- route table: extension route for products with an existing visual
language, feedback row, derived state tokens stay local
- completion: blocking 0 plus reported unverified; hard-gate surface is
the touched scope; delivery report starts with what and how to open
- design.md created at step 0 with a skeleton, fingerprint line and
change log; product-surface rubric reading; direction delegation
states the chosen card and reason
- layout: hero families, nav forms, footer forms; art-direction page
convergence 6 axes; genre sections; image treatments; placeholder
conventions; multi-screen order; Tailwind theme mapping
- platform: scroll-driven examples, anchor positioning, canvas OT,
three/R3F pins, shadcn style prefixes, Safari 26 notes, subgrid
- design-gate: four result states, exit codes, cwd module resolution,
--url/--out-dir/--strict, oklch contrast, dead selector word match
- Korean font budget split from the Latin baseline
- Restore the step-0 interview as a mechanical gate the skill explicitly
depends on; add harness.md (per-harness question tools, limits,
fallbacks) and brief-interview.md (slots, question cards, rounds).
- Add 10 reference docs absorbed from external design skills
(accessibility, interaction-feel, elevation, color, icons, product-copy,
component-systems, critique, change-review, print-email) and extend
existing references.
- Add a review-only route and two hard-gate clauses (truncated content
reachability, three-flashes limit).
- design-gate: split tap targets into WCAG 2.5.8 and 44px contract layers,
run axe-core when available, and fix false positives found on a real
site (decorative alt="", stacked wordmark line count, url-only pages).
- lint-skill: fail if the interview gate section or its links disappear.
- Ship agents/openai.yaml and THIRD_PARTY_NOTICES.md.
