npx skills add https://github.com/zhengfran/dotconfig --skill ljg-paper-flow-zhengfran

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the friction of reading multiple research papers one by one by automating a complete workflow that converts each paper into a structured interpretation and a ready-to-use reading card.

Core Features & Use Cases

  • End-to-end paper-to-card pipeline: Runs ljg-paper to generate a markdown analysis, then runs ljg-card -l to create a long reading card PNG from that markdown.
  • Batch workflow for multiple inputs: Accepts one or more arXiv links, paper URLs, PDFs, or paper names and processes them together.
  • Parallel processing across papers: Executes the two-step sequence per paper (paper first, then card) while running different papers in parallel for faster results.
  • Card mold options: Uses -c for multi-card mode and -i for an information-graphic mode when requested.

Quick Start

Use this workflow by telling the AI: "论文流,把下面这些论文都做成解读和长卡片:<paste your arxiv links/PDF paths/paper names here>,按默认长图生成卡片。"

Frequently Asked Questions about ljg-paper-flow

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

FAQPage Schema
How do I convert arXiv papers into markdown summaries and reading cards?

Batch processing multiple arXiv links or PDFs into markdown summaries and reading card images is supported. You can provide several paper inputs together, and the workflow processes different papers in parallel while running the markdown-to-card sequence sequentially for each individual paper.

Can I generate different visual formats for paper reading cards?

To use the paper workflow, provide arXiv links, paper URLs, PDFs, or paper names and specify the card generation mode. The workflow first generates a markdown analysis for each paper, then applies the specified card mold option to produce the final PNG reading card images.

What is the best way to capture knowledge from multiple research papers?

The paper workflow relies on a two-step sequence: first generating a markdown analysis from the paper input, then creating a PNG reading card from that markdown. These steps execute sequentially within each paper, while multiple papers are processed in parallel.

Does the paper workflow support parallel processing for batch literature triage?

The paper workflow accepts arXiv links, paper URLs, PDFs, and paper names as valid inputs for batch literature triage. It processes these inputs to generate structured markdown interpretations and ready-to-use reading card images.