extracting-pdfslisted

# PDF Content Extraction Skill Extract PDF content to clean, organized markdown. ## Workflow 1. **Extract** — Run script to get raw content + metadata 2. **Analyse** — Review for patterns and issues 3. **Clean** — Manually rewrite, omitting noise 4. **Organise** — Apply formatting principles 5. **Output** — Deliver clean markdown ## Step 1: Extract ```bash python /mnt/skills/user/extracting-pdfs/scripts/extract_pdf.py \ /mnt/user-data/uploads/{filename}.pdf \ /home/claude/extracted/ ``` For scanned PDFs or problematic extractions, use `--method pymupdf`. For page ranges, use `--pages 1-10`. To filter small icons, use `--min-image-size 100`. **Output:** ``` /home/claude/extracted/ ├── {filename}.md # Raw markdown with YAML frontmatter ├── metadata.json # Structured metadata └── images/ # Extracted images (if any) ``` ## Step 2: Analyse Read the extracted markdown: ```bash cat /home/claude/extracted/{filename}.md ``` **Check YAML frontmatter for:** - `extraction_method` — Which extractor was used - `total_pages` — Document length - `has_outline` — Bookmarks exist (helps with structure) - `total_images` — Number of images **Identify issues requiring cleanup:** - Repeated footers/headers on every page - Watermarks, branding, page numbers - Fragmented sentences across line breaks - Malformed tables - Image markers needing repositioning ## Step 3: Clean > **Manual cleanup only.** Do not write scripts, sed/awk commands, or regex replacements