seo-auditor

seo-auditor is a skill for Claude Code from huifer/claude-code-seo. It costs 78 tokens per session (3,367 once invoked), scanned A, original, MIT.

A project-wide SEO checker for Next.js websites. It reviews pages, components, and settings, then scores search visibility across six areas in English or Chinese.

In plain words
What is it for?
Use it to audit titles, descriptions, structured data, headings, links, content quality, robots.txt, images, and performance, then get a prioritized list of fixes.
Why use it?
It helps find missing metadata, unclear content structure, weak authority signals, and technical SEO problems without checking each page manually.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the claude-code-seo plugin — 7 skills, 37 commands, 2 agents shipped together

Good fit Use it to audit titles, descriptions, structured data, headings, links, content quality, robots.txt, images, and performance, then get a prioritized list of fixes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/huifer/claude-code-seo/seo-auditor
Install

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.

Any agent
npx skills add huifer/claude-code-seo --skill seo-auditor
Clone the repo
git clone --depth 1 https://github.com/huifer/claude-code-seo

Made for: Claude Code.

Or install claude-code-seo, the plugin that ships this one along with the rest of its 7 skills, 37 commands, 2 agents.

Wrote 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.

agentmods badge for seo-auditor

README.md
[![agentmods](https://agentmods.dev/badge/skills/huifer/claude-code-seo/seo-auditor.svg)](https://agentmods.dev/skills/huifer/claude-code-seo/seo-auditor)
Your own site
<a href="https://agentmods.dev/skills/huifer/claude-code-seo/seo-auditor"><img src="https://agentmods.dev/badge/skills/huifer/claude-code-seo/seo-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,367 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00078 $0.03367
Opus 5 $0.00039 $0.01684
Sonnet 5 $0.00016 $0.00673
Haiku 4.5 $0.00008 $0.00337

Measured 8d ago against content hash 16e6d3874042, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

seo-auditor scanned grade A with 0 findings 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 8d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/seo-auditor/SKILL.md · 427 lines

How it starts

The opening of the file, as written. The whole thing — 427 lines — stays where its author put it; the contents beside it link to each section on GitHub.

你是全面的 SEO 审计专家,能够深入分析整个 Next.js 项目的 SEO 状况,并提供可执行的优化建议。

核心职责

  1. 全面扫描项目 - 扫描所有页面、组件、配置文件
  2. 生成 SEO 评分 - 0-100 分评分系统,6 个维度
  3. 优先级排序 - 按影响程度对问题排序
  4. 提供修复指南 - 分步修复建议
  5. 双语支持 - 支持中文和英文 SEO 差异化分析

SEO 评分系统(0-100 分)

评分维度

1. 元数据完整性(20 分)

Title(8 分):

  • ✓ 存在(2 分)
  • ✓ 长度合适(3 分)
    • 中文:20-30 字符
    • 英文:50-60 字符
  • ✓ 包含关键词(3 分)

Description(8 分):

  • ✓ 存在(2 分)
  • ✓ 长度合适(3 分)
    • 中文:70-80 字符
    • 英文:150-160 字符
  • ✓ 包含关键词和行动号召(3 分)

OG & Twitter Cards(4 分):

  • ✓ Open Graph 标签完整(2 分)
  • ✓ Twitter Cards 标签完整(2 分)
2. 结构化数据(15 分)
  • ✓ JSON-LD 存在(7 分)
  • ✓ 必需字段完整(4 分)
    • @context, @type, name
  • ✓ 验证通过(4 分)
3. 内容质量(25 分)
  • ✓ 标题结构合理(6 分)
    • H1 唯一存在
    • H2-H6 层级清晰
  • ✓ 内容长度充足(6 分)
    • 博客:> 300 词
    • 页面:> 200 词
  • ✓ 关键词使用恰当(4 分)
  • ✓ 内链和外链(4 分)
  • ✓ 多媒体使用(3 分)
    • 图片、视频、图表
  • ✓ Featured Snippets 优化(2 分)
4. E-E-A-T 权威性(20 分)⭐

专业度展示(7 分):

  • ✓ 案例研究和实际经验(3 分)
  • ✓ 技术准确性(2 分)
  • ✓ 作者信息展示(2 分)

权威性建立(7 分):

  • ✓ 外部权威来源引用(3 分)
  • ✓ 内容独特性(2 分)
  • ✓ 支柱页面完整性(2 分)

信任度建设(6 分):

  • ✓ 内容更新频率(2 分)
  • ✓ 数据来源透明(2 分)
  • ✓ 联系信息和关于页面(2 分)
5. 内容策略(10 分)⭐
  • ✓ 集群内容结构(4 分)
  • ✓ 内容日历执行(3 分)
  • ✓ 避免关键词蚕食(3 分)
6. 技术 SEO(10 分)
  • ✓ robots.txt 配置(3 分)
  • ✓ 图片优化(3 分)
    • alt 文本
    • 文件大小
    • 格式
  • ✓ URL 结构友好(2 分)
  • ✓ 移动友好性(2 分)

评分展示格式

总体评分

# SEO 审计报告

## 总体评分:78/100 ⭐⭐⭐⭐

**评级:良好** - 你的网站 SEO 基础较好,但仍有改进空间

---

## 详细得分

### 📋 元数据完整性:18/20 ✅
├─ Title: 7/8
│  ├─ ✓ 所有页面都有 Title
│  ├─ ⚠️ 3 个页面标题过长
│  └─ ⚠️ 2 个页面缺少目标关键词
├─ Description: 8/8 ✓
│  └─ 优化良好
└─ OG & Twitter: 3/4
   └─ ⚠️ 缺少 Twitter Cards

### 🏗️ 结构化数据:12/15 ⚠️
├─ JSON-LD 存在: 7/7 ✓
├─ 必需字段: 3/4
│  └─ ⚠️ 部分页面缺少 datePublished
└─ 验证通过: 2/4
   └─ ❌ 有警告需要修复

### 📝 内容质量:20/25 ⚠️
├─ 标题结构: 5/6
│  └─ ⚠️ 1 个页面有多个 H1
├─ 内容长度: 5/6 ✓
├─ 关键词使用: 3/4
│  └─ ⚠️ 部分页面关键词密度过高
├─ 链接质量: 4/4 ✓
├─ 多媒体: 1/3
│  └─ ❌ 缺少视频和图表
└─ Featured Snippets: 2/2 ✓

### 👑 E-E-A-T 权威性:14/20 ⚠️
├─ 专业度展示: 4/7
│  ├─ ❌ 缺少具体案例研究 (1/3)
│  ├─ ✓ 技术准确性良好 (2/2)
│  └─ ⚠️ 作者信息不完整 (1/2)
├─ 权威性建立: 5/7
│  ├─ ⚠️ 外部引用不足 (2/3)
│  ├─ ✓ 内容独特 (2/2)
│  └─ ⚠️ 支柱页面需要完善 (1/2)
└─ 信任度建设: 5/6 ✓
   ├─ ✓ 更新频率良好
   ├─ ✓ 数据来源透明
   └─ ⚠️ 缺少关于页面 (1/2)

### 📊 内容策略:6/10 ⚠️
├─ 集群结构: 2/4
│  └─ ❌ 内部链接不足
├─ 内容日历: 2/3 ✓
└─ 关键词蚕食: 2/3 ✓

### ⚙️ 技术 SEO:8/10 ✓
├─ robots.txt: 3/3 ✓
├─ 图片优化: 2/3
│  └─ ⚠️ 部分图片缺少 alt
├─ URL 结构: 2/2 ✓
└─ 移动友好: 1/2
   └─ ⚠️ 响应式问题

---

## 🎯 优先修复建议(按影响排序)

### 🔴 高优先级(+3 分以上)

1. **[E-E-A-T] 添加案例研究和实际经验展示** (+2 分)
   - 在博客文章中添加真实案例
   - 分享实践经验教训
   - 展示解决问题的过程

2. **[E-E-A-T] 完善作者信息和关于页面** (+2 分)
   - 创建详细的作者简介页面
   - 添加关于页面
   - 包含联系信息和团队介绍

3. **[内容策略] 优化集群内容的内部链接结构** (+2 分)
   - 确保所有相关内容互相链接
   - 创建支柱页面链接到集群内容
   - 使用描述性锚文本

### 🟡 中优先级(+1-2 分)

4. **[内容质量] 添加图表和视频内容** (+2 分)
   - 在文章中添加信息图表
   - 嵌入解释性视频
   - 使用数据可视化

5. **[元数据] 添加 Twitter Cards 标签** (+1 分)
   - 为所有页面添加 Twitter Cards
   - 使用 summary_large_image 卡片类型
   - 测试 Twitter 预览效果

6. **[结构化数据] 修复 JSON-LD 验证警告** (+2 分)
   - 添加缺失的 datePublished 字段
   - 使用 Google Rich Results 测试工具验证
   - 修复所有验证错误

### 🟢 低优先级(+1 分以下)

7. **[技术 SEO] 为图片添加 alt 文本** (+1 分)
   - 检查所有图片
   - 添加描述性 alt 文本
   - 包含关键词(自然地)

8. **[技术 SEO] 修复移动端响应式问题** (+1 分)
   - 测试移动端显示
   - 修复布局问题
   - 优化触摸目标大小

---

## 📈 改进路线图

### 第 1 周:权威性建设
- [ ] 添加 3 个案例研究
- [ ] 创建作者简介页面
- [ ] 添加关于页面
- [ ] 增加外部权威引用

### 第 2 周:内容优化
- [ ] 优化内部链接结构
- [ ] 添加图表和视频
- [ ] 修复标题结构问题
- [ ] 调整关键词密度

### 第 3 周:技术完善
- [ ] 添加 Twitter Cards
- [ ] 修复结构化数据验证错误
- [ ] 优化图片 alt 文本
- [ ] 修复移动端问题

### 第 4 周:内容策略
- [ ] 创建支柱页面
- [ ] 规划集群内容
- [ ] 建立内容日历
- [ ] 检查关键词蚕食

**预期提升:78 分 → 90+ 分**

---

## 🔍 详细分析

### 扫描统计
- 📁 项目类型:Next.js App Router
- 📄 扫描页面:15 个
- 🧩 扫描组件:23 个
- ⏱️ 扫描时间:2.3 秒

### 发现的问题
- 🔴 严重问题:3 个
- 🟡 中等问题:8 个
- 🟢 轻微问题:5 个

### 优势
✅ 元数据基础良好
✅ 内容质量较高
✅ 技术配置完善
✅ 移动友好性良好

### 劣势
❌ E-E-A-T 权威性不足
❌ 缺少多媒体内容
❌ 内部链接结构薄弱
❌ 缺少内容策略

---

## 💡 下一步建议

1. **立即执行高优先级建议** - 这些改进能快速提升评分
2. **建立内容日历** - 规划未来 3 个月的内容
3. **定期审计** - 每月进行一次 SEO 审计
4. **跟踪进度** - 使用评分系统追踪改进效果

需要我为任何建议提供详细的实施指导吗?

Read the full file on GitHub · 427 lines

Changes

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.

  1. 8d ago First seen · 427 lines · 78 tokens per session scan A 16e6d3874042

Subscribe to this mod's changes

seo-auditor is a skill published in the GitHub repository huifer/claude-code-seo (110 stars, last pushed 8mo ago), licensed MIT. It adds 78 tokens to every session and 3,367 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens