site-audit

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Site Audit

站点审计

Comprehensive audit of a Webflow site's structure, content health, and quality with detailed analysis and multiple export formats.
对Webflow站点的结构、内容健康度和质量进行全面审计,提供详细分析和多种导出格式。

Important Note

重要说明

ALWAYS use Webflow MCP tools for all operations:
  • Use Webflow MCP's
    data_sites_tool
    with action
    list_sites
    for listing available sites
  • Use Webflow MCP's
    data_sites_tool
    with action
    get_site
    for detailed site information
  • Use Webflow MCP's
    data_pages_tool
    with action
    list_pages
    for retrieving all pages
  • Use Webflow MCP's
    data_cms_tool
    with action
    get_collection_list
    for listing CMS collections
  • Use Webflow MCP's
    data_cms_tool
    with action
    get_collection_details
    for detailed collection schemas
  • Use Webflow MCP's
    data_cms_tool
    with action
    list_collection_items
    for counting items
  • Use Webflow MCP's
    webflow_guide_tool
    to get best practices before starting
  • DO NOT use any other tools or methods for Webflow operations
  • All tool calls must include the required
    context
    parameter (15-25 words, third-person perspective)
所有操作务必使用Webflow MCP工具:
  • 使用Webflow MCP的
    data_sites_tool
    ,指定动作
    list_sites
    来列出可用站点
  • 使用Webflow MCP的
    data_sites_tool
    ,指定动作
    get_site
    来获取详细站点信息
  • 使用Webflow MCP的
    data_pages_tool
    ,指定动作
    list_pages
    来获取所有页面
  • 使用Webflow MCP的
    data_cms_tool
    ,指定动作
    get_collection_list
    来列出CMS集合
  • 使用Webflow MCP的
    data_cms_tool
    ,指定动作
    get_collection_details
    来获取详细集合架构
  • 使用Webflow MCP的
    data_cms_tool
    ,指定动作
    list_collection_items
    来统计项目数量
  • 在开始前使用Webflow MCP的
    webflow_guide_tool
    获取最佳实践
  • 请勿使用任何其他工具或方法进行Webflow操作
  • 所有工具调用必须包含必填的
    context
    参数(15-25个单词,第三人称视角)

Instructions

操作步骤

Phase 1: Site Selection & Discovery

第一阶段:站点选择与发现

  1. Get site: Identify the target site. If user does not provide site ID, ask for it.
  2. Fetch site details: Use Webflow MCP's
    data_sites_tool
    with action
    get_site
    to retrieve:
    • Site name and ID
    • Last published date
    • Last updated date
    • Timezone
    • Locales (primary and secondary)
    • Custom domains
  3. Ask user preferences: Ask what level of detail they want:
    • Quick summary (counts only)
    • Standard inventory (pages + collections + counts)
    • Detailed inventory (includes all field schemas, item samples, SEO data)
    • Full export (everything + export to file format)
  1. 获取站点信息:确定目标站点。如果用户未提供站点ID,请向其索要。
  2. 获取站点详情:使用Webflow MCP的
    data_sites_tool
    ,指定动作
    get_site
    来获取以下信息:
    • 站点名称和ID
    • 最后发布日期
    • 最后更新日期
    • 时区
    • 区域设置(主区域和次区域)
    • 自定义域名
  3. 询问用户偏好:询问用户需要的详细程度:
    • 快速摘要(仅统计数据)
    • 标准清单(页面+集合+统计数据)
    • 详细清单(包含所有字段架构、项目样本、SEO数据)
    • 完整导出(全部内容+文件格式导出)

Phase 2: Pages Inventory

第二阶段:页面清单

  1. List all pages: Use Webflow MCP's
    data_pages_tool
    with action
    list_pages
    to fetch all pages
  2. Categorize pages:
    • Static pages (no collectionId)
    • CMS template pages (has collectionId)
    • Archived pages
    • Draft pages
  3. Analyze page structure:
    • Count pages by type
    • Identify pages missing SEO metadata
    • Detect orphaned pages (no navigation links)
    • Check for duplicate slugs
  1. 列出所有页面:使用Webflow MCP的
    data_pages_tool
    ,指定动作
    list_pages
    来获取所有页面
  2. 页面分类
    • 静态页面(无collectionId)
    • CMS模板页面(有collectionId)
    • 已归档页面
    • 草稿页面
  3. 分析页面结构
    • 按类型统计页面数量
    • 识别缺少SEO元数据的页面
    • 检测孤立页面(无导航链接)
    • 检查重复路径别名

Phase 3: CMS Collections Inventory

第三阶段:CMS集合清单

  1. List all collections: Use Webflow MCP's
    data_cms_tool
    with action
    get_collection_list
  2. For each collection:
    • Get detailed schema using Webflow MCP's
      collections_get
    • Count items using Webflow MCP's
      collections_items_list_items
    • Analyze field types and requirements
    • Identify required vs optional fields
    • Detect reference fields and relationships
  3. Collection analysis:
    • Empty collections (0 items)
    • Unused collections (no template page)
    • Large collections (100+ items)
    • Collections with missing required fields
  1. 列出所有集合:使用Webflow MCP的
    data_cms_tool
    ,指定动作
    get_collection_list
  2. 针对每个集合
    • 使用Webflow MCP的
      collections_get
      获取详细架构
    • 使用Webflow MCP的
      collections_items_list_items
      统计项目数量
    • 分析字段类型和必填要求
    • 区分必填字段与可选字段
    • 检测引用字段和关联关系
  3. 集合分析
    • 空集合(0个项目)
    • 未使用的集合(无模板页面)
    • 大型集合(100+个项目)
    • 存在必填字段缺失的集合

Phase 4: Analysis & Insights

第四阶段:分析与洞察

  1. Generate insights:
    • Total content count (pages + items)
    • Content health score
    • SEO readiness
    • Recommended improvements
  2. Identify issues:
    • Missing SEO metadata
    • Empty collections
    • Orphaned pages
    • Draft content ratio
  3. Show relationships:
    • Which pages use which collections
    • Reference field connections
    • Content dependencies
  1. 生成洞察建议
    • 内容总数(页面+项目)
    • 内容健康评分
    • SEO就绪情况
    • 推荐改进措施
  2. 识别问题
    • 缺少SEO元数据
    • 空集合
    • 孤立页面
    • 草稿内容占比
  3. 展示关联关系
    • 哪些页面使用了哪些集合
    • 引用字段的关联
    • 内容依赖关系

Phase 5: Export & Formatting

第五阶段:导出与格式化

  1. Ask export format (if user wants full export):
    • Markdown (readable, great for documentation)
    • JSON (machine-readable, for migrations)
    • CSV (spreadsheet-friendly, for analysis)
    • Text summary (console output only)
  2. Generate report in requested format
  3. Provide actionable insights: Suggest next steps based on findings
  1. 询问导出格式(如果用户需要完整导出):
    • Markdown(易读,适合文档)
    • JSON(机器可读,适合迁移)
    • CSV(适合电子表格,便于分析)
    • 文本摘要(仅控制台输出)
  2. 按请求格式生成报告
  3. 提供可执行洞察:根据发现结果建议后续步骤

Examples

示例

User prompt:
Give me a complete inventory of my site.
Step 1: Initial Report (Standard Inventory)
📊 Site Audit: MCP Demo#1

**Site Details:**
- Site ID: 6924868ede9d3fbbc3195eb0
- Last published: January 9, 2026
- Last updated: January 9, 2026
- Timezone: Asia/Calcutta
- Primary locale: English (en)

---

**Pages (2 total):**

Static Pages (1):
├── Home (/)

CMS Template Pages (1):
└── Blog Posts Template (/post)
    - Collection: Blog Posts

---

**CMS Collections (1):**

Blog Posts (9 items)
├── Slug: post
├── Fields (8):
│   ├── Name (PlainText, required)
│   ├── Slug (PlainText, required)
│   ├── Post Body (RichText)
│   ├── Post Summary (PlainText)
│   ├── Main Image (Image)
│   ├── Thumbnail image (Image)
│   ├── Featured? (Switch)
│   └── Color (Color)

---

**Summary:**
- ✅ 2 pages (1 static, 1 CMS template)
- ✅ 1 CMS collection with 9 published items
- ✅ Site fully published and up-to-date

Would you like a detailed analysis or export in a specific format?
Step 2: Detailed Analysis (when user requests)
🔍 Detailed Analysis: MCP Demo#1

**Content Health Score: 85/100**

✅ Strengths:
- All collections have items (no empty collections)
- All pages are published (no drafts)
- Site recently published (Jan 9, 2026)
- Consistent field structure in Blog Posts

⚠️ Areas for Improvement:
- No SEO metadata on template page (missing meta description)
- Limited page count (consider adding About, Contact pages)
- No reference fields (could link categories/authors to posts)

💡 Recommendations:
1. Add meta descriptions to all pages for better SEO
2. Consider creating a Categories collection for post organization
3. Add an Authors collection for multi-author blog support
4. Create navigation pages (About, Contact, Privacy Policy)

**Collection Breakdown:**

Blog Posts:
- 9 published items (0 drafts, 0 archived)
- 5 featured posts (56%)
- All required fields populated ✓
- Field usage:
  - Name: 100% (9/9)
  - Slug: 100% (9/9)
  - Post Body: 100% (9/9)
  - Post Summary: 100% (9/9)
  - Main Image: 100% (9/9)
  - Thumbnail: 100% (9/9)
  - Featured: 100% (9/9)
  - Color: 100% (9/9)

**Sample Items:**
1. "Why Webflow is the Best Choice for 2026" (featured)
2. "Top Webflow Features to Look Forward to in 2026"
3. "Webflow vs. Competitors: Who Will Win in 2026?" (featured)

---

Export this inventory? (markdown/json/csv/no)
Step 3: Export Options
📥 Export Format Options:

1. **Markdown** - Human-readable documentation
   - Great for README files, wikis, documentation
   - Preserves structure and formatting

2. **JSON** - Machine-readable structured data
   - Perfect for migrations, integrations
   - Includes all raw API data

3. **CSV** - Spreadsheet-friendly
   - Easy to analyze in Excel/Google Sheets
   - Separate files for pages and collections

Which format would you like? (1/2/3)
用户提示:
给我一份我的站点的完整清单。
步骤1:初始报告(标准清单)
📊 站点审计:MCP Demo#1

**站点详情:**
- 站点ID:6924868ede9d3fbbc3195eb0
- 最后发布日期:2026年1月9日
- 最后更新日期:2026年1月9日
- 时区:Asia/Calcutta
- 主区域设置:English (en)

---

**页面(共2个):**

静态页面(1个):
├── 首页 (/)

CMS模板页面(1个):
└── 博客文章模板 (/post)
    - 集合:博客文章

---

**CMS集合(共1个):**

博客文章(9个项目)
├── 路径别名:post
├── 字段(8个):
│   ├── 名称(PlainText,必填)
│   ├── 路径别名(PlainText,必填)
│   ├── 文章正文(RichText)
│   ├── 文章摘要(PlainText)
│   ├── 主图片(Image)
│   ├── 缩略图(Image)
│   ├── 精选?(Switch)
│   └── 颜色(Color)

---

**摘要:**
- ✅ 2个页面(1个静态页面,1个CMS模板页面)
- ✅ 1个CMS集合,包含9个已发布项目
- ✅ 站点已完全发布且内容最新

是否需要详细分析或导出为特定格式?
步骤2:详细分析(用户请求时)
🔍 详细分析:MCP Demo#1

**内容健康评分:85/100**

✅ 优势:
- 所有集合均包含项目(无空集合)
- 所有页面均已发布(无草稿)
- 站点最近发布(2026年1月9日)
- 博客文章集合的字段结构一致

⚠️ 待改进领域:
- 模板页面缺少SEO元数据(缺少元描述)
- 页面数量有限(建议添加关于我们、联系我们页面)
- 无引用字段(可将分类/作者与文章关联)

💡 建议:
1. 为所有页面添加元描述以提升SEO表现
2. 考虑创建分类集合来组织文章
3. 添加作者集合以支持多作者博客
4. 创建导航页面(关于我们、联系我们、隐私政策)

**集合细分:**

博客文章:
- 9个已发布项目(0个草稿,0个已归档)
- 5篇精选文章(占56%)
- 所有必填字段均已填写 ✓
- 字段使用率:
  - 名称:100% (9/9)
  - 路径别名:100% (9/9)
  - 文章正文:100% (9/9)
  - 文章摘要:100% (9/9)
  - 主图片:100% (9/9)
  - 缩略图:100% (9/9)
  - 精选:100% (9/9)
  - 颜色:100% (9/9)

**项目样本:**
1. "Why Webflow is the Best Choice for 2026"(精选)
2. "Top Webflow Features to Look Forward to in 2026"
3. "Webflow vs. Competitors: Who Will Win in 2026?"(精选)

---

是否导出此清单?(markdown/json/csv/否)
步骤3:导出选项
📥 导出格式选项:

1. **Markdown** - 人类可读的文档格式
   - 适合README文件、维基、文档
   - 保留结构和格式

2. **JSON** - 机器可读的结构化数据
   - 非常适合迁移、集成场景
   - 包含所有原始API数据

3. **CSV** - 适合电子表格
   - 便于在Excel/Google Sheets中分析
   - 为页面和集合分别生成文件

您需要哪种格式?(1/2/3)

Guidelines

指南

Phase 1: Critical Requirements

第一阶段:关键要求

Site Information:
  • Always fetch complete site details using
    sites_get
  • Include last published and last updated dates
  • Show timezone and locale information
  • Display custom domains if configured
User Options: Offer multiple detail levels:
  • Quick: Just counts
  • Standard: Pages + collections + basic info
  • Detailed: Full schema + analysis + insights
  • Export: Everything + file output
站点信息:
  • 务必使用
    sites_get
    获取完整站点详情
  • 包含最后发布和最后更新日期
  • 显示时区和区域设置信息
  • 若配置了自定义域名则展示
用户选项: 提供多种详细程度选项:
  • 快速版:仅统计数据
  • 标准版:页面+集合+基础信息
  • 详细版:完整架构+分析+洞察
  • 导出版:全部内容+文件输出

Phase 2: Pages Analysis

第二阶段:页面分析

Page Categorization:
  • Separate static pages from CMS template pages
  • Flag archived and draft pages separately
  • Show page slugs/URLs for reference
  • Identify pages with missing SEO metadata
Page Health Checks:
  • Missing meta descriptions
  • Missing OG tags
  • Duplicate slugs (error condition)
  • Orphaned pages (not linked in nav)
页面分类:
  • 区分静态页面和CMS模板页面
  • 单独标记已归档和草稿页面
  • 展示页面路径别名/URL供参考
  • 识别缺少SEO元数据的页面
页面健康检查:
  • 缺少元描述
  • 缺少OG标签
  • 重复路径别名(错误情况)
  • 孤立页面(未在导航中链接)

Phase 3: Collections Analysis

第三阶段:集合分析

Collection Details: For each collection, show:
  • Display name and singular name
  • Slug (URL structure)
  • Total field count
  • Required vs optional fields breakdown
  • Item count (published/draft/archived)
  • Last updated date
Field Analysis: Categorize by type:
  • Text fields (PlainText, RichText)
  • Media fields (Image, Video, File)
  • Relationship fields (Reference, MultiReference)
  • Data fields (DateTime, Number, Color)
  • Boolean fields (Switch)
  • Selection fields (Option)
Field Validation:
  • Show max length constraints
  • Show validation patterns
  • Flag required fields
  • Identify reference field targets
集合详情: 针对每个集合,展示:
  • 显示名称和单数名称
  • 路径别名(URL结构)
  • 总字段数
  • 必填字段与可选字段的细分
  • 项目数量(已发布/草稿/已归档)
  • 最后更新日期
字段分析: 按类型分类:
  • 文本字段(PlainText、RichText)
  • 媒体字段(Image、Video、File)
  • 关联字段(Reference、MultiReference)
  • 数据字段(DateTime、Number、Color)
  • 布尔字段(Switch)
  • 选择字段(Option)
字段验证:
  • 展示最大长度限制
  • 展示验证规则
  • 标记必填字段
  • 识别引用字段的目标

Phase 4: Analysis & Insights

第四阶段:分析与洞察

Content Health Score (0-100): Calculate based on:
  • SEO metadata completeness (25 points)
  • Content-to-page ratio (20 points)
  • Field utilization (20 points)
  • Recent updates (15 points)
  • Structure quality (20 points)
Issue Detection:
  • 🔴 Critical: Missing required fields, duplicate slugs
  • ⚠️ Warning: Empty collections, missing SEO, drafts
  • 💡 Suggestion: Add pages, create relationships, organize
Recommendations: Suggest improvements based on:
  • Missing page types (About, Contact, etc.)
  • Underutilized collections
  • Missing relationships between collections
  • SEO optimization opportunities
内容健康评分(0-100): 基于以下维度计算:
  • SEO元数据完整性(25分)
  • 内容与页面占比(20分)
  • 字段使用率(20分)
  • 最近更新情况(15分)
  • 结构质量(20分)
问题检测:
  • 🔴 严重问题:缺少必填字段、重复路径别名
  • ⚠️ 警告:空集合、缺少SEO元数据、草稿内容
  • 💡 建议:添加页面、创建关联关系、优化组织
建议: 基于以下情况提出改进措施:
  • 缺失的页面类型(关于我们、联系我们等)
  • 未充分利用的集合
  • 集合间缺失的关联关系
  • SEO优化机会

Phase 5: Export Formats

第五阶段:导出格式

Markdown Export:
markdown
undefined
Markdown导出示例:
markdown
undefined

Site Audit: [Site Name]

站点审计: [Site Name]

Site Information

站点信息

  • ID: [site-id]
  • Last Published: [date]
  • ID: [site-id]
  • 最后发布日期: [date]

Pages

页面

Static Pages

静态页面

  • Home (/)
  • About (/about)
  • 首页 (/)
  • 关于我们 (/about)

CMS Templates

CMS模板

  • Blog Post (/post/[slug])
  • 博客文章 (/post/[slug])

Collections

集合

Blog Posts (47 items)

博客文章 (47个项目)

Fields:
  • Title (PlainText, required)
  • Slug (PlainText, required)
  • Content (RichText) ...

**JSON Export:**
```json
{
  "site": {
    "id": "...",
    "name": "...",
    "lastPublished": "..."
  },
  "pages": [...],
  "collections": [...]
}
CSV Export: Generate separate files:
  • pages.csv
    : All pages with metadata
  • collections.csv
    : Collection metadata
  • fields.csv
    : All fields across collections
  • items.csv
    : Item counts per collection
字段:
  • 标题 (PlainText, 必填)
  • 路径别名 (PlainText, 必填)
  • 内容 (RichText) ...

**JSON导出示例:**
```json
{
  "site": {
    "id": "...",
    "name": "...",
    "lastPublished": "..."
  },
  "pages": [...],
  "collections": [...]
}
CSV导出: 生成单独的文件:
  • pages.csv
    : 包含所有页面及元数据
  • collections.csv
    : 集合元数据
  • fields.csv
    : 所有集合的字段信息
  • items.csv
    : 各集合的项目统计

Performance Optimization

性能优化

Batch Processing:
  • For sites with 20+ collections, show progress
  • For collections with 100+ items, paginate counts
  • Provide estimated time for large sites
Error Handling:
  • If
    pages_list
    fails, continue with collections
  • If
    collections_get
    fails, show basic collection info
  • Report partial successes separately
  • Offer to retry failed operations
Data Efficiency:
  • Use pagination for large result sets
  • Only fetch detailed schemas when needed
  • Limit item samples to 3-5 per collection
  • Cache site info for repeat operations
批量处理:
  • 对于包含20+个集合的站点,展示处理进度
  • 对于包含100+个项目的集合,分页统计数量
  • 为大型站点提供预计处理时间
错误处理:
  • pages_list
    调用失败,继续处理集合
  • collections_get
    调用失败,展示基础集合信息
  • 单独报告部分成功的情况
  • 提供重试失败操作的选项
数据效率:
  • 对大型结果集使用分页
  • 仅在需要时获取详细架构
  • 每个集合的项目样本限制为3-5个
  • 缓存站点信息以支持重复操作

Best Practices

最佳实践

Read-Only Operation:
  • No confirmation needed (read-only)
  • Safe to run multiple times
  • No side effects or modifications
Clear Organization:
  • Group by content type (pages/collections)
  • Use visual hierarchy (├── └──)
  • Show counts prominently
  • Highlight issues with icons (✅ ⚠️ 🔴 💡)
Actionable Output:
  • Always end with recommendations
  • Offer export options for detailed inventories
  • Suggest next steps based on findings
  • Provide comparison against best practices
Version Tracking: If user runs inventory multiple times:
  • Compare with previous run
  • Show changes (new pages, deleted collections)
  • Track content growth over time
  • Alert on significant changes
只读操作:
  • 无需确认(只读操作)
  • 可安全多次运行
  • 无副作用或修改操作
清晰的组织:
  • 按内容类型分组(页面/集合)
  • 使用视觉层级(├── └──)
  • 突出显示统计数据
  • 使用图标标记问题(✅ ⚠️ 🔴 💡)
可执行的输出:
  • 始终以建议结尾
  • 为详细清单提供导出选项
  • 根据发现结果建议后续步骤
  • 与最佳实践进行对比
版本跟踪: 若用户多次运行清单:
  • 与上一次运行结果对比
  • 展示变更(新增页面、已删除集合)
  • 跟踪内容随时间的增长情况
  • 对重大变更发出警报
",