Moh4696/cinematic-skill ? reverse-engineered prompt

Reverse engineered prompt

Build me a coding agent skill that can make narrated cinematic mini films from a simple prompt, like “make me a 90 second documentary about the Wright brothers.”

I want it to write the script, generate or record the voice, find suitable public domain images with their licenses, and turn everything into one continuous camera move over a designed scene with photos, maps, cards, stamps, counters, and captions that match the narration. The style should feel like a polished documentary or explainer, with a strong visual theme and sound effects, and it should be able to retime the whole film automatically if the voice changes.

Please make it work in a way that is repeatable and cheap to rerun, with every frame drawn from code rather than using generated video. It should also create credits, check for bad sources, and give me a draft I can review before the final render. If you need current docs for any tools, look them up online first.

Are you gonna build this?

make sure you review the code using coderabbit

Try freeSponsored — opens CodeRabbit in a new tab