framedex

Indexes video and photo files into a searchable, structured format with metadata and previews.

372|23|Updated May 21, 2026
One-click install
npx skills add https://github.com/Simbastack-hq/framedex --skill framedex
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: framedex
Source: https://github.com/Simbastack-hq/framedex/tree/main
Command: npx skills add https://github.com/Simbastack-hq/framedex --skill framedex

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires whisperx, pillow, osxphotos, opencv-python-headless, onnxruntime, requests, PyYAML, insightface, onnxruntime, opencv-python-headless, requests, PyYAML, insightface, onnxruntime, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill turns your video and photo archive into a portable, plain-text knowledge base, allowing you to search, reason about, and trust your media for decades.

Core Features & Use Cases

  • Video Indexing: Automatically generate metadata for video clips, including GPS location, transcripts, translations, face detection, and AI scene descriptions.
  • Photo Indexing: Similar to video, but for still photos, including EXIF data, GPS location, face detection, and scene descriptions.
  • Search and Query: Easily search and filter your media based on various criteria like location, keywords, rating, and time of day.
  • Summary Generation: Generate summaries for folders and drives, providing an overview of the content.
  • Integration with Lightroom: Export ratings and keywords into Lightroom for easy access and organization.
  • Use Case: Imagine you have a large collection of videos and photos from various events. Use this Skill to automatically index and organize them, making it easy to search for specific moments or scenes.

Quick Start

Use the framedex skill to index all videos and photos in the folder '/path/to/your/media'.

Frequently Asked Questions about framedex

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

FAQPage Schema
How do I index a video and photo archive to make it searchable?

Indexing a video and photo archive automatically extracts metadata like GPS location, transcripts, face detection, and AI scene descriptions into a portable, plain-text knowledge base for easy search and query.

What metadata is automatically extracted during photo and video indexing?

During photo and video indexing, the system automatically extracts GPS location, transcripts, translations, face detection data, EXIF data, and AI-generated scene descriptions to build a searchable knowledge base.

Can I use face detection and AI scene descriptions to search my media collection?

Yes, you can search and filter your media collection using automatically generated face detection and AI scene descriptions, querying by location, keywords, ratings, and time of day.

Does Python media processing support extracting GPS and transcripts for video indexing?

Yes, video indexing uses Python libraries like whisperx for transcripts, insightface for face detection, and onnxruntime for AI analysis to extract GPS and generate scene descriptions.

What is the best way to organize extensive media collections into a knowledge base?

Organizing extensive media collections into a plain-text knowledge base with folder and drive summaries allows you to search, reason about, and trust your media archive for decades.

How do I export generated keywords and ratings into Lightroom?

To export generated keywords and ratings into Lightroom, use the integration feature that passes indexed metadata from your portable knowledge base directly into Lightroom for easy access and organization.