Rylaispirit Document Converter Suite
Original portable workflow by Rylai.
Use the bundled scripts for deterministic local-file work. Keep source files unchanged and inspect every generated artifact.
Start With A Dependency Check
python scripts/rylai_convert.py doctor
The report distinguishes required Python support from optional routes provided by MarkItDown, Pandoc, LibreOffice, pypdf, python-docx, python-pptx, openpyxl, and pdfplumber.
Convert One File
python scripts/rylai_convert.py convert input.docx output.md
python scripts/rylai_convert.py convert notes.md notes.docx
python scripts/rylai_convert.py convert workbook.xlsx workbook.pdf
Add --overwrite only after checking that replacing the destination is intended.
Convert A Folder
python scripts/rylai_convert.py batch source output --to md --recursive
python scripts/rylai_convert.py batch source output --to pdf --include docx --include pptx
The batch command preserves relative paths and reports every failed file.
Focused Utilities
PDF page operations:
python scripts/rylai_pdf_pages.py info report.pdf
python scripts/rylai_pdf_pages.py extract report.pdf excerpt.pdf --pages 1,3-5
python scripts/rylai_pdf_pages.py merge combined.pdf part-a.pdf part-b.pdf
python scripts/rylai_pdf_pages.py split report.pdf split-pages
python scripts/rylai_pdf_pages.py rotate report.pdf rotated.pdf --pages all --degrees 90
Table extraction:
python scripts/rylai_tables.py data.xlsx table.csv --sheet Summary
python scripts/rylai_tables.py report.pdf table.md --table 2
Template filling:
python scripts/rylai_template_fill.py template.docx filled.docx --values values.json
python scripts/rylai_template_fill.py template.md filled.md --set project=Rylai --set status=Ready
Read references/routes.md when choosing between conversion engines or explaining limitations.
Operating Rules
- Resolve scripts relative to this skill folder.
- Accept local files only; do not download a URL and convert it without explicit user approval.
- Never execute macros, embedded programs, or document attachments.
- Treat OCR as a separate step. A scanned PDF may contain no extractable text.
- Prefer semantic extraction for editing and LibreOffice or Pandoc routes for format conversion.
- Do not promise exact fonts, pagination, animation, chart, formula, or layout preservation.
- Use a dedicated format skill when visual fidelity or advanced editing is the primary requirement.
- Report the selected route, missing dependency, and any known loss in the final answer.