Use when processing PDF rulebooks, extracting raw markdown and image artifacts, or preparing source materials before `chapter-split`, `init-doc`, or translation setup.
Convert a source PDF into extracted markdown and image artifacts ready for chapter planning and translation setup.
Core principle: Extract cleanly and verify raw artifacts before chapter planning starts.
Run:
uv run python scripts/extract_pdf.py data/pdfs/<filename>.pdf
Expected outputs in data/markdown/:
<name>.md<name>_pages.mdimages/<name>/Validate:
_pages.mdIf extraction is garbled or page markers are broken:
Hand off extracted outputs to:
chapter-split for chapter/file planning and navigation generationinit-doc when project-level decisions and terminology bootstrap are still pendingStop when:
Return to Step 1 when:
Never:
chapter-split is the correct next skillContinue with chapter-split or /init-doc.