pawwork

Native .docx generation and editing with Python python-docx: real Heading styles that drive the navigation pane and table of contents, explicit fonts and sizes, native tables, clean paragraph structure. Also reads and parses existing documents. Use this for any Word document, report, letter, or memo request, and for reading or modifying an existing .docx.

PDF parsing (uv + pdfplumber / pypdf): use this for reading or extracting text/tables from any PDF. PDF generation (author print-ready HTML, then print with PawWork's bundled Chromium) is best-effort — where the runtime exposes no print entry point, report that generation is unavailable rather than substituting another tool. Hard rule: never use PyMuPDF / fitz (AGPL).

Native .pptx generation by authoring one SVG per slide and converting with the bundled offline svg_to_pptx tool — every shape stays natively editable in PowerPoint / Keynote / WPS. Also reads and parses existing decks with python-pptx. Use this for any presentation, pitch deck, slides, or .pptx request, and for reading or modifying an existing .pptx.

Native .xlsx generation and editing with Python openpyxl: real formulas the recipient can recalc, explicit number formats and fonts, native charts. Also reads and parses existing workbooks. Use this for any Excel, spreadsheet, or financial-model request, and for reading or modifying an existing .xlsx.