agent-docs

Processes Word, PDF, PowerPoint, and Excel files for conversion, editing, extraction, and validation.

Updated Apr 27, 2026
One-click install
npx skills add https://github.com/Handy369/passto-pi-frame --skill agent-docs-handy369
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-docs
Source: https://github.com/Handy369/passto-pi-frame/tree/main/skills/agent-docs
Command: npx skills add https://github.com/Handy369/passto-pi-frame --skill agent-docs-handy369

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires LibreOffice (soffice), pandoc, pypdf, pdfplumber, reportlab, qpdf, pdftoppm, pdf2image, pytesseract, pypdfium2, html4docx, markitdown[pptx], Pillow, docx (npm package), PptxGenJS, openpyxl, pandas, LibreOffice macros, Headless Chrome, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill solves the problem of needing to create, read, edit, convert, and extract content from common office/document file types (Word, PDF, PowerPoint, Excel) without getting stuck on format-specific tooling and formatting pitfalls.

Core Features & Use Cases

  • Document ingestion & routing: Automatically selects the right processing path based on file type and requested operation.
  • Cross-format conversion: Converts between docx/pptx/xlsx and PDF via LibreOffice/soffice, plus HTML→PDF for faithful CSS rendering.
  • Format-specific editing & extraction: Supports Word XML editing, PDF text/table extraction and form filling, PPTX reading/editing, and XLSX reading/analysis.
  • Quality guardrails: Provides validation-first workflows (Office XML validation/repair; PDF form field validation; Excel formula recalculation guidance) to reduce broken outputs.

Quick Start

Tell the agent: “Convert this file to the requested format and extract the main text for me, then save the converted output.”

Frequently Asked Questions about agent-docs

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

FAQPage Schema
How do I convert Word, PowerPoint, or Excel files to PDF and extract the main text?

For PDF form filling, the Skill validates PDF form fields first to ensure they exist and are compatible, then executes matching scripts to populate the form data deterministically. This validation-first workflow reduces broken outputs and ensures the filled PDF retains its structural integrity.

Does this approach support extracting tables and text from scanned PDFs?

When Office conversion or PDF extraction yields broken outputs, the Skill applies quality guardrails like Office XML validation and repair, PDF form field validation, and Excel formula recalculation guidance. These validation-first workflows check structural integrity before executing matching scripts to reduce formatting errors.

Can I edit the XML of a Word document directly to fix formatting issues?

Yes, you can edit the XML of a Word document directly to fix formatting issues using the Skill's format-specific editing capabilities. It supports Word XML editing by unpacking the docx structure, allowing you to modify the underlying XML code and validate the changes before saving the output.

What is the best way to read and analyze data from an XLSX spreadsheet?

The best way to read and analyze XLSX spreadsheet data is by using openpyxl and pandas within the Skill's execution scripts. It reads the Excel file, analyzes the cell values and formulas, and provides Excel formula recalculation guidance to ensure the extracted data is accurate and reliable.