skills.rest
LigphiDonk
LigphiDonkCOMMUNITY
Explore all skills by this author →
GitHub

literature-pdf-ocr-library

Discover papers via stable APIs, OCR PDFs, and emit Markdown libraries with metadata.

708|51|Updated Mar 10, 2026
Search Tags:#ocr#pdf#markdown#indexing#literature#papers#corpus
One-click install
npx skills add https://github.com/LigphiDonk/Oh-my--paper --skill literature-pdf-ocr-library-ligphidonk
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: literature-pdf-ocr-library
Source: https://github.com/LigphiDonk/Oh-my--paper/tree/main/skills/literature-pdf-ocr-library
Command: npx skills add https://github.com/LigphiDonk/Oh-my--paper --skill literature-pdf-ocr-library-ligphidonk

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, pdfminer.six, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Build a real, traceable literature corpus from PDFs by discovery via stable APIs, careful selection of openly accessible PDFs, and conversion to Markdown with machine-readable metadata.

Core Features & Use Cases

  • Discovery and download: query official APIs (arXiv, Semantic Scholar, OpenAlex, Hugging Face daily papers) to assemble a set of candidate papers with provenance.
  • OCR and layout parsing: convert PDFs to Markdown using PaddleOCR layout parsing, with a pdfminer fallback when needed, producing per-paper Markdown and embedded images.
  • Structured library output: organize results under .pipeline/literature/<corpus-name>/ with per-paper metadata.json, OCR results, and a consolidating library_index.json for downstream AI agents.
  • Use Case: Build a curated corpus for a given topic, OCR all PDFs, and ingest them into a knowledge base for rapid literature surveys.

Quick Start

Run the workflow on your project to search for papers, download PDFs, OCR them to Markdown, and assemble the literature library.

Frequently Asked Questions about literature-pdf-ocr-library

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

FAQPage Schema
How do I build a traceable literature corpus from PDFs?▼

Build a traceable literature corpus by querying official APIs like arXiv and Semantic Scholar to discover papers, downloading openly accessible PDFs, and converting them to Markdown with machine-readable metadata.

How do I OCR PDF papers to Markdown for a knowledge base?▼

OCR PDF papers to Markdown by using PaddleOCR layout parsing to extract text and images, with a pdfminer fallback for processing, producing per-paper Markdown files for your knowledge base.

Can I use PaddleOCR for literature PDF layout parsing?▼

Yes, you can use PaddleOCR for literature PDF layout parsing by configuring it via token or API URL to convert documents to Markdown, with an optional pdfminer fallback for processing.

What is the best way to index academic papers for AI agents?▼

The best way to index academic papers for AI agents is to generate a consolidating library_index.json file alongside per-paper metadata.json files, organizing the structured library output for downstream consumption.

Does pdfminer work as a fallback for PDF OCR processing?▼

Yes, pdfminer works as a fallback for PDF OCR processing when PaddleOCR layout parsing is unavailable, ensuring the conversion of literature PDFs to Markdown continues without interruption.

Related Skills

Explore More Education & Research Skills→
yejinleiyejinlei
14

pdf-ocr-skill

Extract text from scanned PDFs and images using OCR engines.

Community
Advanced
zhouboyu-xrealzhouboyu-xreal

pinecone

Manage and optimize Pinecone vector databases for AI applications.

Community
Intermediate
jaredcroxtonjaredcroxton

arxiv

Search arXiv by keyword, author, category, or ID and retrieve paper metadata.

Community
Basic
sheawinklersheawinkler
78

ocr-and-documents

Extract text from PDFs, scans, and images via pymupdf and marker-pdf.

Community
Intermediate