Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add nongjun/feishu-cursor-claw --skill page-health-checkgit clone --depth 1 https://github.com/nongjun/feishu-cursor-clawWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nongjun/feishu-cursor-claw/page-health-check)<a href="https://agentmods.dev/skills/nongjun/feishu-cursor-claw/page-health-check"><img src="https://agentmods.dev/badge/skills/nongjun/feishu-cursor-claw/page-health-check/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nongjun/feishu-cursor-claw/page-health-check"><img src="https://agentmods.dev/badge/skills/nongjun/feishu-cursor-claw/page-health-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00064 | $0.02108 |
| Opus 5 | $0.00032 | $0.01054 |
| Sonnet 5 | $0.00013 | $0.00422 |
| Haiku 4.5 | $0.00006 | $0.00211 |
Grade A, and why
page-health-check scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**API 响应** — 从网络请求分析耗时:< 300ms 正常,300ms-1s 记录,1-3s 需优化(应有 loading),> 3s 必须优化。慢接口用 curl 测 TTFB,TTFB > 600ms 需排查后端。 How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
页面健康检查 SOP
给一个 URL,用 Cursor 内置浏览器完成完整体检。能修的当场修,不能修的列清单。
流程
打开页面 → 截屏 → 交互探索 → 逐项审查(数据/视觉/控制台/性能) → 修复 → 再验证
最多 3 轮修复循环。每轮修复后重新截图验证。
Step 1: 截屏
打开目标 URL,等待渲染完成(至少 2s),先 snapshot 获取 DOM 结构,再 fullPage 截图。内部滚动容器截不全时分段滚动截图。
Step 2: 交互探索
点击页面内的交互元素,暴露子视图和弹窗,确保所有可达视图都被检查到。
安全分类:
| 级别 | 举例 | 操作 |
|---|---|---|
| 安全 | Tab 切换、折叠展开、筛选、排序、分页、查看详情、搜索 | 放心点 |
| 只读弹窗 | 新增按钮、编辑按钮 | 打开看布局就关闭,不提交 |
| 危险 | 删除、禁用开关、审批、确认提交 | 不点 |
去重:同类重复元素只点一个代表(如表格每行的编辑按钮只点第一行)。
顺序:Tab/分段器 → 筛选/搜索 → 查看/编辑弹窗 → 新增弹窗 → 展开折叠。每步截图,对新视图同样执行后续审查。
不做的事:不切换导航、不提交表单、不点删除、不做破坏性测试。
Step 3: 逐项审查
对主页面及交互探索中暴露的每个视图,逐一检查以下维度。不打分,只找问题。
3.1 数据正确性(P0 优先级)
乱码 — 观察截图和 DOM 文本中是否有 �、锟斤拷、â€"、???、□□□、emoji 异常等。可通过 browser_snapshot 获取 DOM 文本后检测。常见原因:charset 未声明、数据库连接字符集不匹配、utf8 应升级 utf8mb4。
模拟数据 — 疑似特征:规律姓名(张三李四)、整齐数字(100/200)、不合理时间、Lorem ipsum、占位图、虚假联系方式(13800138000)、数据量太规律。同时检查网络请求是否指向 mock 服务。
异常空数据 — 空表格、全零统计、空下拉选项、全空详情页。空数据大概率是 bug,排查路径:前端是否发请求 → API 是否正常返回 → 查询参数是否正确 → 数据库是否有数据。即使确认真无数据,也要确保空状态 UI 友好。
3.2 视觉与交互
整体视觉 — 关注:色彩是否统一、排版层次是否清晰、间距是否一致、对齐是否规整、信息密度是否适中、视觉焦点是否明确。
交互反馈 — 关注:hover 是否有反馈、状态切换是否有过渡动效、数据加载是否有 loading/skeleton、空状态 UI 是否友好、长文本是否正确 ellipsis/换行。
组件一致性 — 关注:按钮主次是否分明、表格表头是否固定且列宽合理、表单标签是否对齐、卡片圆角阴影是否统一、弹窗尺寸是否适中、图标风格是否统一。
3.3 控制台
获取控制台消息。error 判断是否为业务错误(排除 Permissions-Policy 等环境噪音),忽略 [CursorBrowser] 前缀消息。
3.4 性能与响应速度
API 响应 — 从网络请求分析耗时:< 300ms 正常,300ms-1s 记录,1-3s 需优化(应有 loading),> 3s 必须优化。慢接口用 curl 测 TTFB,TTFB > 600ms 需排查后端。
前端加载 — 通过 Performance API 获取 FCP(< 1s 优秀 / > 2.5s 需优化)、Page Load(< 3s 优秀 / > 6s 需优化)。
体感 — 首屏 1s 内应可见主要内容、切换筛选 < 500ms、翻页应有 loading、弹窗应立即弹出。
Step 4: 修复
优先级
- P0 — 白屏、JS 报错不可用、乱码、模拟数据残留、异常空数据
- P0.5 — 接口 > 3s、页面加载 > 6s、操作无响应
- P1 — 布局错乱、文字溢出、元素重叠
- P1.5 — 接口 1-3s、缺 loading 状态
- P2 — 缺 hover 反馈、间距不一致、色彩不统一
- P3 — 过渡动效、微交互美化
默认行为:直接修
发现问题就修,不要只列清单。agent 做检查的价值就是修完交付,不是当 QA 提工单。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 161 lines · 64 tokens per session scan A fd141816df22
page-health-check is a skill published in the GitHub repository nongjun/feishu-cursor-claw (14 stars, last pushed 2mo ago), licensed MIT. It adds 64 tokens to every session and 2,108 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
architecture-feature-first
Use when creating a feature, designing folder structure, adding repositories/services/view models, wiring dependency injection, or deciding which layer owns logic.
flutter-use-column-row-first
Use when building any Flutter screen or component to choose responsive Row, Column, Expanded, Flexible, and Spacer layouts before fixed-size or coordinate-based alternatives.
component-creation
Step-by-step workflow for creating accessible, tested UI components. Use when the user asks to create a new UI component.
enhance-web-landing
Build landing pages, portfolios, and marketing sites that don't look AI-generated. Use when asked for "landing page", "portfolio", "marketing site", "anti-slop", "Awwwards-style", "premium frontend", or when design needs a strong point of view.
enhance-capacitor-ui
Cross-surface UIUX separation skill for hybrid web apps that ship as PWA + iOS + Android via Capacitor (or Tauri / Expo Web / Ionic / RN-Web). Use when a previous UI/UX sweep "improved one surface and broke the other" — desktop polished but mobile cramped, or mobile native but desktop wastes space.
enhance-web-ui
Polish an existing page's hierarchy, spacing, type, and visual personality. Use when "make this page polished/premium", "less crowded", or "better visual hierarchy". Understood / CPL → enhance-readability. Flow/IA → enhance-web-ux. Breakpoints → audit-responsive.