SEO审计工具

SEO Audit Skill

by amdf01-debug

3.9k搜索与获取未扫描2026年3月23日

安装

claude skill add --url github.com/openclaw/skills/tree/main/skills/amdf01-debug/sw-seo-audit

文档

Trigger

When the user wants to audit a page or site for SEO issues, check metadata, review headings structure, or identify content gaps.

Trigger phrases: "SEO audit", "check SEO", "audit this page", "metadata check", "why isn't this ranking", "SEO issues"

Process

  1. Fetch: Load the target URL and extract HTML structure
  2. Technical audit: Check metadata, headings, images, links, schema
  3. Content audit: Assess keyword targeting, content depth, readability
  4. Competitor check: Compare against top 3 ranking pages for target keyword
  5. Report: Prioritised issues with specific fixes

Audit Checklist

Technical

  • Title tag: present, unique, 50-60 chars, includes target keyword
  • Meta description: present, 150-160 chars, compelling, includes keyword
  • H1: exactly one, includes primary keyword
  • H2-H6: logical hierarchy, include related keywords
  • Images: all have alt text, descriptive filenames, appropriate sizes
  • Internal links: at least 3 relevant internal links
  • External links: at least 1-2 authoritative outbound links
  • URL: clean, readable, includes keyword
  • Schema markup: appropriate type (Article, Product, FAQ, etc.)
  • Canonical tag: present and correct
  • OG/Twitter meta tags: present with image

Content

  • Word count: appropriate for topic (compare to ranking competitors)
  • Keyword density: natural usage, not stuffed
  • Content structure: scannable, uses lists and subheadings
  • Freshness: content is current and accurate
  • Unique value: offers something competitors don't
  • Media: includes images, diagrams, or video where appropriate

Output Format

markdown
# SEO Audit: [URL]

## Score: [X/100]

## Critical Issues (fix immediately)
1. [Issue] — [specific fix]

## Warnings (fix this week)
1. [Issue] — [specific fix]

## Opportunities (improve ranking)
1. [Opportunity] — [how to implement]

## Competitor Comparison
| Factor | Your Page | Competitor 1 | Competitor 2 |
|--------|-----------|-------------|-------------|
...

## Recommended Actions (prioritised)
1. [Action] — Est. impact: [High/Medium/Low]

Rules

  • Always provide specific, actionable fixes — not generic advice
  • Prioritise by impact: title tag fix > alt text fix
  • Compare against actual competitors, not abstract best practices
  • Flag quick wins separately from long-term improvements

相关 Skills

浏览器自动化

by chulla-ceja

热门

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

搜索与获取
未扫描3.9k

多视角辩论

by caius-kong

Multi-perspective structured debate for complex topics. Spawn parallel subagents with opposing stances, cross-inject arguments for rebuttal, then synthesize via neutral judge into a consensus report with recommendations and scenario matrix. Use when: (1) user asks for deep comparison, pros/cons, or X vs Y analysis, (2) user asks for multi-angle research on a controversial or complex topic, (3) user explicitly requests debate, dialectical analysis, or adversarial research. NOT for: simple factual lookups, single-perspective deep research (use academic-deep-research), or quick opinion questions.

搜索与获取
未扫描3.9k

接口规范

by alexxxiong

热门

API 规范管理工具 - 跨项目 API 文档的初始化、更新、查询与搜索。Triggers: 'API文档', 'API规范', '接口文档', '路由解析', 'apispec', 'API lookup', 'API search'.

搜索与获取
未扫描3.9k

相关 MCP 服务

by Anthropic

热门

Puppeteer 是让 Claude 自动操作浏览器进行网页抓取和测试的 MCP 服务器。

这个服务器解决了手动编写 Puppeteer 脚本的繁琐问题,适合需要自动化网页交互的开发者,比如抓取动态内容或做端到端测试。不过,作为参考实现,它可能缺少生产级的安全防护,建议在可控环境中使用。

搜索与获取
83.1k

网页抓取

编辑精选

by Anthropic

热门

Fetch 是 MCP 官方参考服务器,让 AI 能抓取网页并转为 Markdown 格式。

这个服务器解决了 AI 直接处理网页内容时格式混乱的问题,适合需要让 Claude 分析在线文档或新闻的开发者。不过作为参考实现,它缺乏生产级的安全配置,你得自己处理反爬虫和隐私风险。

搜索与获取
83.1k

Brave 搜索

编辑精选

by Anthropic

热门

Brave Search 是让 Claude 直接调用 Brave 搜索 API 获取实时网络信息的 MCP 服务器。

如果你想让 AI 助手帮你搜索最新资讯或技术文档,这个工具能绕过传统搜索的限制,直接返回结构化数据。特别适合需要实时信息的开发者,比如查 API 更新或竞品动态。不过它依赖 Brave 的 API 配额,高频使用可能受限。

搜索与获取
83.1k

评论