oma-pdf

1# PDF Skill - PDF to Markdown Conversion
2 
3## Scheduling
4 
5### Goal
6Convert PDF files into structured Markdown or another requested extraction format while preserving readable document structure for LLM context, RAG, or downstream review.
7 
8### Intent signature
9- User asks to convert, parse, read, extract, or transform a PDF.
10- User needs PDF text, headings, lists, tables, or images prepared for AI consumption.
11- User mentions "PDF to markdown", "parse PDF", "read this PDF", or equivalent wording.
12 
13### When to use
14- Converting PDF documents to Markdown for LLM context or RAG
15- Extracting structured content such as tables, headings, lists, images, footnotes, or hyperlinks
16- Preparing PDF data for AI consumption
17- Checking whether a PDF has a text layer before choosing OCR
18 
19### When NOT to use
20- Generating or creating PDFs -> use document-generation tools
21- Editing existing PDFs -> out of scope
22- Reading an already-text file -> use direct file reading
23- Processing HWP, HWPX, DOCX, XLSX, or slide decks -> use the matching document skill
24 
25### Expected inputs
26- `input_path`: PDF file or folder path
27- `output_dir`: optional target directory
28- `format`: optional output format, default `markdown`
29- `ocr_languages`: optional OCR language list for scanned or image-based PDFs
30- `extraction_options`: optional flags for tagged structure, image extraction, or hybrid conversion
31 
32### Expected outputs
33- Markdown, text, JSON, HTML, or combined extraction output
34…