Felpborges/skill-reel ? reverse-engineered prompt

Reverse engineered prompt

Build me a Claude Code skill that takes a raw talking head video and turns it into a polished vertical reel with no manual choices.

It should trim out silences, breaths, filler sounds, stumbles, repeated bits, and false starts, then cut on the audio in a way that feels natural and keeps the speech intact. After that, it should turn the result into a punchy 9:16 reel with animated framing, captioning that follows the speaker, clean sound effects, and final audio leveled for social video. I want the whole thing to run from a simple prompt like “edit this reel”, then produce a finished render in render/reel-v1.mp4 and a quick verification step so I know it’s good.

Please wire it up so the flow is basically automatic, but still lets me rerun it if I want a different pass. Use the current docs online if you need to, and make sure the final output matches the style and rules described in the project files.

Are you gonna build this?

make sure you review the code using coderabbit

Try freeSponsored — opens CodeRabbit in a new tab