rea-video Reverse-Engineers Videos Shot by Shot
rea-video is an open-source agent skill that analyzes videos shot by shot, identifying live footage, AI generation, 3D, code-rendered motion graphics, captions, edits, audio, and remake requirements. It produces an HTML report and supports Claude Code and Codex. [GitHub](https://github.com/JuneYaooo/rea-video)
rea-video’s strongest idea is treating video analysis as production forensics rather than one-click imitation.
- –Combines shot detection, frame measurements, OCR, metadata, audio analysis, and optional vision-model review
- –Separates remake paths by medium: reshoot live footage, generate AI shots, or recreate motion graphics with code
- –Reports strong self-tested accuracy, but the evaluation sets are small and platform compression can reduce offline reliability
- –Offline, tools-only analysis lowers costs; adding Gemini, Doubao, or another vision model improves ambiguous cases
- –Useful for AI video creators, developers studying production workflows, and teams auditing how reference content was made
DISCOVERED
1h ago
2026-11-06
PUBLISHED
1h ago
2026-11-06
RELEVANCE
AUTHOR
GithubProjects