What problem does it solve? Creating professional diagrams manually in draw.io is slow, and asking an LLM directly produces inconsistent layouts with overlapping shapes and crossing edges. This Skill turns natural language descriptions into well-structured .drawio files with enforced layout rules, then exports them locally via the draw.io desktop CLI. ## Core Features & Use Cases - 6 diagram type presets: ERD, UML Class, Sequence, Architecture, ML/Deep Learning, and Flowchart, each with predefined shapes, styles, and layout conventions. - Self-check and iterative refinement: reads the exported PNG with a vision model, auto-fixes 6 issue types (overlaps, clipped labels, stacked edges), then supports a 5-round targeted-edit review loop. - Production layout rules: grid-aligned coordinates, complexity-scaled spacing, routing corridors, a 7-color semantic palette, and animated connectors for data-flow diagrams. - Use Case: Describe a microservices e-commerce architecture with API Gateway, Kafka, and per-service databases, and receive an exported PNG plus an editable .drawio source file. ## Quick Start Ask the agent to create a microservices architecture diagram with an API gateway, auth and order services, Kafka, and separate databases, exported as a PNG.
