pptx

Process and manipulate .pptx files for reading, editing, combining, splitting, and generating slide decks.

Updated Jan 26, 2023
One-click install
npx skills add https://github.com/yuyalun-allen/dotfiles --skill pptx-yuyalun-allen
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pptx
Source: https://github.com/yuyalun-allen/dotfiles/tree/main/tools/pi/agent/skills/pptx
Command: npx skills add https://github.com/yuyalun-allen/dotfiles --skill pptx-yuyalun-allen

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires defusedxml, Pillow, lxml, and includes scripts (resource) components.

What problem does it solve?

Many workflows need reliable, programmatic handling of PowerPoint files—reading content, extracting text and visual thumbnails, applying template-based edits, validating structure, and repacking presentations—without manually opening PowerPoint. This Skill centralizes those tasks and automates the extract → edit → clean → pack pipeline so presentations can be processed at scale and integrated into other automation systems.

Core Features & Use Cases

  • Read and extract text and speaker notes from .pptx files using markitdown, and produce visual thumbnails for layout analysis.
  • Template-based editing workflow: unpack a PPTX, duplicate or create slides from layouts, update slide XML, clean orphaned artifacts, and repack a validated .pptx.
  • Create slide decks from scratch using pptxgenjs guidance and examples.
  • Visual QA and conversion utilities: convert to PDF/images via LibreOffice (soffice) and pdftoppm for inspection and automated visual checks.
  • Schema validation and auto-repair routines using provided XSDs and validation scripts to detect broken relationships, duplicate IDs, and content-type mismatches.

Quick Start

Extract text and thumbnails from presentation.pptx, apply template edits, run the cleaning pipeline, and repack the result as output.pptx.

Frequently Asked Questions about pptx

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

FAQPage Schema
How do I extract text and generate thumbnails from pptx files programmatically?

You can extract text and speaker notes from pptx files using markitdown, and generate visual thumbnails by converting slides to PDF via LibreOffice (soffice) and rendering images with pdftoppm for layout analysis.

What is the best way to automate template-based editing of PowerPoint presentations?

Automating template-based editing of PowerPoint presentations involves unpacking the pptx, duplicating or creating slides from layouts, updating slide XML, cleaning orphaned artifacts, and repacking the result into a validated pptx file.

Can I create slide decks from scratch using pptxgenjs?

Yes, you can create slide decks from scratch using pptxgenjs. This Skill provides dedicated guidance and examples for programmatically generating new presentations without requiring manual PowerPoint interaction.

How do I validate and repair broken PPTX files?

You can validate and repair broken PPTX files using provided XSDs and validation scripts that detect broken relationships, duplicate IDs, and content-type mismatches, applying auto-repair routines to fix structural issues.

Does processing PPTX files require LibreOffice and pdftoppm installed?

Visual QA, thumbnail generation, and automated visual checks require LibreOffice (soffice) for PDF conversion and pdftoppm for image rendering, while text extraction and template editing rely on Python libraries like lxml and Pillow.

When should I use this approach instead of manually editing PowerPoint files?

You should use this approach instead of manually editing PowerPoint files when processing presentations at scale, integrating into automation systems, or requiring reliable extract, edit, clean, and pack pipelines without manual PowerPoint intervention.