office-tools

Generate and edit Word, Excel, PowerPoint, and PDF documents with OOXML validation.

10|3|Updated Mar 7, 2026
One-click install
npx skills add https://github.com/Cynthia1070711/PHYCOOL_Tools --skill office-tools-cynthia1070711
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: office-tools
Source: https://github.com/Cynthia1070711/PHYCOOL_Tools/tree/main/config-templates/claude/skills/office-tools
Command: npx skills add https://github.com/Cynthia1070711/PHYCOOL_Tools --skill office-tools-cynthia1070711

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdfplumber, reportlab, openpyxl, python-docx, python-pptx, pdf2image, pytesseract, Pillow, pandas, lxml, defusedxml, pptxgenjs, docx, and includes scripts (resource) and references (resource) components.

What problem does it solve? Creating and editing Office documents programmatically is error-prone: Excel formulas don't recalculate, PowerPoint slides ship with overlapping elements, and hand-edited OOXML can corrupt files. This Skill provides distilled workflows, validation scripts, and dependency setup for reliable docx, xlsx, pptx, and pdf generation. ## Core Features & Use Cases - Four-format toolkit: Create and edit Word documents (docx-js, python-docx, OOXML unpack/pack), Excel spreadsheets (openpyxl with financial-model color standards and LibreOffice formula recalculation), PowerPoint decks (pptxgenjs with a mandatory visual QA loop), and general PDFs (pypdf, pdfplumber, reportlab, OCR, form filling). - OOXML schema validation: Validate edited documents against ISO-IEC 29500 XSD schemas to prevent file corruption after XML edits. - Lazy dependency installation: References are always available; Python/npm/system dependencies are installed only when a specific tool is actually triggered. - Use Case: Build a financial model in Excel where inputs are blue, formulas black, and cross-sheet links green, then recalculate all formulas via LibreOffice and deliver an auditable workbook. ## Quick Start Ask the AI to generate an Excel financial model with proper input/formula color coding and recalculated formulas using the office-tools skill.

Frequently Asked Questions about office-tools

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I recalculate Excel formulas after writing them with openpyxl?

openpyxl writes formulas as strings without computing them, so run the recalc.py script which drives a LibreOffice Basic macro calling calculateAll() and saving the workbook. Reading the file afterward returns computed values instead of formula strings.

How do I create a PowerPoint presentation programmatically?

Use pptxgenjs in Node.js to define slide masters, add text, shapes, and images with explicit coordinates, then write the .pptx file. Afterward convert to PDF via LibreOffice and images via Poppler to run a visual QA loop checking for overflow and overlap.

What is the financial model color standard for Excel?

The standard assigns blue font to user inputs, black to formulas, green to cross-sheet links, red to external workbook links, and yellow background to assumption cells. This lets any auditor identify the model structure within seconds.

Can I edit an existing docx file without losing formatting?

Yes, unpack the .docx ZIP container with the provided unpack script, edit document.xml directly with lxml, repack, and validate against ISO-IEC 29500 XSD schemas. Skipping validation risks producing a corrupted file Word cannot open.

Does PDF text extraction work on scanned documents?

Scanned PDFs contain images without a text layer, so pypdf and pdfplumber return nothing. Convert pages to images with pdf2image and Poppler, then run pytesseract OCR with the appropriate language pack such as chi_tra for Traditional Chinese.

When should I not use this skill for PDF generation?

PhyCool PCPT printing business documents such as triangular tent cards, duplex printing, and cut-stack layouts must use the dedicated phycool-pdf-engine instead. This skill covers only general-purpose PDF tasks like form filling, merging, watermarking, and OCR.