timothywarner-org

Pptx Shredder — AI skill for Claude Code

AI community

Transform PowerPoint presentations into LLM-optimized markdown while preserving instructional design narrative.

How to install Pptx Shredder

This entry records only its repository, not the path inside it, so there is no exact command to give. Open timothywarner-org/pptx-shredder and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Pptx Shredder does

Transform PowerPoint presentations into LLM-optimized markdown while preserving instructional design narrative. Built for technical trainers.

Alternatives in AI

  • Qwen Code — A command-line AI workflow tool adapted from Gemini CLI, optimized for Qwen3-Coder models with enhanced parser 20.8k ★
  • Skill Seekers Roadmap — Transform Skill Seekers into the easiest way to create Claude AI skills from any knowledge source - documentat 11.1k ★
  • Ante — Ghost in your shell 1.9k ★

README

PPTX Shredder 🎯

**One tool. One purpose. Rock solid.**

Transform PowerPoint presentations into LLM-optimized markdown. Built for technical trainers who need dead-simple reliability.

**Does one thing and does it very, very well** ✨

⚡ Quick Start

Step 1: Get Running (30 seconds)

# Clone and setup
git clone https://github.com/timothywarner-org/pptx-shredder.git
cd pptx-shredder
pip install -r requirements.txt

# Drop your PPTX files in input/ folder, then:
python shred.py

# ✅ Done! Your markdown is in output/

Step 2: Use from Claude Desktop (optional)

# Global access (works from any directory)
claude mcp add pptx-shredder npx -y @timothywarner/pptx-shredder-mcp

# Now use in Claude Desktop from any project:
# "Use shred_pptx to process my presentation.pptx"

🧠 How It Works (Now with AI!)

**NEW: Intelligent Extraction with DeepSeek LLM** 🤖

flowchart TD
    A[📁 Drop PPTX in input/] --> B[🚀 Run python shred.py]
    B --> C[🔍 PowerPoint Object Model]
    C --> D[📝 Structured Content Extract]
    D --> E[🧠 DeepSeek LLM Analysis]
    E --> F[🎯 Learning Objectives Detection]
    E --> G[📚 Module Boundary Recognition]
    E --> H[🏷️ Activity Type Classification]
    E --> I[⏱️ Time Estimation]
    F --> J[🧩 Intelligent Chunking]
    G --> J
    H --> J
    I --> J
    J --> K[📋 Rich YAML Metadata]
    K --> L[📄 High-Quality Markdown]
    L --> M[📂 Save to output/]
    
    N[🖥️ Claude Desktop
Any Directory] --> O[📦 npx @timothywarner/
pptx-shredder-mcp] O --> P[🔌 MCP Server] P --> B style A fill:#e1f5fe style M fill:#e8f5e8 style N fill:#fff3e0 style O fill:#e8f0ff style E fill:#ff9800 style J fill:#f3e5f5

📁 Project Structure

pptx-shredder/                 🏠 Main project directory
├── 🚀 shred.py               ← Entry point (run this!)
├── 📋 requirements.txt       ← Py