Turns user intent into model-specific prompts for text-to-video and image-to-video generation across seven models (Ovi, Sora, Veo 3, Wan 2.2, Seedance 2.0, LTX-2, LTX-2.3), plus character sheet prompts for image models when you need consistent characters across shots. Routes requests, asks minimal clarifying questions, then follows strict per-model formatting rules stored in reference files. Handles the full workflow from character turnaround to scene still to i2v prompt if you're building a sequence. Strips out metadata like duration and aspect ratio from the prompt text itself, since those live in API parameters. Useful if you're working with multiple video models and tired of remembering which one wants camera movement first versus action beats, or how to structure dialogue differently for each.
npx skills add https://github.com/square-zero-labs/video-prompting-skill --skill video-prompting