Image Generator Skill

Context & Problem

Visual generation converges toward accepting first output ("looks good enough") and following technical specifications rigidly. This produces generic aesthetics and misses Gemini 3's reasoning capabilities.

This skill provides multi-turn reasoning partnership methodology with professional quality standards.

Core Principles

1. Reasoning mode over prediction mode - Creative briefs (Story/Intent/Metaphor) activate reasoning; technical specs don't
2. Multi-turn partnership - Teach Gemini your standards through principle-based feedback
3. Professional quality gates - Explicit pass/fail criteria (99% spelling, not "check spelling")
4. Autonomous agency - Batch mode without permission-asking between visuals