papergrep

Search Google Scholar, download open-access PDFs, and query a local full-text index.

1|Updated Nov 25, 2021
One-click install
npx skills add https://github.com/budmonde/dotfiles --skill papergrep
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: papergrep
Source: https://github.com/budmonde/dotfiles/tree/main/opencode/skills/papergrep
Command: npx skills add https://github.com/budmonde/dotfiles --skill papergrep

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Researchers often need to locate relevant academic papers, obtain open-access PDFs, and perform fast content search across their own library. papergrep provides an integrated workflow to do all three efficiently.

Core Features & Use Cases

  • Find papers via Google Scholar and review results
  • Download open-access PDFs into a local papers directory
  • Full-text search across indexed PDFs using a local database
  • Read cached renderings of indexed papers for quick reference

Quick Start

Search for a paper and, if open-access, download the PDF to ~/papers and index it for fast local search.

Frequently Asked Questions about papergrep

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

FAQPage Schema
How do I search Google Scholar and download open-access PDFs locally?

To search Google Scholar and download open-access PDFs locally, use this workflow to find papers, retrieve the PDFs, and save them directly into a designated local papers directory for offline access.

How do I perform full-text search across downloaded academic PDFs?

Full-text search across downloaded academic PDFs is performed by initializing a local database index with the papergrep CLI, allowing you to query the indexed content and read cached renderings of the papers.

Do I need to set up a specific directory structure before indexing PDFs?

Yes, you need a local papers directory initialized at ~/papers before indexing PDFs. The CLI requires this specific directory structure to operate safely and manage the local full-text search database.

What is the best way to manage academic research papers for offline access?

The best way to manage academic research papers for offline access is to search Google Scholar, download open-access PDFs to a local directory, and build a local full-text index for fast content querying.

Can I read cached renderings of indexed papers without the original PDF?

Yes, you can read cached renderings of indexed papers without the original PDF. Once the local full-text index is built using the CLI, the cached renderings are available for quick reference.

Why does full-text search on academic PDFs require a local indexing step?

Full-text search on academic PDFs requires a local indexing step because the CLI must process and cache the document contents into a local database to enable fast, offline content querying across the library.