repowiserepowise

Agent skill

juneyaooo / rea-video

Reverse-engineer any video, shot by shot: filmed, AI-generated or coded, and how to remake it. Breakdowns in the open VIDEO.md format. 逆向一切视频，逐个镜头看是拍的、AI 生成的还是代码做的，再告诉你怎么复刻；拆解结果按 VIDEO.md 格式输出。

★ 8,349stars on GitHubPythonApache-2.0
Install rea-videoView on GitHub★ 8.3kSee this for your own repoAsk this codebase

Repowise maps public repos from their source. Not affiliated with juneyaooo. What is Repowise?

github.com/juneyaooo/rea-videoIndexed at b08faf2

What is rea-video?

rea-video is a command-line tool for reverse-engineering any video shot by shot, showing whether each shot was filmed, AI-generated or coded, and explaining how to remake it. It splits a video into shots and labels each one as filmed, AI-generated, code-rendered, screen capture or a mix, using visual and audio evidence. It is written in Python. To install it, run git clone https://github.com/juneyaooo/rea-video.git and follow the steps below. Its code health is 5.3 out of 10 (Needs_work), ranked #213 of 4,000+ indexed repos. The last commit to rea-video was on Nov 13, 2026, and 15 people have contributed.

As of commit b08faf2, indexed Nov 14, 2026. What it is comes from a model reading the README; the rest is measured from the source and git history, not from the maintainer.

For agentsrea-video.md

Repo facts: type, license, health, rank, contributors
rea-video facts
TypeAgent skill
LicenseApache-2.0
Code health5.3 / 10 (Needs_work)
Health rank#213 of 4,000+ indexed repos
Last commitNov 13, 2026
Contributors15
Bus factor1
Size173 files, 19,075 lines

Install rea-video

Built from the repo's files

  1. 1Clone the rea-video repository.
    git clone https://github.com/juneyaooo/rea-video.git
  2. 2Copy the skill into your Claude Code skills folder.
    mkdir -p ~/.claude/skills && cp -r rea-video/skills/rea-video ~/.claude/skills/

Releases on GitHub (latest v0.1.0, Nov 11, 2026)

Full install notes on GitHub

Explore rea-video

Ask about this code in your agent

This connects Repowise to rea-video's code. It does not install rea-video. To install rea-video, use the install steps.

Useful if you want to change or fork rea-video: your agent can ask how it is put together and get answers that cite its files.

Show the connect command (Claude Code, Cursor, Codex, VS Code)

Run it in a terminal, then type /mcp in Claude Code and sign in with Repowise. No key to paste.

Docs
bash
claude mcp add --transport http repowise https://api.repowise.dev/mcp/juneyaooo/rea-video
Claude Code, Claude, Cursor and VS Code sign you in on first use, free. Codex and Windsurf need an API key: sign in to create one.Sign in for a key

This repo is public, so anyone with a free Repowise account can connect.

Try asking

  • get_risk(["rea_video/vlm.py"])
  • get_answer("how is rea-video put together?")
  • get_why("why is rea-video structured this way?")

Ask about rea-video

Answers come from rea-video's README and source, with the files they cite. Two free answers a day without an account.

Want this for your own codebase? Map your repo free

About this page

Get a page like this for your own codebase

Repowise built this map of juneyaooo/rea-video from its source and git history. It parses every symbol, draws the dependency graph, scores each file's health from complexity, duplication, coverage and churn, finds hotspots and owners in the history, and writes documentation for every module. Your coding agent reads the same index over MCP, so its answers cite real files.

Free for 2 public repos, with a page like this one. No card. See how Repowise works

Prefer local? pip install repowise && repowise init indexes your own checkout, no account needed. Star Repowise on GitHub

juneyaooo/rea-video FAQ

What does rea-video do?

rea-video reverse-engineers a video shot by shot. It labels each shot as filmed, AI-generated, code-rendered, screen capture or a mix, and explains how to remake it.

Which coding agents does rea-video work with?

rea-video works with Claude Code and Codex, and with any agent that can run commands. You ask the agent to install it and break down a video for you.

What does rea-video change in my project?

rea-video writes a breakdown for each video you give it. The breakdown is a report as report.html or PDF for people and a VIDEO.md file for AI agents.

What license does rea-video use?

rea-video is licensed under Apache-2.0.

Code health

5.3out of 10Needs work

Hotspots average 3.3, the place fixes pay off most.

Full health report

On the leaderboards:#62 of 64 Python repos

Key features of rea-video

  • Splits a video into shots and labels each shot as filmed, AI-generated, code-rendered, screen capture or a mix.
  • Writes each breakdown as a report for people, as report.html or PDF, and as a VIDEO.md file for AI agents.
  • Describes live footage in detail, including setups, camera positions, framing, camera moves, lighting and color grade.
  • Breaks down captions, stickers, editing pace and cut timing, and audio such as voice, music BPM and sound effect timing.
  • Lists the material you will need to supply yourself, such as screen recordings, screenshots and product photos.
  • Plans a remake by batching shots according to what the target video model can do.

How juneyaooo/rea-video works

You ask your coding agent to install the rea-video command line and then give it a video file to break down. The rea-video command in rea_video/cli.py hands each step to modules that split the video into shots and the audio into voice, music and effects, then gather evidence and decide each shot's origin. The skills/rea-video folder holds the skill that tells the agent how to run this workflow, and the scripts folder contains helpers that install that skill and check its definitions. Each run produces a report, as report.html or PDF, for people and a VIDEO.md file for AI agents.

The codebase has 173 files and 1,395 symbols in 3 modules, led by Python and Shell. Code health is 5.3 out of 10, rated needs work.