DESIGN/设计资源·UI-KIT
superdesigndev/superdesign-skill
别再交出 AI 味界面：一条命令，让你的前端变成能上线的设计。That default AI UI?
给编程助手用的设计技能，帮它们做出能交付的前端界面。A design skill for coding agents that turns AI-generated UI into shippable, tasteful frontends.
怎么装：Install: npx skills add superdesigndev/superdesign-skill
02 / 现在的位置02 / Why now
首次发现FIRST SEEN
03 OCT 202603 OCT 2026
增长GROWTH
+3.1%+3.1%
620 → 639 stars · 7 个快照620 → 639 stars · 7 snapshots
讨论DISCUSSION
1 SOURCES1 SOURCES
2 条外部提及2 external mentions
状态STATUS
持续活跃Active
质量 AQuality A
项目获得639个star，社区关注度较高。Installs as a skill for 70+ coding agents.
HN_STORY · 2 points · 0 comments
HN_STORY · 24 points · 8 comments
03 / 它能帮你做什么03 / What it helps you do
重新设计UI页面，告别AI生成的粗糙外观
从现有代码中提取并建立设计系统
改进仪表盘等页面的视觉设计
创建多页演示文稿或用户流程
搜索设计灵感并获取参考HTML
Redesign a settings page to look polished.
Set up a design system from your codebase.
Improve your dashboard's layout and style.
Create an 8-slide presentation about a product.
Explore multiple design variations in one go.
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.
npx skills add superdesigndev/superdesign-skillRun `npx skills add superdesigndev/superdesign-skill` to add the skill, then install the CLI with `npm install -g @superdesign/cli@latest` and log in with `superdesign login`.
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
需检查Needs review
静态扫描STATIC SCAN
01执行 Shell 命令Runs shell commandsskills/superdesign/SKILL.md
Superdesign runs entirely through its CLI, so you must be able to execute shell commands. Confirm that capability first, before any CLI veri
该项目通过 CLI 执行 Shell 命令，属于中等风险。使用前请确认你的环境允许运行 Shell 命令，并理解其潜在影响。Static scan found a medium risk: the skill executes shell commands through its CLI. Make sure your environment allows that before using it.
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": "claude-code",
"evidence": "tree: .claude/"
},
{
"agent": "vscode",
"evidence": "readme: …`superdesigndev/superdesign` VS Code extension is an older, separa…"
}
],
"apiKey": null,
"docker": null,
"taxonomy": {
"scores": {
"design": 4,
"ai-tools": 1,
"dev-tools": 1,
"indie-web": 1,
"skill-agent": 9,
"productivity": 0
},
"primary": "design",
"secondary": "ui-kit"
},
"localRuntime": null,
"skillMdTotal": 1,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 0,
"agent": 0,
"media": 1,
"design": 21,
"browser": 0,
"devtool": 3,
"security": 0,
"marketing": 1,
"productivity": 0
},
"classification": [
{
"signal": "1 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "skills/ directory with 12 markdown files",
"weight": 0.75
},
{
"signal": "Claude Code plugin manifest",
"weight": 0.7
},
{
"signal": "name contains 'skill'",
"weight": 0.4
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
"skills/superdesign/SKILL.md"
],
"skillMdFetched": 1
}