hf-papers-reporter

Generates Word reports from Hugging Face Daily Papers by extracting abstracts, introductions, and figures.

1|Updated Jan 30, 2026

Search Tags:#data extraction #HuggingFace #generate #papers #PDF parsing #Word report

Ready to run

npx skills add https://github.com/xdrshjr/JR-Agent-Skills --skill hf-papers-reporter

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: hf-papers-reporter
Source: https://github.com/xdrshjr/JR-Agent-Skills/tree/main/hf-papers-reporter
Command: npx skills add https://github.com/xdrshjr/JR-Agent-Skills --skill hf-papers-reporter

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires PyMuPDF, python-docx, Pillow, beautifulsoup4, requests, and includes scripts (resource) components.

What problem does it solve?

This Skill automates turning Hugging Face Daily Papers into a single, professionally formatted Word report by fetching papers, extracting abstracts and introductions from PDFs, pulling figures, and compiling results into a shareable document.

Core Features & Use Cases

Automated paper collection: Retrieve top Hugging Face papers and collect their metadata.
Content extraction: Parse PDFs to extract abstracts, introductions, and figure images.
Document generation: Produce a polished Word document with cover images, citations, and structured sections.
Use Case: A researcher receives daily summaries in a single docx, ready for briefing decks or notes.

Quick Start

Run the main script to generate today's HF Daily Papers report: python3 scripts/process_papers.py

Frequently Asked Questions about hf-papers-reporter

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

FAQPage Schema

How do I generate a Word report from HuggingFace papers?▼

To generate a Word report from HuggingFace papers, you run the main Python script to automatically fetch daily papers, parse PDFs for abstracts and introductions, extract figure images, and compile everything into a formatted .docx file along with a metadata JSON.

Can I automatically extract abstracts and figures from HuggingFace PDFs?▼

Yes, you can automatically extract abstracts and figures from HuggingFace PDFs. The process downloads the daily papers and uses PDF parsing to pull out abstracts, introductions, and figure images for your documentation.

Does this PDF parsing approach work with python-docx and PyMuPDF?▼

Yes, this PDF parsing approach works by using PyMuPDF to extract text and figures from academic PDFs, while python-docx assembles the extracted content into a professionally formatted Word document.

What is the best way to summarize HuggingFace Daily Papers for a briefing deck?▼

The best way to summarize HuggingFace Daily Papers for a briefing deck is to automate content extraction. This fetches paper metadata, pulls introductions and abstracts, and outputs a single ready-to-share Word document.

Are there limitations when extracting figures from multiple academic PDFs?▼

A limitation when extracting figures from academic PDFs is that the process specifically targets abstracts, introductions, and images, meaning complex tables or full-text body sections outside the introduction are not included in the generated Word report.