pdf-analyzer
Intelligent multi-pass PDF analyzer for extracting document structure, content inventory, and metadata. Uses overview-first approach - scans for TOC, infers structure from semantics when TOC missing. Handles large PDFs (>10 pages) by splitting into chunks using pdfcpu. Use when creating test expectations for pdf-translator, validating PDF conversion output, or understanding complex document structure before conversion.
Installation and usage
Intelligent multi-pass PDF analyzer for extracting document structure, content inventory, and metadata. Uses overview-first approach - scans for TOC, infers structure from semantics when TOC missing. Handles large PDFs (>10 pages) by splitting into chunks using pdfcpu. Use when creating test expectations for pdf-translator, validating PDF conversion output, or understanding complex document structure before conversion.
Once installed, you can use this skill by running the following command in your terminal:
skills use pdf-analyzer