Google

This skill should be used when the user specifically asks for Veo, or names a Veo-specific control: "generate video with Veo", "extend this video" / "video-to-video", "first and last frame transition", "ingredients to video" / "consistent characters across shots", or integrating with an existing Veo pipeline. Not the default for a plain "generate a video" / "make a video from this photo" request with no Veo-specific control named — prefer Gemini Omni Flash for that. Reach for this skill only when the task specifically needs Veo's own controls.

This skill should be used when the user asks to "analyze video", "summarize video", "extract video transcript", "understand video content", "video to text", "describe video", "ask questions about video", or "what happens in this video". Takes a local video file or a public YouTube URL and returns text: summaries, timestamped event lists, transcripts, visual descriptions, or answers. Out of scope, and refused rather than attempted: uploading video to storage, files too large to send in one request, bucket objects and pre-signed URLs, clipping, frame-rate control, and generating video.