设计语言直接来自已发布的产品，每个颜色、弹簧常数都是产品中实际使用的。
Every hex code, spring constant, and radius is extracted from a shipped product, not a prototype.
独立开发者
Frontend developers using React and Tailwind
目标用户 · 非用户评价Target user · not a testimonial
DESIGN/设计资源·UI-KIT
OpenLabs-so/oa-design
134 星、0 次提交，一个从已发布产品里提取的设计语言，agent 直接能用。134 stars, zero commits — a design language extracted from a shipped product, executable by any agent.
Open Analytics 的设计语言，打包成 AI agent 能用的组件配方和命令行工具。A design language from a shipped analytics product, delivered as component recipes and token CSS.
怎么装：Install: npx getopen-design list # what's available
02 / 现在的位置02 / Why now
首次发现FIRST SEEN
03 OCT 202603 OCT 2026
增长GROWTH
历史不足Not enough history
只有 1 个快照，还不足以计算增长Only 1 snapshots so far — not enough to compute growth
讨论DISCUSSION
暂无None
还没有采集到外部讨论No external discussion collected yet
状态STATUS
持续活跃Active
质量 A-Quality A-
设计语言直接来自已发布的产品，每个颜色、弹簧常数都是产品中实际使用的。Every hex code, spring constant, and radius is extracted from a shipped product, not a prototype.
03 / 它能帮你做什么03 / What it helps you do
获取设计令牌样式
添加组件配方到项目
安装设计系统文件
克隆仓库获取源码
查看可用组件列表
Copy production-grade UI components into your project.
Apply token CSS without touching React.
Use the same motion springs as the analytics dashboard.
Get a flat design reference file for any AI coding tool.
Import type-checked source that passes `npm run typecheck`.
04 / 谁在用04 / WHO IT’S FOR
设计语言直接来自已发布的产品，每个颜色、弹簧常数都是产品中实际使用的。
Every hex code, spring constant, and radius is extracted from a shipped product, not a prototype.
独立开发者
Frontend developers using React and Tailwind
目标用户 · 非用户评价Target user · not a testimonial
有CLI、agent skill、单文件三种使用方式，适配不同工作流。
The design is available as installable component recipes, a standalone token CSS, or a single-file guide for any AI assistant.
前端开发者
Teams building analytics dashboards or admin panels
目标用户 · 非用户评价Target user · not a testimonial
包含类型检查的组件源码和token CSS，可直接集成到项目中。
Licensed MIT — you can use it in commercial projects without restrictions.
设计师
Anyone who wants a consistent, motion-rich UI fast
目标用户 · 非用户评价Target user · not a testimonial
设计语言直接来自已发布的产品，每个颜色、弹簧常数都是产品中实际使用的。
Every hex code, spring constant, and radius is extracted from a shipped product, not a prototype.
技术创业者
Developers using AI coding tools like Claude Code or Cursor
目标用户 · 非用户评价Target user · not a testimonial
不适合谁Not for同样来自文档，不是我们的判断Also from the docs, not our judgement
05 / 安装05 / 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.
使用 `npx getopen-design add` 命令将组件配方添加到项目中。Run `npx getopen-design add` to copy component recipes, or `git clone` the repo and place the skill folder into your project.
06 / 限制与风险06 / 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。Static scanning of the documentation found no common risk patterns. However, scanning is not exhaustive, and this does not prove the project is safe.
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": "readme: …ll into .claude/skills ``` **Claude Code**, without the CLI: ```sh gi…"
}
],
"apiKey": null,
"docker": null,
"taxonomy": {
"scores": {
"design": 13,
"ai-tools": 0,
"dev-tools": 4,
"indie-web": 0,
"skill-agent": 10,
"productivity": 0
},
"primary": "design",
"secondary": "ui-kit"
},
"localRuntime": null,
"skillMdTotal": 1,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 6,
"agent": 0,
"media": 0,
"design": 16,
"browser": 0,
"devtool": 4,
"security": 0,
"marketing": 0,
"productivity": 0
},
"classification": [
{
"signal": "1 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "skills/ directory with 19 markdown files",
"weight": 0.75
},
{
"signal": "README describes a Claude / Agent Skill",
"weight": 0.7
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
"skills/oa-design/SKILL.md"
],
"skillMdFetched": 1
}