Video reverse engineering

ReaVideo
Reverse any video.

Talking-head, tabletop, AI clips, 3D, motion graphics, mixed edits — get a shot-by-shot report on how the picture, captions, cuts and audio were made, plus a plan to remake it.

Original live shoot ↔ AI remake with a new product

Coverage

What ReaVideo can break down

Every shot is judged on its own, then put back on the original timeline — so mixed videos stay honest.

Live footage

Talking-head, tabletop, handheld demos, vlogs. Setups, camera positions, lighting recipes and grade notes.

AI video

Evidence per shot, reverse-engineered prompts, and how to batch generations across models.

Avatar / lip-sync

Which shots are portrait-driven, what face and audio you still need to supply.

3D & code motion

Blender / C4D explainers or Remotion-ready kinetic type, UI demos and chart cards.

Screen recordings

Marks real material you must capture yourself, separate from generated filler.

Mixed edits

AI characters + coded UI + real capture, each shot classified, then re-timed.

Workflow

From a video file to a remake plan

Built for AI agents. Drop a path into Claude Code or Codex and let the skill run the full pipeline.

01

Install the skill

Point your agent at github.com/JuneYaooo/rea-video. It installs the CLI, reads the workflow, and starts.

02

Shot-by-shot report

You get a one-line verdict, per-shot evidence, prompts, captions, audio BPM and a full HTML report.

03

Remake recipe

The plan splits what to film, generate or code — ready for capsule-cinema or your own pipeline.

One-click remake

Keep the motion. Swap the product.

After breakdown, remake with the same camera moves, pacing and cuts — only the elements you choose change. Web remake is coming to reavideo.net; the open recipe already ships in capsule-cinema.

Examples

Reports people can read without installing

Sample breakdowns from the open-source project — mixed media, 3D explainers, and more.

Thumbnail of a mixed AI and code UI video breakdown

Mixed-media clip · 19s · 10 shots

AI dialogue + code UI + 8 seconds of real screen capture. Five dialogue shots share one set, so one generation covers them.

Thumbnail of a 3D salted-egg explainer video

3D explainer · 67s · 21 shots

All 3D with AI narration. Doable as about ten video generations, or have an LLM write Blender / Three.js code.

FAQ

Questions before you install

Is ReaVideo free?

The CLI and skill are open source. The hosted remake experience on reavideo.net is in early access — email us if you want in.

Do I need a vision model?

No. Without one it still works; with Gemini or Doubao the live / AI / 3D calls get sharper and every shot gets a reverse-engineered prompt.

What is one-click remake?

A remake that keeps camera, motion, pacing and transitions from the original, while swapping the subject, product or setting you choose.

Who is this for?

Creators, growth teams and AI builders who want to learn from reference videos instead of guessing prompts and shot lists.

How is this different from a transcript tool?

Transcripts give you words. ReaVideo gives you production: how each frame was made, what to film, generate or code, and a remake path.

Start reverse-engineering videos today

Run the open-source skill now, or join the waitlist for hosted remake on reavideo.net.