SKILLS & AGENTS/Skill 与 Agent·CLAUDE-SKILL
sukirman1901/frontend-expert
中文简介生成中Frontend Expert — chat-first agent skills for shipping product web UI (tokens, anti-slop, shell chrome, responsive, motion).
怎么装:Install: npx skills add sukirman1901/frontend-expert
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
03 / 它能帮你做什么03 / What it helps you do
中文能力说明生成中Chinese capability copy is being generated
中文能力说明生成中Chinese capability copy is being generated
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.
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
需检查Needs review
静态扫描STATIC SCAN
01控制浏览器Controls a browserskills/engineering-vocabulary/SKILL.md
| Test user flows end-to-end | **E2E test (Playwright/Cypress)** | Simulate real user interaction in browser |
02控制浏览器Controls a browserskills/testing/SKILL.md
- E2E (~5%): critical paths only (Playwright/Cypress)
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": "cursor",
"evidence": "tree: .cursor/"
},
{
"agent": "gemini-cli",
"evidence": "tree: .gemini/"
},
{
"agent": "opencode",
"evidence": "readme: …or /path/to/your-app ``` ### OpenCode / Codex / Gemini ```bash git…"
}
],
"apiKey": null,
"docker": null,
"taxonomy": {
"scores": {
"design": 2,
"ai-tools": 0,
"dev-tools": 2,
"indie-web": 1,
"skill-agent": 3,
"productivity": 0
},
"primary": "skill-agent",
"secondary": "claude-skill"
},
"localRuntime": null,
"skillMdTotal": 34,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 0,
"agent": 0,
"media": 0,
"design": 10,
"browser": 0,
"devtool": 2,
"security": 0,
"marketing": 1,
"productivity": 0
},
"classification": [
{
"signal": "34 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "skills/ directory with 33 markdown files",
"weight": 0.75
},
{
"signal": "README describes a Claude / Agent Skill",
"weight": 0.7
},
{
"signal": "Claude Code plugin manifest",
"weight": 0.7
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
"SKILL.md",
"skills/accessibility/SKILL.md",
"skills/anti-slop-code/SKILL.md",
"skills/anti-slop-design/SKILL.md",
"skills/app-shell/SKILL.md",
"skills/architecture/SKILL.md",
"skills/components/SKILL.md",
"skills/content-design/SKILL.md",
"skills/data-fetching/SKILL.md",
"skills/design-color/SKILL.md",
"skills/design-direction/SKILL.md",
"skills/design-foundations/SKILL.md",
"skills/design-surfaces/SKILL.md",
"skills/design-typography/SKILL.md",
"skills/design-vocabulary/SKILL.md",
"skills/devtools/SKILL.md",
"skills/engineering-vocabulary/SKILL.md",
"skills/fidelity/SKILL.md",
"skills/forms/SKILL.md",
"skills/frontend-expert/SKILL.md",
"skills/marketing/SKILL.md",
"skills/monitoring/SKILL.md",
"skills/motion-inspection/SKILL.md",
"skills/motion/SKILL.md",
"skills/performance/SKILL.md",
"skills/polish/SKILL.md",
"skills/prototype/SKILL.md",
"skills/quality-loop/SKILL.md",
"skills/responsive/SKILL.md",
"skills/seo/SKILL.md",
"skills/skill-authoring/SKILL.md",
"skills/testing/SKILL.md",
"skills/tokens/SKILL.md",
"skills/webgl/SKILL.md"
],
"skillMdFetched": 34
}