Video Prompting

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.

skills.sh installs: 693
GitHub stars: 190
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add square-zero-labs/video-prompting-skill --skill video-prompting --agent claude-code

Installs into .claude/skills of the current project.

Files

Video Prompting

Overview

Turn a user’s intent into either:

a strong, model-compliant video prompt, or
a strong image-model prompt for a character sheet that will later support image-to-video consistency.

Model-specific video guidance lives in references/models/. Character-sheet guidance lives in references/workflows/character-sheets.md. This file is the entry point: route to the right path, ask the minimum clarifying questions, then draft the prompt in the expected format.