pdf-reader

Text extraction from PDFs converts document content into structured markdown and plain text. This Skill reads local PDF files or URLs using PyMuPDF, automatically parsing sections, detecting figures, and preserving citations for downstream analysis and searchability.

Yes. This Skill identifies and extracts figures and references from PDFs, making it suited for processing scientific papers, theses, and research reports. Extracted citations and images are separated for easier reference management and analysis.

Both. The Skill supports multiple input sources—local file paths and direct URLs—so you can process PDFs stored anywhere without downloading them first, enabling batch processing across distributed sources.

PDF-to-markdown conversion creates structured, editable text that improves searchability and downstream processing. This Skill extracts plain text organized by sections, making content indexable and suitable for analysis tools or note-taking systems.

Extraction produces markdown sections, plain text content, detected figures as separate files, and structured citation data. These outputs are ready for downstream search, analysis, or integration with other tools like note-writing or document management systems.

Yes. PyMuPDF is required for PDF processing. The Skill handles the extraction logic, but PyMuPDF must be available in your environment to parse PDF files and extract structured content.