Token导航 LogoToken导航

Agent Skill · 研究检索

seo-optimizer(SEO 优化器)

seo-optimizer 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

seo-optimizer 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 64,698。

总安装 294周安装 12GitHub Stars 23下载 95核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:seo-optimizer(SEO 优化器)
来源仓库:https://github.com/chongdashu/cc-skills
仓库路径:skills/seo-optimizer
安装命令:
npx skills add https://github.com/chongdashu/cc-skills --skill seo-optimizer
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/chongdashu/cc-skills --skill seo-optimizer

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

将网页从“不可见”转化为可被搜索引擎与社交平台索引的发现友好内容。分析代码库并实施语义化优化,包括标签结构、元数据与内容清晰度改进。核心是向机器清晰传达页面主题与受众,而非堆砌关键词追求排名。适用于单页应用、静态站点或传统网站,需结合具体项目结构定制实施方案。

seo-optimizer 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/seo-optimizer

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/chongdashu/cc-skills --skill seo-optimizer;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

seo-optimizer 怎么安装?

在终端执行 npx skills add https://github.com/chongdashu/cc-skills --skill seo-optimizer。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

seo-optimizer 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

seo-optimizer 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

seo-optimizer 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

seo-optimizer 用的人多吗?

公开数据是累计安装 294 次,近一周安装 12 次,下载 95 次,GitHub 23 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

seo-optimizer 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
seo-optimizer

SEO 优化器 · 本页

29423需要联网未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

SEO Optimizer

Transform your web application from invisible to discoverable. This skill analyzes your codebase and implements comprehensive SEO optimizations that help search engines and social platforms understand, index, and surface your content.

Philosophy: SEO as Semantic Communication

SEO is not about gaming algorithms—it's about clearly communicating what your content IS to machines (search engines, social platforms, AI crawlers) so they can properly understand and surface it.

Before optimizing, ask:

  • What is this page actually about? (not what keywords we want to rank for)
  • Who is the intended audience and what are they searching for?
  • What unique value does this content provide?
  • How should machines categorize and understand this content?

Core Principles:

  1. Accuracy Over Optimization: Describe what IS, not what you wish would rank
  2. User Intent First: Match content to what searchers actually want
  3. Semantic Clarity: Use structured data to make meaning machine-readable
  4. Progressive Enhancement: Basic SEO for all pages, rich optimization for key pages
  5. Framework-Native: Use each framework's idioms, not generic hacks

The SEO Hierarchy (prioritize in order):

1. Content Quality      ← Foundation: Valuable, accurate, unique content
2. Technical Access     ← Can crawlers find and index your pages?
3. Semantic Structure   ← Do machines understand your content's meaning?
4. Meta Optimization    ← Are your titles/descriptions compelling?
5. Structured Data      ← JSON-LD for rich search results
6. Performance          ← Core Web Vitals affect rankings

Codebase Analysis Workflow

ALWAYS analyze before implementing. Different codebases need different approaches.

Step 1: Discover Framework and Structure

Identify the framework and routing pattern:

  • Next.js: Look for next.config.js, app/ or pages/ directory
  • Astro: Look for astro.config.mjs, src/pages/
  • React Router: Look for route configuration, react-router-dom
  • Gatsby: Look for gatsby-config.js, gatsby-node.js
  • Static HTML: Look for .html files in root or public/

Step 2: Audit Current SEO State

Check for existing implementations:

  • Meta tags in <head> (title, description, viewport)
  • Open Graph tags (og:title, og:image, etc.)
  • Twitter Card tags (twitter:card, twitter:image)
  • Structured data (<script type="application/ld+json">)
  • Sitemap (sitemap.xml or generation config)
  • Robots.txt file
  • Canonical URLs
  • Alt text on images

Step 3: Identify Page Types

Different pages need different SEO approaches:

Page TypePriorityKey Optimizations
Landing/HomeCriticalBrand keywords, comprehensive structured data
Product/ServiceHighProduct schema, reviews, pricing
Blog/ArticleHighArticle schema, author, publish date
DocumentationMediumHowTo/FAQ schema, breadcrumbs
About/ContactMediumOrganization schema, local business
Legal/PrivacyLowBasic meta only, often noindex

Step 4: Generate Implementation Plan

Based on analysis, prioritize:

  1. Quick wins: Missing meta tags, viewport, basic structure
  2. High impact: Structured data for key pages, sitemap
  3. Refinement: Performance, advanced schema, social optimization

See references/analysis-checklist.md for detailed audit procedures.


Meta Tags Implementation

Essential Meta Tags (Every Page)

<!-- Required -->
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>{Page Title} | {Site Name}</title>
<meta name="description" content="{150-160 char description}">

<!-- Recommended -->
<link rel="canonical" href="{full canonical URL}">
<meta name="robots" content="index, follow">

Title Tag Best Practices

Format: {Primary Content} | {Brand} or {Primary Content} - {Brand}

Guidelines:

  • 50-60 characters (Google truncates at ~60)
  • Front-load important keywords
  • Unique for every page
  • Accurately describe page content
  • Include brand for recognition (usually at end)

Title Patterns by Page Type:

Homepage:     {Brand} - {Value Proposition}
Product:      {Product Name} - {Key Benefit} | {Brand}
Article:      {Article Title} | {Brand}
Category:     {Category} Products | {Brand}
Search:       Search Results for "{Query}" | {Brand}

Meta Description Best Practices

Guidelines:

  • 150-160 characters (Google may truncate at ~155)
  • Include a call to action when appropriate
  • Accurately summarize page content
  • Unique for every page
  • Include primary keyword naturally

DO NOT:

  • Stuff keywords unnaturally
  • Use the same description across pages
  • Write descriptions that don't match content
  • Start with "Welcome to..." or similar filler

Open Graph Tags (Social Sharing)

<meta property="og:type" content="website">
<meta property="og:url" content="{canonical URL}">
<meta property="og:title" content="{title}">
<meta property="og:description" content="{description}">
<meta property="og:image" content="{1200x630 image URL}">
<meta property="og:site_name" content="{Site Name}">

Twitter Card Tags

<meta name="twitter:card" content="summary_large_image">
<meta name="twitter:site" content="@{handle}">
<meta name="twitter:title" content="{title}">
<meta name="twitter:description" content="{description}">
<meta name="twitter:image" content="{image URL}">

See references/meta-tags-complete.md for comprehensive tag reference.


Structured Data (JSON-LD)

Structured data enables rich search results (star ratings, prices, FAQs, etc.).

When to Use Which Schema

Content TypeSchemaRich Result
Organization infoOrganizationKnowledge panel
ProductsProductPrice, availability, reviews
Articles/BlogArticleHeadline, image, date
How-to guidesHowToStep-by-step in search
FAQsFAQPageExpandable Q&A
EventsEventDate, location, tickets
RecipesRecipeImage, time, ratings
Local businessLocalBusinessMaps, hours, contact
BreadcrumbsBreadcrumbListNavigation path

Implementation Pattern

<script type="application/ld+json">
{
  "@context": "https://schema.org",
  "@type": "Organization",
  "name": "Company Name",
  "url": "https://example.com",
  "logo": "https://example.com/logo.png",
  "sameAs": [
    "https://twitter.com/company",
    "https://linkedin.com/company/company"
  ]
}
</script>

Multiple Schemas Per Page

Use @graph to combine schemas:

{
  "@context": "https://schema.org",
  "@graph": [
    { "@type": "Organization", ... },
    { "@type": "WebSite", ... },
    { "@type": "BreadcrumbList", ... }
  ]
}

See references/structured-data-schemas.md for complete schema examples.


Technical SEO

Sitemap Generation

XML Sitemap Requirements:

  • Include all indexable pages
  • Exclude noindex pages, redirects, error pages
  • Update <lastmod> when content changes
  • Submit to Google Search Console

Framework implementations: See references/framework-implementations.md

Robots.txt

Standard Template:

User-agent: *
Allow: /

# Block admin/private areas
Disallow: /admin/
Disallow: /api/
Disallow: /private/

# Point to sitemap
Sitemap: https://yourdomain.com/sitemap.xml

Canonical URLs

Always set canonical URLs to:

  • Prevent duplicate content issues
  • Consolidate link equity
  • Specify preferred URL version

Handle:

  • www vs non-www
  • http vs https
  • Trailing slashes
  • Query parameters

Performance (Core Web Vitals)

Core Web Vitals affect rankings. Monitor:

MetricTargetWhat It Measures
LCP< 2.5sLargest Contentful Paint (loading)
INP< 200msInteraction to Next Paint (interactivity)
CLS< 0.1Cumulative Layout Shift (visual stability)

Quick wins:

  • Optimize images (WebP, lazy loading, proper sizing)
  • Minimize JavaScript bundles
  • Use efficient fonts (display: swap)
  • Implement proper caching

Anti-Patterns to Avoid

❌ Keyword Stuffing

<!-- BAD -->
<title>Best Shoes | Buy Shoes | Cheap Shoes | Shoes Online | Shoe Store</title>

<!-- GOOD -->
<title>Running Shoes for Marathon Training | SportShop</title>

Why bad: Search engines penalize unnatural keyword repetition. Users don't click spammy titles.

❌ Duplicate Descriptions Using the same meta description across multiple pages. Why bad: Misses opportunity for page-specific relevance. Google may ignore and auto-generate.

❌ Description/Content Mismatch Writing descriptions for keywords rather than actual content. Why bad: High bounce rates signal low quality. Users feel deceived.

❌ Missing Alt Text

<!-- BAD -->
<img src="product.jpg">

<!-- GOOD -->
<img src="product.jpg" alt="Blue Nike Air Max running shoe, side view">

Why bad: Accessibility violation. Missed image search opportunity.

❌ Blocking Crawlers Unintentionally

# Accidentally blocking everything
User-agent: *
Disallow: /

Why bad: Complete deindexing. Check robots.txt carefully.

❌ Ignoring Mobile Not having responsive design or mobile-specific considerations. Why bad: Google uses mobile-first indexing. Most traffic is mobile.

❌ Over-Optimization Adding structured data for content that doesn't exist. Why bad: Schema violations can result in penalties. Trust erosion.

❌ Generic Auto-Generated Content

<!-- BAD: Template without customization -->
<meta name="description" content="Welcome to our website. We offer great products and services.">

Why bad: Provides no value. Won't rank. Won't get clicks.


Variation Guidance

IMPORTANT: SEO implementation should vary based on context.

Vary based on:

  • Industry: E-commerce needs Product schema; SaaS needs Software schema
  • Content type: Blog posts vs landing pages vs documentation
  • Audience: B2B vs B2C affects tone and keywords
  • Competition: Highly competitive niches need more sophisticated optimization
  • Framework: Use native patterns (Next.js metadata API vs manual tags)

Avoid converging on:

  • Same title format for all page types
  • Generic descriptions that could apply to any site
  • Identical structured data without page-specific content
  • One-size-fits-all sitemap configuration

Framework Quick Reference

Next.js (App Router)

// app/page.tsx
import { Metadata } from 'next'

export const metadata: Metadata = {
  title: 'Page Title | Brand',
  description: 'Page description',
  openGraph: {
    title: 'Page Title',
    description: 'Page description',
    images: ['/og-image.png'],
  },
}

Next.js (Pages Router)

// pages/index.tsx
import Head from 'next/head'

export default function Page() {
  return (
    <Head>
      <title>Page Title | Brand</title>
      <meta name="description" content="Page description" />
    </Head>
  )
}

Astro

---
// src/pages/index.astro
import Layout from '../layouts/Layout.astro';
---
<Layout
  title="Page Title | Brand"
  description="Page description"
  ogImage="/og-image.png"
/>

React (react-helmet)

import { Helmet } from 'react-helmet';

function Page() {
  return (
    <Helmet>
      <title>Page Title | Brand</title>
      <meta name="description" content="Page description" />
    </Helmet>
  );
}

See references/framework-implementations.md for complete guides.


Scripts

analyze_seo.py

Analyzes a codebase for SEO issues and opportunities:

python scripts/analyze_seo.py <path-to-project>

Output:

  • Current SEO state (what's implemented)
  • Missing elements by priority
  • Page-by-page recommendations
  • Structured data opportunities

generate_sitemap.py

Generates sitemap.xml from project routes:

python scripts/generate_sitemap.py <path-to-project> --domain https://example.com

Remember

SEO is semantic communication, not algorithm manipulation.

The best SEO:

  • Accurately describes what content IS
  • Helps machines understand meaning through structured data
  • Prioritizes user value over keyword optimization
  • Uses framework-native patterns
  • Implements progressively based on page importance

Focus on making your content findable and understandable. The rankings follow from genuine value clearly communicated.

Claude is capable of comprehensive SEO analysis and implementation. These guidelines illuminate the path—they don't fence it.

平台分布

Codex

35.35%
按下载量换算34

Claude

27.49%
按下载量换算26

Cursor

18.15%
按下载量换算17

Gemini CLI

9.7%
按下载量换算9

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills