ALBEDO-TABAI

Video Expert Analyzer Vnext

Name: Video Expert Analyzer Vnext
Author: ALBEDO-TABAI

Productivity community

SOURCE https://github.com/ALBEDO-TABAI/video-expert-analyzer-vnext

Description

Long-task-oriented video analysis skill for Claude Code (/vea) — resumable staged execution, automatic parallel scoring, OpenClaw orchestration, audiovisual analysis with agent handoff

Installation

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

README

[![Version](https://img.shields.io/badge/version-3.0.0-blue)](https://img.shields.io/badge/version-3.0.0-blue) [![License](https://img.shields.io/badge/license-MIT-green)](https://img.shields.io/badge/license-MIT-green) [![Python](https://img.shields.io/badge/python-3.9+-yellow)](https://img.shields.io/badge/python-3.9+-yellow) [![AI Models](https://img.shields.io/badge/AI-GPT--5.4%20%7C%20Kimi%20K2.6%20%7C%20GLM--5v--turbo%20%7C%20Xiaomi--v2--omni-purple)](https://img.shields.io/badge/AI-multi--model-purple)

**🌐 Language / 语言** [English](#-video-expert-analyzer-vnext) | [中文](#-视频专家分析器-vnext)

🎬 Video Expert Analyzer VNext

**Next-generation** AI-powered professional video analysis tool — evolved from [v2.x](https://github.com/ALBEDO-TABAI/video-expert-analyzer) with **standardized storyboard tables**, **multi-dimensional audiovisual reports**, and a **resumable parallel pipeline** designed for long videos.

🆕 What's New in VNext (vs v2.x)

Area	v2.x	VNext
📋 Storyboard	Basic scene list	Standardized storyboard table with shot size, lighting, camera movement, visual style, technique, voiceover, on-screen text, and screenshot per scene
📊 Audiovisual Report	5D scoring report	Multi-dimensional audiovisual analysis — 25 route-specific frameworks across 4 families (Narrative / Atmospheric / Meme / Graphic), with SVG diagrams
🔄 Pipeline	Single-pass, restarts on failure	Resumable staged execution — prepare → score → merge → finalize, with `run_state.json` checkpoints
⚡ Performance	Sequential scoring	Parallel batch scoring — configurable concurrency (default: 4 workers), vision API calls run simultaneously
🎯 Video Routing	4 scene types	19 video type classifications via dual-axis routing (5 Visual × 5 Audio = 25 route combinations)
🤖 Model Support	Gemini / Kimi / Claude	GPT-5.4, Kimi K2.6, GLM-5v-turbo, Xiaomi-v2-omni tested