What problem does it solve? Creating publication-quality scientific diagrams (flowcharts, neural network architectures, biological pathways, circuit diagrams) normally requires manual drawing tools or complex code. This Skill generates them from plain-language descriptions and iteratively refines them until they meet quality thresholds for the target document type. ## Core Features & Use Cases - Natural Language Diagram Generation: Describe a CONSORT flowchart, Transformer architecture, MAPK pathway, or IoT system diagram and receive a publication-ready PNG via the OpenRouter API. - Smart Iterative Refinement: Gemini 3.1 Pro Preview reviews each generated image against document-type quality thresholds (8.5/10 for journals down to 6.5/10 for presentations) and only regenerates when the score falls short. - Structured Review Logs: Every run saves versioned images plus a JSON log with per-iteration scores, critiques, and early-stop reasons. - Use Case: A researcher writing a journal submission runs the generator with --doc-type journal to produce a CONSORT participant flow diagram that is automatically refined until it scores 8.5/10 or higher. ## Quick Start Set the OPENROUTER_API_KEY environment variable, then ask the assistant to generate a scientific diagram such as a CONSORT flowchart saved to figures/consort.png with journal quality settings.
