What problem does it solve? Creating AI-generated video with Google Veo requires crafting precise prompts covering camera movement, subject, action, environment, and audio, plus managing cost, duration, and model selection. This Skill provides structured guidance, prompt formulas, and ready-to-use examples so video generation requests produce consistent, high-quality results on the first attempts. ## Core Features & Use Cases - Text-to-Video and Image-to-Video: Generate clips from text prompts or animate existing images with motion descriptions via the nano-banana CLI. - Prompt Engineering Framework: Five-part prompt formula (camera + subject + action + environment + audio) with camera movement references, dialogue formatting, and layered audio design. - Cost-Optimized Workflow: Iterate with the fast model at ~$1.20 per video before final renders on the premium model, with duration, resolution, aspect ratio, and seed controls. - Use Case: A marketer needs an 8-second product shot. The Skill guides crafting a dolly-in prompt with studio lighting terms, suppresses subtitles, and runs nano-banana --video with the right flags. ## Quick Start Ask the AI to generate a video of your scene using the nano-banana video skill, describing the camera movement, subject, and mood you want.
