Image-Heavy Presentation Detection Skill

Detect image-heavy presentations by analyzing text-to-slide ratio and average text per slide.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/Absolute-Space-GHCP/leo-participation-translator --skill image-heavy-presentation-detection-skill
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Image-Heavy Presentation Detection Skill
Source: https://github.com/Absolute-Space-GHCP/leo-participation-translator/tree/main/.cursor/skills/image-heavy-detection
Command: npx skills add https://github.com/Absolute-Space-GHCP/leo-participation-translator --skill image-heavy-presentation-detection-skill

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the challenge of processing presentations where crucial information is embedded within images rather than plain text, ensuring that no key concepts are missed during RAG ingestion.

Core Features & Use Cases

  • Image-Heavy Detection: Automatically identifies presentations with a low text-to-slide ratio.
  • Contextual Analysis: Analyzes text density per slide and overall text volume.
  • Remediation Guidance: Provides actionable options like speaker note extraction or companion summary files.
  • Use Case: When ingesting a creative pitch deck, this skill flags slides that are primarily visual mood boards, prompting the user to add descriptive text or speaker notes for better AI understanding.

Quick Start

Use the image-heavy detection skill to analyze the presentation file 'campaign_brief.pptx'.

Frequently Asked Questions about Image-Heavy Presentation Detection Skill

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

FAQPage Schema
How do I detect image-heavy presentations before RAG ingestion?

Detecting image-heavy presentations involves analyzing the text-to-slide ratio and average text per slide. This flags files where crucial information is embedded in visuals rather than extractable text.

Why does my presentation analysis miss key concepts from visual slides?

Presentation analysis misses key concepts from visual slides because crucial information is embedded within images rather than plain text. Low text density per slide prevents standard text extraction from capturing the full context.

What is the best way to enrich content for slides with low text density?

The best way to enrich content for slides with low text density is using remediation options like speaker note extraction and companion summary file creation. These add descriptive text for better AI understanding.

Can I extract speaker notes to provide more context for image-heavy slides?

Yes, you can extract speaker notes to provide more context for image-heavy slides. This Skill supports speaker note extraction and companion summary file creation to ensure no key concepts are missed during RAG ingestion.

Does this slide analysis tool work with creative pitch decks that use visual mood boards?

Yes, this slide analysis tool works with creative pitch decks using visual mood boards. It flags slides that are primarily visual and prompts the user to add descriptive text or speaker notes for better AI understanding.

When should I not rely on automated text extraction for presentation files?

You should not rely on automated text extraction for presentation files when the text-to-slide ratio is low. In these image-heavy cases, key concepts are conveyed visually, requiring companion summary files or speaker notes for accurate ingestion.