gem
Multimodal AI processing using Google Gemini. Use for analyzing PDFs, images, videos, YouTube links, and other large documents. Ideal when you need to extract information from files that require vision or multimodal understanding.
When & Why to Use This Skill
This Claude skill leverages Google Gemini's advanced multimodal capabilities to process and analyze complex data formats including PDFs, images, videos, and YouTube links. It enables users to extract deep insights, summarize long-form content, and perform visual reasoning across multiple file types through a streamlined CLI interface, bridging the gap between text-based AI and visual media.
Use Cases
- Automated Document Analysis: Quickly summarize lengthy PDF reports, whitepapers, or legal documents to extract key findings and actionable data points.
- Video Content Intelligence: Generate concise summaries and extract specific information from YouTube videos or MP4 files without the need for manual transcription or viewing.
- Visual Data Extraction: Analyze images, charts, and diagrams to convert visual information into structured text, descriptions, or analytical insights.
- Cross-Media Comparison: Compare multiple files of different formats (e.g., a PDF report vs. an infographic) to identify discrepancies, similarities, or trends.
- Web-Enhanced Research: Combine multimodal file analysis with real-time web search to verify facts or update information found within static documents.
| name | gem |
|---|---|
| description | Multimodal AI processing using Google Gemini. Use for analyzing PDFs, images, videos, YouTube links, and other large documents. Ideal when you need to extract information from files that require vision or multimodal understanding. |
Gemini Multimodal Tool
Use the ai-gem CLI tool for multimodal AI processing via Google's Gemini API.
Usage
# Text queries
ai-gem "Write a haiku about Python programming"
# Analyze documents
ai-gem "Summarize this document" document.pdf
# Analyze images
ai-gem "What's in this image?" photo.jpg
# Process YouTube videos
ai-gem "Create a 5-point summary" "https://youtu.be/VIDEO_ID"
# Compare multiple files
ai-gem "Compare these files" file1.pdf file2.png
# Web search
ai-gem "Current AI news" --search
Requirements
GEMINI_API_KEYenvironment variable must be set- The
hamelpackage must be installed:pip install hamel
Supported Input Types
- PDFs
- Images (PNG, JPEG, GIF, WebP)
- Videos (MP4, etc.)
- YouTube URLs
- Plain text files
- Multiple files for comparison