design-policy
Skill0 starsChanged 5 months agoNo licenceView on GitHub
Frontend design / UX policy hub — 프론트엔드 디자인·UX 정책 네 영역을 증상별로 구분해 맞는 reference shard 로 라우팅한다. (1) design tokens → Tailwind — CSS custom property design tokens 가 `:root` 에 있는데 컴포넌트는 여전히 raw `bg-rose-500` / `border-zinc-200` / `shadow-sm` 를 씀, 토큰을 `@theme inline` 으로 utility 클래스로 노출해 `bg-theme-500` 류 token class 로 bridge → tailwind-v4-theme-bridge. (2) mobile header IA — 헤더가 모바일에서 crowded ("왜 모바일이 무겁지?", 헤더 200px 초과, primary task 가 fold 아래로 밀림), 헤더엔 primary task 만 두고 meta chips / breadcrumb / filter 는 below the fold 보조 strip 으로 → mobile-header-info-architecture. (3) click-to-compare UX — 아이템 하나 클릭하면 나머지 전부와 "이거랑 얼마나 비슷?" 비교 ("more like this" / "이 시설과 비슷한 다른 시설"), multi-select 강요 없이 single-vector cosine similarity 정렬 + ≈XX% 배지 → click-anchor-similarity. (4) design-feedback checkpoint — 사용자가 UI/UX 변경을 제안하며 의견을 물을 때 ("어때?", "어떻게 생각해?", "너의 생각을 먼저") 즉시 구현 금지, 의견·우려·대안 1-2개 FIRST 제시 후 동의 신호 받고 구현 → design-feedback-checkpoint. 트리거 — `@theme inline`, design token, `bg-rose-500`, `shadow-soft`, 모바일 헤더 crowded, meta chips, below the fold, cosine similarity, "more like this", "이 시설과 비슷한", ≈XX% 배지, "어때?", "너의 생각을 먼저".
In this repository21 other files it gives its agents.
- adsense-content-approval-strategySkill
- apple-buildSkill
- bulk-data-via-script-not-tokensSkill
- consulting-deck-craftSkill
- data-go-kr-api-quirksSkill
- docs-toc-shards-styleSkill
- external-content-citation-policySkill
- feature-flag-removalSkill
- geometric-folding-fabricationSkill
- geometric-foldingSkill
- git-commit-message-qualitySkill
- kakao-map-client-nav-relayoutSkill
- leaflet-marker-hitboxSkill
- macos-nativeSkill
- mit-ocw-vaultSkill
- obsidian-dailySkill
- obsidian-knowledgeSkill
- ssg-determinismSkill
- swiftuiSkill
- tier-grading-systemSkill
- writing-tone-personalSkill
The file
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.