Converts a directory of academic PDFs into a two-tier markdown structure: a lightweight index for broad browsing and full-text cleaned markdown files for deep diving. This drastically reduces token costs when performing literature reviews across large sets of papers.
Use this skill when you have a large collection of research papers and want to enable the AI to navigate them efficiently without reading every full PDF in every turn.
convert.py which handles PDF extraction, metadata parsing (Title, Author, JEL codes), and index generation.pymupdf4llm), script execution, and managing incremental updates.Primarily designed for Claude Code due to its ability to execute local Python scripts and read markdown files efficiently.
This skill has not been reviewed by our automated audit pipeline yet.