asset-semantic-extractor

Name: asset-semantic-extractor
Availability: InStock
Author: bachdyon

Generate a TOML semantic index for image and video assets using Gemini Vision.

Updated Aug 27, 2026

Search Tags:#video production #semantic analysis #TOML #Gemini Vision #asset indexing

Ready to run

npx skills add https://github.com/bachdyon/video-automator-skills --skill asset-semantic-extractor

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: asset-semantic-extractor
Source: https://github.com/bachdyon/video-automator-skills/tree/main/skills/asset-semantic-extractor
Command: npx skills add https://github.com/bachdyon/video-automator-skills --skill asset-semantic-extractor

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill generates a semantic index for image and video raw assets, providing a structured and reusable representation of the assets for video production workflows.

Core Features & Use Cases

Semantic Index Generation: Creates a TOML file with detailed metadata for each asset, including descriptions, tags, and scene details.
Asset Analysis: Utilizes Gemini Vision to analyze and extract visual and semantic information from the assets.
Use Case: For a video editor working on a project, this Skill can be used to quickly generate a semantic index for all raw video assets, allowing for efficient scene mapping and content organization.

Quick Start

Use the asset-semantic-extractor skill to generate a semantic index for all video assets in the 'raw_assets' directory.

Frequently Asked Questions about asset-semantic-extractor

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

FAQPage Schema

How do I generate a semantic index for raw video assets?▼

Generating a semantic index for raw video assets involves using Gemini Vision to analyze visual content and output a structured TOML file. This TOML file contains detailed metadata, descriptions, and scene details for each asset, enabling efficient scene mapping and content organization.

What is the best way to extract scene details and tags from video production assets?▼

Extracting scene details and tags from video production assets is done by utilizing Gemini Vision for semantic analysis. This mechanism processes raw assets to produce a TOML file populated with detailed descriptions, tags, and scene information for each asset.

Can I use Gemini Vision to create a TOML metadata file for image and video assets?▼

Yes, you can use Gemini Vision to create a TOML metadata file for image and video assets. The system analyzes raw assets using Gemini Vision and produces a TOML file containing detailed metadata, descriptions, and scene details for each asset.

How do I organize raw video assets for efficient scene mapping?▼

Organizing raw video assets for efficient scene mapping requires generating a semantic index using Gemini Vision. This process outputs a TOML file containing detailed metadata, descriptions, and scene details for each asset, allowing for efficient content organization.

Does the asset semantic extraction process work with both images and videos?▼

Yes, the asset semantic extraction process works with both images and videos. It utilizes Gemini Vision to analyze raw assets and outputs a TOML file containing detailed metadata, descriptions, and scene details for each asset.