Menu
Extract text and tables from PDF files.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Compute checksums (MD5, SHA-256) for text or files.
Review code for quality, bugs, and security issues.
Build book
Check chapters consistency betweend chapters.md and chapters/*/chapter.md
Review chapter
Does stuff
| name | pdf-processing |
| description | Extract text and tables from PDF files. |
| compatibility | Requires PyMuPDF library. |
Use this skill when the task involves reading, extracting, or transforming content from PDF documents.
For standard extraction, run the bundled script:
python scripts/extract.py <file.pdf>
The script reads the PDF and outputs structured content with page numbers and detected tables.
Return extracted text with page numbers and any detected tables in a structured format.
If you encounter scanned PDFs or complex layouts, OCR processing may be required.