document-processor
Installation
SKILL.md
Document Processor
Extract content from PDFs and DOCX files for analysis, summarization, and note integration.
Design Philosophy
The Large File Problem
Claude can read PDFs directly, but large files (>5MB) often fail or timeout. This skill provides extraction scripts that handle files of any size by processing page-by-page and optionally splitting output into chunks.
Extract First, Summarize Second
The Python scripts focus on extraction quality, not summarization. They produce clean text output that Claude can then analyze, summarize, or integrate into notes. This separation means extraction is deterministic and repeatable.