pptx

Extract text inventory with positions and formatting from PPTX slides.

5.8k|918|Updated Feb 12, 2026

Search Tags:#automation #presentation #pptx #layout-analysis #text-inventory #overflow-detection

Ready to run

npx skills add https://github.com/netease-youdao/LobsterAI --skill pptx-netease-youdao

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pptx
Source: https://github.com/netease-youdao/LobsterAI/tree/main/SKILLs/pptx
Command: npx skills add https://github.com/netease-youdao/LobsterAI --skill pptx-netease-youdao

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires playwright, pptxgenjs, sharp, Pillow, python-pptx, and includes scripts (resource) components.

What problem does it solve?

This Skill streamlines PowerPoint workflow by enabling automated creation, editing, and analysis of PPTX decks, reducing manual formatting and repetitive tasks.

Core Features & Use Cases

Text inventory & layout analysis: extract all slide text with paragraph-level formatting, absolute positions, and placeholder metadata, including content from grouped shapes
Overflow and layout checks: detect text and shape overflow relative to slide bounds to guide design fixes
Template-driven editing: support for bulk text replacements and slide reordering using inventory-backed JSON
End-to-end PPTX automation: combine Python-based parsing (python-pptx) with optional Node.js HTML-to-PPTX workflows for dynamic slide generation

Quick Start

Provide a PPTX file and run the tool to extract its text inventory to a JSON file.

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 formatting details from a PowerPoint PPTX file?▼

You can extract text from a PPTX file by parsing the deck to inventory all slide text, including paragraph-level formatting, absolute positions, and placeholder metadata, outputting the results to a JSON file.

Can I detect text overflow and layout issues in PowerPoint slides automatically?▼

Yes, automated overflow detection checks text and shape boundaries relative to slide bounds, identifying layout issues in PPTX decks to guide necessary design fixes.

How do I perform bulk text replacements across multiple PowerPoint slides?▼

Bulk text replacement is supported by generating a JSON text inventory from the PPTX file, then using that inventory-backed JSON to apply template-driven edits and automate text substitutions.

Does python-pptx extract text from grouped shapes in PowerPoint presentations?▼

Yes, using python-pptx for parsing allows the extraction process to inventory text content from grouped shapes, capturing absolute positions and placeholder metadata alongside standard slide text.

Do I need Node.js tools to automate PPTX creation and editing workflows?▼

Node.js tools like playwright, pptxgenjs, and sharp are optional dependencies for HTML-driven PPTX workflows, while Python with python-pptx handles the core parsing and text inventory tasks.

What's the best way to generate dynamic PowerPoint slides from HTML content?▼

The best approach is combining Python-based parsing using python-pptx with optional Node.js HTML-to-PPTX workflows utilizing pptxgenjs and playwright to dynamically generate slides.