What problem does it solve? Creating video clips from text descriptions normally requires complex video editing tools or direct integration with a video generation model. This Skill lets an AI agent call the Mochi Video API through the Pixazo gateway to produce a roughly 5-second video from a plain text prompt, handling authentication, submission, and polling automatically. ## Core Features & Use Cases - Text-to-Video Generation: Submit a prompt (plus an optional seed) to the Mochi v1 endpoint and receive a fixed ~5-second video clip. - Managed API Key Flow: Guides the agent to find or securely store a Pixazo API key in ~/.pixazo/api-key so the user only provides it once. - Async Polling & Error Handling: Includes a polling loop for the asynchronous generation task and clear user-facing messages for 401, 402, 429, 4xx, and 5xx responses. - Use Case: A content creator asks the agent to "generate a video of a sparrow flying through a forest" and receives a ready-to-share video URL after the task completes. ## Quick Start Ask the agent to generate a short video of any scene you describe, and it will use the Mochi skill to produce the clip and return the video URL.