2026年7月10日创建，8月16日还有提交，项目刚起步。
Derived from the README and GitHub data
前端开发者
Derived from the README and GitHub data
目标用户 · 非用户评价Target user · not a testimonial
SKILLS & AGENTS/Skill 与 Agent·BROWSER
yg2224/app-shell-ui
用 app-shell-ui，一句话描述让 AI 生成完整前端界面，无需手写代码。English copy pending
给 Codex、Claude Code、Grok 的一套界面配方，照着搭就是桌面工具界面或官网。App Shell UI: reusable desktop-utility frontend skill for Codex / Claude Code / Grok
怎么装：Install: git clone https://github.com/yg2224/app-shell-ui.git ~/.codex/skills/app-shell-ui
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 AQuality A
2026年7月10日创建，8月16日还有提交，项目刚起步。English copy pending
03 / 它能帮你做什么03 / What it helps you do
做陶瓷工作室管理台，一屏完成今日排产
做作品优先的官网，首屏放真实器物图
重做现有页面，保留原逻辑只修体验问题
从50个现成React界面零件里选来拼装
在本地浏览器打开示例，直接看效果
中文能力说明生成中Chinese capability copy is being generated
04 / 谁在用04 / WHO IT’S FOR
2026年7月10日创建，8月16日还有提交，项目刚起步。
Derived from the README and GitHub data
前端开发者
Derived from the README and GitHub data
目标用户 · 非用户评价Target user · not a testimonial
56个star和4个fork，小圈子里已经有人开始用。
Derived from the README and GitHub data
独立开发者
Derived from the README and GitHub data
目标用户 · 非用户评价Target user · not a testimonial
自带50个React组件参考，agent生成界面时不用从零开始。
Derived from the README and GitHub data
技术创业者
Derived from the README and GitHub data
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.
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 git clone https://github.com/yg2224/app-shell-ui.git ~/.codex/skills/app-shell-ui 装到Codex的技能目录（Claude Code和Grok也有对应路径）。English copy pending
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。文档中未命中已知风险模式，也没有需要特别指出的高风险项。
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: …<a href=\"#安装\"><img alt=\"Codex Claude Code Grok\" src=\"https://img.shield…"
}
],
"apiKey": null,
"docker": null,
"taxonomy": {
"scores": {
"design": 1,
"ai-tools": 0,
"dev-tools": 0,
"indie-web": 1,
"skill-agent": 0,
"productivity": 0
},
"primary": "skill-agent",
"secondary": "browser"
},
"localRuntime": "install: git-clone",
"skillMdTotal": 1,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 1,
"agent": 0,
"media": 1,
"design": 9,
"browser": 1,
"devtool": 0,
"security": 0,
"marketing": 1,
"productivity": 0
},
"classification": [
{
"signal": "1 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "README describes a Claude / Agent Skill",
"weight": 0.7
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
"SKILL.md"
],
"skillMdFetched": 1
}