pptx-to-md
PPTX → Markdown
PPTX information often lives in visual layout (side-by-side comparisons, flowchart arrows, charts). Plain shape-text extraction loses this structure. This skill renders each slide as a PNG and lets you describe the full content — preserving spatial relationships.
Pipeline
PPTX → PDF (LibreOffice) → per-slide PNG (pymupdf, 150 dpi) → .md with  placeholders → you fill in descriptions
Workflow (agent mode — default, zero config)
Step 1 — Run the renderer
python "${CLAUDE_SKILL_DIR}/scripts/pptx_to_md.py" \
--input <pptx_or_dir> \
--output <output_dir>
More from ocozyo/docs-to-wiki
pdf-to-md
Convert PDF files to structured Markdown. Auto-detects native-text PDFs (extracted instantly with pymupdf, zero API cost) versus scanned/image PDFs (routed through PaddleOCR). Embedded large images are extracted to disk and referenced via standard Markdown image syntax — you (the agent) then describe them using your built-in Vision capability via the Read tool. No separate API key required. Use this skill whenever the user wants to convert a PDF to Markdown, extract text from PDFs, OCR scanned documents, or turn PDF reports into notes — even if they say "PDF → md", "extract this PDF", or "OCR these scans".
1docx-to-md
Convert DOCX/Word documents to structured Markdown. Extracts headings, paragraphs, and tables losslessly via python-docx. Embedded large images are extracted to disk and referenced via standard Markdown image syntax at their original document position — you (the agent) then describe them using your built-in Vision capability via the Read tool. No separate API key required. Use this skill whenever the user wants to convert a Word document to Markdown, extract content from a .docx, or process Word reports into notes — even if they say "Word → md", "extract this docx", or "turn this report into Markdown".
1docs-to-wiki
>
1