Run Python code in Gemini's sandboxed execution environment to verify math, test regex patterns, simulate logic, or validate algorithms without local execution. Use when you need computational verification without side effects.
Dispatch rule for consulting the five Gemini agents. Read this when deciding whether to get a Gemini second opinion and which agent to route to (researcher, validator, challenger, summarizer, reviewer). Enforces a one-consult-per-turn cap on manual dispatches.
Analyze files (PDFs, images, audio, video, large source files) via Gemini's multi-modal file analysis. Use when a file is too large for Claude's context or when the file is a non-text format requiring visual/audio understanding.
Generate images using Gemini's native image generation (Nano Banana) or Imagen 4. Use for UI mockups, hero images, product shots, infographic frames, or any visual content creation task.
Perform live-web research via Gemini's search-grounded answers or deep research synthesis. Use when a question involves post-training-cutoff information, library versions, CVEs, API docs, or any claim needing a primary source with citations.
Generate short video clips using Veo 3.1. Async start+poll pattern; returns an MP4 file. Use for product demos, B-roll footage, short animations, or motion design concepts.
Master router for the Gemini plugin. Use when uncertain whether a Gemini consult is warranted; covers cost discipline, anti-hallucination triggers, and the five subagent roles. Invoke before any other gemini- skill.