gemini-media-task-planning

Plans Gemini work for video and long-document inputs, model tier selection, real-time audio or video sessions, search grounding, and context caching, with explicit checks of current limits before any paid or uploaded request. Use when the user says "analyze this video", "feed a huge document to gemini", "which gemini model should I use", "set up a live voice session", or "ground the answer with search". Not for supplying API credentials, promising model availability, or substituting for verification of current quotas.

Version

v1.0.0

Size

7 KB

Updated

2026-10-02

Your client verifies the signature before reading. This explicit manual read is available on every plan. Free automatically loads five chosen skills; paid plans automatically load relevant skills across the library.