/ 目錄 / 演練場 / seo-audit-skill
← 全部伺服器 ↗ GitHub
● 社群 seo-skills ⚡ 即開即用

seo-audit-skill

作者 seo-skills · seo-skills/seo-audit-skill

108 SEO audit rules across 12 categories — Core Web Vitals, security headers, structured data, accessibility — run from Claude Code.

SEO Audit Skill wraps a CLI that crawls any URL and evaluates 108 rules across 12 categories: on-page SEO, Core Web Vitals, security headers, structured data, accessibility, crawlability, mobile, i18n, and more. Claude Code invokes it, interprets the report, and drafts actionable fixes grouped by impact.

▶ 觀看演示 📦 安裝 💡 使用場景

為什麼要用

核心特性

即時演示

實際使用效果

seo-audit-skill.replay ▶ 就緒
0/0

安裝

選擇你的客戶端

~/Library/Application Support/Claude/claude_desktop_config.json  · Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "seo-audit-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/seo-skills/seo-audit-skill",
        "~/.claude/skills/seo-audit-skill"
      ],
      "_inferred": true
    }
  }
}

開啟 Claude Desktop → Settings → Developer → Edit Config。儲存後重啟應用。

~/.cursor/mcp.json · .cursor/mcp.json
{
  "mcpServers": {
    "seo-audit-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/seo-skills/seo-audit-skill",
        "~/.claude/skills/seo-audit-skill"
      ],
      "_inferred": true
    }
  }
}

Cursor 使用與 Claude Desktop 相同的 mcpServers 格式。專案級設定優先於全域。

VS Code → Cline → MCP Servers → Edit
{
  "mcpServers": {
    "seo-audit-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/seo-skills/seo-audit-skill",
        "~/.claude/skills/seo-audit-skill"
      ],
      "_inferred": true
    }
  }
}

點擊 Cline 側欄中的 MCP Servers 圖示，然後選 "Edit Configuration"。

~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "seo-audit-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/seo-skills/seo-audit-skill",
        "~/.claude/skills/seo-audit-skill"
      ],
      "_inferred": true
    }
  }
}

格式與 Claude Desktop 相同。重啟 Windsurf 生效。

~/.continue/config.json
{
  "mcpServers": [
    {
      "name": "seo-audit-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/seo-skills/seo-audit-skill",
        "~/.claude/skills/seo-audit-skill"
      ]
    }
  ]
}

Continue 使用伺服器物件陣列，而非映射。

~/.config/zed/settings.json
{
  "context_servers": {
    "seo-audit-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/seo-skills/seo-audit-skill",
          "~/.claude/skills/seo-audit-skill"
        ]
      }
    }
  }
}

加入 context_servers。Zed 儲存後熱重載。

claude mcp add seo-audit-skill -- git clone https://github.com/seo-skills/seo-audit-skill ~/.claude/skills/seo-audit-skill

一行命令搞定。用 claude mcp list 驗證，claude mcp remove 移除。

使用場景

實戰用法： seo-audit-skill

How to run your first full SEO audit and prioritize fixes

👤 Site owners and SEO practitioners who inherit a site with unknown SEO health ⏱ ~30 min beginner

何時使用： New project, new site, or pre-launch checklist.

前置條件
  • Skill installed — git clone https://github.com/seo-skills/seo-audit-skill ~/.claude/skills/seo-audit-skill
  • Node 18+ — nvm install 18
步驟
  1. Run full audit
    Run seo-audit-skill on https://example.com — all 108 rules, output markdown.✓ 已複製
    → Report with per-rule pass/fail and a category summary
  2. Prioritize by impact
    Group the failures into 'ship this week' (high impact, low effort) vs 'backlog'. Explain the cutoff.✓ 已複製
    → Ranked fix list with rationale
  3. Generate fix PRs
    For the top 5 'ship this week' items, draft the code changes in a PR-ready diff.✓ 已複製
    → Diffs for meta tags, headers, and structured data

結果： A sprint-sized SEO fix list with drafted diffs.

注意事項
  • Lighthouse scores vary run-to-run — Run 3 times, take median; skill supports --runs=3
  • Rules flag false positives on JS-heavy SPAs — Use --render=js to enable JS rendering; costs more time
搭配使用： trae-skill

Run just the Core Web Vitals checks in CI

👤 Performance engineers wiring SEO to CI ⏱ ~20 min intermediate

何時使用： You want a CI gate that blocks regressions in LCP/CLS/INP.

步驟
  1. Scope to CWV category
    Run seo-audit-skill --category=cwv on our staging URL.✓ 已複製
    → Just the CWV rules with values
  2. Wrap in CI
    Generate a GitHub Actions step that runs this and fails if LCP > 2.5s.✓ 已複製
    → YAML snippet with threshold logic

結果： A CI gate that catches perf regressions before prod.

注意事項
  • CI runner is slower than users — Use field data via CrUX where possible; treat lab data as a regression detector, not absolute target

Validate and fix structured data (JSON-LD)

👤 Developers wanting rich results in SERPs ⏱ ~25 min intermediate

何時使用： Your pages aren't getting rich snippets despite having JSON-LD.

步驟
  1. Scope to structured-data rules
    Run seo-audit-skill --category=structured-data on these 5 URLs.✓ 已複製
    → Per-URL list of schema errors and missing required fields
  2. Generate corrected JSON-LD
    For each error, produce the corrected JSON-LD snippet keyed to the page type.✓ 已複製
    → Per-page snippets ready to paste

結果： Schema.org-valid JSON-LD deployed; ready to re-check via Google Rich Results Test.

注意事項
  • Schema valid but Google still doesn't show rich results — Validity is necessary, not sufficient. Check eligibility guidelines for the specific rich result type.

Audit and set security headers

👤 Developers wanting baseline security + SEO signal ⏱ ~45 min intermediate

何時使用： securityheaders.com gave you an F and you want to understand why.

步驟
  1. Run security category
    Run seo-audit-skill --category=security on https://example.com.✓ 已複製
    → CSP, HSTS, X-Frame-Options, Referrer-Policy status
  2. Generate headers config
    Produce the nginx and Cloudflare Worker configs to set the missing headers safely (report-only CSP first).✓ 已複製
    → Copy-paste configs with report-only CSP

結果： A secure header config rolled out behind report-only mode.

注意事項
  • Enforcing CSP breaks the site — Always start with Content-Security-Policy-Report-Only; watch reports for 1-2 weeks before enforcing
搭配使用： claude-code-owasp-skill

組合

與其他 MCP 搭配，撬動十倍槓桿

seo-audit-skill + trae-skill

TRAE scaffolds SEO basics, seo-audit verifies them

Scaffold SEO with TRAE, run seo-audit to verify, fix gaps.✓ 已複製
seo-audit-skill + claude-code-owasp-skill

Security-header subset of SEO overlaps with OWASP checks

Run seo-audit security category, then OWASP skill for deeper security review.✓ 已複製

工具

此 MCP 暴露的能力

工具輸入參數何時呼叫成本
full_audit url: str, runs?: int, render?: 'js'|'static' First audit on a site 0
category_audit url, category: 'cwv'|'security'|'structured-data'|... Focused checks or CI 0
diff_fix_generator report, top_n? After audit, to turn findings into PRs Claude tokens

成本與限制

運行它的成本

API 配額
None. Runs locally via headless Chromium.
每次呼叫 Token 數
Report interpretation uses 5-15k Claude tokens depending on site size
費用
Free
提示
Use --category= to avoid running all 108 rules when you only need a subset.

安全

權限、密鑰、影響範圍

憑證儲存： No credentials
資料出站： Fetches the target URL and its assets. Does not send report to any third party.

故障排查

常見錯誤與修復

Puppeteer fails to launch

Install Chrome dependencies: apt-get install libgbm1 libnss3 (Linux) or run npx puppeteer browsers install chrome

驗證： node -e 'require("puppeteer").launch().then(b=>b.close())'
Rules flag modern JS framework features as problems

Use --render=js so the audit runs post-hydration

All CWV rules report N/A

Lighthouse lab mode; on slow connections it times out. Increase --timeout.

替代方案

seo-audit-skill 對比其他方案

替代方案何時用它替代權衡
Google Lighthouse CLIYou only need the canonical CWV/perf subsetNo structured-data or SEO-specific rules
Screaming FrogYou need enterprise-grade crawling of large sitesPaid, desktop app, not LLM-integrated

更多

資源

📖 閱讀 GitHub 上的官方 README

🐙 查看未解決的 issue

🔍 瀏覽全部 400+ MCP 伺服器和 Skills