Auto Markup

End-to-end automatic markup — recreate a page or component as HTML/CSS from a target screenshot (or UI Contract IR), driven by deterministic signal tools with an optional VLM assist. Pipeline; scaffold the landmark skeleton (contract scaffold), converge composition (build page - missing/extra components, ordering, stacking gaps), converge each part (build component + report.json), then audit decoration (check palette / tokens / theme). Works with any agent model including Haiku; the tools are pure Playwright + pixel math, no API key required. Use when asked to implement markup from a design image, rebuild a page to match a reference, or prove a screenshot-to-HTML loop converges.

mizchi Updated 419 repo stars
The same web page on a phone, a tablet and a desktop monitor; a magnifying glass over the desktop finds overlapping text outlined in red, while a robot and a pe

File contents

mizchi/vlmkit commit 993a5846e4

Frequently asked questions

npx get-skill add mizchi/auto-markup-2