What problem does it solve? Creating video content programmatically requires navigating complex multimodal APIs, async polling, and authentication flows. This Skill gives your AI agent a complete, copy-paste-ready workflow for generating videos with Google's Gemini Omni 1.1 Flash model through the Pixazo API gateway. ## Core Features & Use Cases - Four video operations: text-to-video, image-to-video, reference-to-video, and video-to-video editing, all routed through one API with selectable 3-10 second clip durations. - Guided authentication: walks the agent through acquiring a Pixazo API key once and saving it to ~/.pixazo/api-key so it is never requested again. - Async polling and error handling: includes a polling loop for task completion plus a status-code table (401/402/429/4xx/5xx) with user-friendly recovery messages. - Use Case: Ask your agent to "create a 10-second cinematic clip of a sunset over the ocean" and it submits the request, polls until ready, and returns the video URL. ## Quick Start Ask your agent to generate a short video from a text prompt using Gemini Omni 1.1, and provide your Pixazo API key when prompted.