DESIGN/设计资源·MOTION
dickwu/apple-design-skill
Bring Apple's HIG into your cross-platform stack and let every screen pass design review
一个让AI助手按苹果设计规范审查跨平台UI的技能。A cross-platform design reviewer that checks your UI against Apple's Human Interface Guidelines, for apps built with Flutter, Tauri, Electron, or React Native.
怎么装:Install: npx skills add dickwu/apple-design-skill
02 / 现在的位置02 / Why now
首次发现FIRST SEEN
03 OCT 202603 OCT 2026
增长GROWTH
+6.2%+6.2%
937 → 995 stars · 4 个快照937 → 995 stars · 4 snapshots
状态STATUS
持续活跃Active
项目近 7 天仍有提交,说明还在维护更新995 stars and 89 forks show community interest
03 / 它能帮你做什么03 / What it helps you do
检查界面设计是否符合苹果规范
把苹果设计术语翻译成Flutter等框架的对应叫法
自动从苹果官网拉取最新的设计指南
在Cursor和Claude Code里直接做设计评审
用Liquid Glass风格规则检查跨平台应用
Check UI against Apple's 123-page HIG
Translate design rules to Flutter, React Native, Tauri, Electron
Run design reviews inside Claude Code or Cursor
Keep references updated with a single command
04 / 安装04 / Install
$ README 里给出的安装方式。The installation method given in the README.
$ README 里给出的安装方式。The installation method given in the README.
两种装法选一个即可 —— 上面那条给命令行用户,下面那条给写代码的用户。Pick one of the two — the first is for command-line users, the second for people writing code.
用 npx skills add dickwu/apple-design-skill 安装,或者 git clone 到 ~/.claude/skills/apple-design。Install with `npx skills add dickwu/apple-design-skill` or clone it manually into your Claude skills folder.
05 / 限制与风险05 / Limits and risk
风险不是警告,是可信度的一部分。以下结论只基于文档静态扫描,我们不会执行项目里的任何代码。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
未知Unknown
静态扫描STATIC SCAN
在 README、SKILL.md 和依赖清单中没有匹配到已知风险模式。No known risk patterns matched in the README, SKILL.md or dependency list.这不等于安全that does not mean it is safe,只能说明文档里没写。 — only that the docs do not mention it.
静态扫描未发现明显风险,但不代表安全。The static scan found no known risk patterns, but that doesn't guarantee the skill is safe. Review the code before using it in production.
这里只做静态扫描:读 README、SKILL.md 和依赖清单,不执行代码。没有命中不代表安全。This is static scanning only: we read the README, SKILL.md and dependency list, and never execute code. No findings does not mean safe.
{
"agents": [
{
"agent": "cursor",
"evidence": "tree: .cursorrules/"
},
{
"agent": "claude-code",
"evidence": "readme: …ign-skill ``` This works for Claude Code, Codex, Cursor, OpenCode, Win…"
},
{
"agent": "windsurf",
"evidence": "readme: …ode, Codex, Cursor, OpenCode, Windsurf, and every other agent the [s…"
},
{
"agent": "opencode",
"evidence": "readme: …r Claude Code, Codex, Cursor, OpenCode, Windsurf, and every other ag…"
}
],
"apiKey": null,
"docker": null,
"taxonomy": {
"scores": {
"design": 8,
"ai-tools": 0,
"dev-tools": 2,
"indie-web": 0,
"skill-agent": 5,
"productivity": 0
},
"primary": "design",
"secondary": "motion"
},
"localRuntime": null,
"skillMdTotal": 1,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 0,
"agent": 0,
"media": 0,
"design": 20,
"browser": 0,
"devtool": 2,
"security": 0,
"marketing": 0,
"productivity": 0
},
"classification": [
{
"signal": "1 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "README describes a Claude / Agent Skill",
"weight": 0.7
},
{
"signal": "name contains 'skill'",
"weight": 0.4
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
"SKILL.md"
],
"skillMdFetched": 1
}