rea-video
A skill plus CLI that takes a video apart shot by shot: whether each shot was filmed, AI-generated, 3D or coded, what overlays and sound were added, and how you could remake it. Writes a readable report and a layered VIDEO.md file for agents. Apache-2.0; v0.1.0.
Test results
Run with our skill harness: the skill alone in a throwaway project, invoked by name, and the real output file checked. Skills are tested in Claude Code and Cursor only so far.
| Client | Result | Last passed | What we checked |
|---|---|---|---|
| Claude Code | Not tested yet | never | |
| Cursor 2026.11.13-eacade1 | Failed Tested 2026-11-15 | never passed | rea-video: {'rea-video decompose ran in the project (fresh breakdown.json + VIDEO.md)': True, 'answer.md with token': True, '0-4 s called code/template render': True, '4-8 s called still photo + zoom/pan': True, '8-12 s |
Skill version: github.com/JuneYaooo/rea-video @ 820d661e (2026-11-15).
Get it
The skill’s files and install instructions are in its repository: github.com/JuneYaooo/rea-video.
Not working?
Fixes from our own test runs: Skill not working in Cursor?