Excalidraw Render Skill

Make a polished Excalidraw diagram from a rough input, without baby-sitting. The main agent thinks in pixels (by viewing rendered PNGs); a Haiku sub-agent does the JSON work.

Core principle — cost discipline

A .excalidraw file is huge: a 10-box diagram is 3–5K tokens. Reading or editing it with the main model is wasteful and slow. Vision on a rendered PNG is far cheaper and far more accurate for layout judgment.

The main agent MUST:

• ✅ View the rendered PNG to judge correctness (this is what vision is for)
• ✅ Plan layouts up-front (positions, sizes, colors) — architectural judgment
• ✅ Critique specific visual issues from the PNG (overlaps, clipping, misalignment)
• ✅ Dispatch surgical fix instructions to a Haiku sub-agent