Token导航 LogoToken导航

Agent Skill · 研究检索

roier-seo(roier SEO 搜索)

roier-seo 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。

roier-seo 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,权限为可写文件;许可证为 MIT,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 17,794。

总安装 6,414周安装 262GitHub Stars 26,385下载 2,075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
MIT

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:roier-seo(roier SEO 搜索)
来源仓库:https://github.com/davila7/claude-code-templates
仓库路径:skills/roier-seo
安装命令:
npx skills add https://github.com/davila7/claude-code-templates --skill roier-seo
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。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/davila7/claude-code-templates --skill roier-seo

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。

roier-seo 用于网站 SEO 审计与自动修复,基于 Lighthouse 检测和技术优化建议提升搜索排名。它适用于需要改进页面性能、核心 Web 指标或结构化数据的场景,支持多框架适配。可通过自动化工具实现 meta 标签、JSON-LD 和无障碍优化的直接代码级修复。

安装命令为 npx skills add https://github.com/davila7/claude-code-templates --skill roier-seo,需确认权限范围和维护状态。使用前请核实是否会触发联网、命令执行或文件读写操作,避免对生产环境造成意外影响。

来源仓库内路径:skills/roier-seo

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/davila7/claude-code-templates --skill roier-se…;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

    它需要可写文件,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

roier-seo 怎么安装?

在终端执行 npx skills add https://github.com/davila7/claude-code-templates --skill roier-seo。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

roier-seo 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。

roier-seo 需要什么权限?

权限级别是可写文件。该 Skill 可能写入或修改本地文件,使用前需要确认目标目录和修改范围。

roier-seo 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

roier-seo 用的人多吗?

公开数据是累计安装 6,414 次,近一周安装 262 次,下载 2,075 次,GitHub 26,385 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。

roier-seo 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

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。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 来源仓库有 26,385 星,维护活跃度相对可查。

先想清楚的地方

  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 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
roier-seo

roier SEO 搜索 · 本页

6,41426,385可写文件MIT有提醒

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

Roier SEO - Technical SEO Auditor & Fixer

AI-powered SEO optimization skill that audits websites and automatically implements fixes.

When to use this skill

Use Roier SEO when:

  • User asks to "audit my site" or "check SEO"
  • User wants to "improve performance" or "fix SEO issues"
  • User mentions "lighthouse", "pagespeed", or "core web vitals"
  • User wants to add/fix meta tags, structured data, or accessibility
  • User has a local dev server and wants SEO analysis

Key features:

  • Full Audits: Lighthouse audits on any URL (localhost or live)
  • Auto-Fix: Implements fixes directly in the codebase
  • Framework Aware: Detects Next.js, React, Vue, Nuxt, plain HTML
  • Core Web Vitals: Track FCP, LCP, TBT, CLS metrics
  • Structured Data: JSON-LD schemas for rich snippets
  • Accessibility: WCAG compliance fixes

Use alternatives instead:

  • React Best Practices: For general React performance optimization
  • Manual Lighthouse: For one-off audits without auto-fixing

Quick start

Installation

After installing the skill, install the audit dependencies:

cd ~/.claude/skills/roier-seo/scripts
npm install

Running an Audit

For a live website:

node ~/.claude/skills/roier-seo/scripts/audit.js https://example.com

For a local dev server (must be running):

node ~/.claude/skills/roier-seo/scripts/audit.js http://localhost:3000

Output formats:

# JSON output (default, for programmatic use)
node ~/.claude/skills/roier-seo/scripts/audit.js https://example.com

# Human-readable summary
node ~/.claude/skills/roier-seo/scripts/audit.js https://example.com --output=summary

# Save to file
node ~/.claude/skills/roier-seo/scripts/audit.js https://example.com --save=results.json

Audit categories

The audit returns scores (0-100) for five categories:

CategoryDescriptionWeight
PerformancePage load speed, Core Web VitalsHigh
AccessibilityWCAG compliance, screen reader supportHigh
Best PracticesSecurity, modern web standardsMedium
SEOSearch engine optimization, crawlabilityHigh
PWAProgressive Web App complianceLow

Technical SEO fix patterns

Meta tags (HTML Head)

Title tag
<!-- Bad -->
<title>Home</title>

<!-- Good -->
<title>Primary Keyword - Secondary Keyword | Brand Name</title>

Rules:

  • 50-60 characters max
  • Include primary keyword near the beginning
  • Unique per page
  • Include brand name at end
Meta description
<meta name="description" content="Compelling description with keywords. 150-160 characters that encourages clicks from search results.">

Rules:

  • 150-160 characters
  • Include primary and secondary keywords naturally
  • Compelling call-to-action
  • Unique per page
Essential meta tags
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1">
<html lang="en">

Open Graph tags (social sharing)

<meta property="og:title" content="Page Title">
<meta property="og:description" content="Page description">
<meta property="og:image" content="https://example.com/image.jpg">
<meta property="og:url" content="https://example.com/page">
<meta property="og:type" content="website">
<meta property="og:site_name" content="Brand Name">

Twitter Card tags

<meta name="twitter:card" content="summary_large_image">
<meta name="twitter:title" content="Page Title">
<meta name="twitter:description" content="Page description">
<meta name="twitter:image" content="https://example.com/image.jpg">

Canonical URL

<link rel="canonical" href="https://example.com/canonical-page">

Robots meta

<!-- Allow indexing (default) -->
<meta name="robots" content="index, follow">

<!-- Prevent indexing (for staging, admin pages) -->
<meta name="robots" content="noindex, nofollow">

Structured data (JSON-LD)

Website schema

<script type="application/ld+json">
{
  "@context": "https://schema.org",
  "@type": "WebSite",
  "name": "Site Name",
  "url": "https://example.com",
  "potentialAction": {
    "@type": "SearchAction",
    "target": "https://example.com/search?q={search_term_string}",
    "query-input": "required name=search_term_string"
  }
}
</script>

Organization schema

<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>

BreadcrumbList schema

<script type="application/ld+json">
{
  "@context": "https://schema.org",
  "@type": "BreadcrumbList",
  "itemListElement": [
    {"@type": "ListItem", "position": 1, "name": "Home", "item": "https://example.com"},
    {"@type": "ListItem", "position": 2, "name": "Category", "item": "https://example.com/category"},
    {"@type": "ListItem", "position": 3, "name": "Page"}
  ]
}
</script>

Article schema (for blog posts)

<script type="application/ld+json">
{
  "@context": "https://schema.org",
  "@type": "Article",
  "headline": "Article Title",
  "author": {"@type": "Person", "name": "Author Name"},
  "datePublished": "2024-01-15",
  "dateModified": "2024-01-20",
  "image": "https://example.com/article-image.jpg",
  "publisher": {
    "@type": "Organization",
    "name": "Publisher Name",
    "logo": {"@type": "ImageObject", "url": "https://example.com/logo.png"}
  }
}
</script>

Performance optimizations

Image optimization

<!-- Add width/height to prevent CLS -->
<img src="image.jpg" alt="Description" width="800" height="600">

<!-- Add lazy loading -->
<img src="image.jpg" alt="Description" loading="lazy">

<!-- Use modern formats -->
<picture>
  <source srcset="image.avif" type="image/avif">
  <source srcset="image.webp" type="image/webp">
  <img src="image.jpg" alt="Description">
</picture>

Font optimization

<!-- Preload critical fonts -->
<link rel="preload" href="/fonts/main.woff2" as="font" type="font/woff2" crossorigin>
@font-face {
  font-family: 'Custom Font';
  src: url('/fonts/custom.woff2') format('woff2');
  font-display: swap;
}

Resource hints

<!-- Preconnect to critical third-party origins -->
<link rel="preconnect" href="https://fonts.googleapis.com">
<link rel="preconnect" href="https://cdn.example.com">

<!-- DNS prefetch for non-critical origins -->
<link rel="dns-prefetch" href="https://analytics.example.com">

<!-- Preload critical resources -->
<link rel="preload" href="/critical.css" as="style">

Accessibility fixes

Alt text

<!-- Good (descriptive) -->
<img src="photo.jpg" alt="Team members collaborating in the office">

<!-- Good (decorative) -->
<img src="decoration.jpg" alt="" role="presentation">

Color contrast

  • 4.5:1 contrast ratio for normal text
  • 3:1 contrast ratio for large text (18px+ or 14px+ bold)

Form labels

<label for="email">Email Address</label>
<input type="email" id="email" name="email">

Skip link

<a href="#main-content" class="skip-link">Skip to main content</a>

<style>
.skip-link {
  position: absolute;
  left: -9999px;
}
.skip-link:focus {
  left: 0;
  top: 0;
  z-index: 9999;
  background: #000;
  color: #fff;
  padding: 8px 16px;
}
</style>

Button accessibility

<!-- Icon button needs aria-label -->
<button aria-label="Close menu">
  <svg>...</svg>
</button>

Framework-specific patterns

Next.js (App Router)

// app/layout.tsx
import type { Metadata } from 'next'

export const metadata: Metadata = {
  title: {
    default: 'Site Name',
    template: '%s | Site Name'
  },
  description: 'Site description',
  openGraph: {
    title: 'Site Name',
    description: 'Site description',
    url: 'https://example.com',
    siteName: 'Site Name',
    type: 'website',
  },
}

Next.js (Pages Router)

import Head from 'next/head';

export default function Page() {
  return (
    <>
      <Head>
        <title>Page Title | Brand</title>
        <meta name="description" content="Page description" />
        <link rel="canonical" href="https://example.com/page" />
      </Head>
      <main>...</main>
    </>
  );
}

React (with react-helmet)

import { Helmet } from 'react-helmet';

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

Vue.js (with useHead)

<script setup>
useHead({
  title: 'Page Title | Brand',
  meta: [
    { name: 'description', content: 'Page description' }
  ],
  link: [
    { rel: 'canonical', href: 'https://example.com/page' }
  ]
})
</script>

Nuxt.js

<script setup>
useSeoMeta({
  title: 'Page Title | Brand',
  description: 'Page description',
  ogTitle: 'Page Title',
  ogDescription: 'Page description',
  ogImage: 'https://example.com/og-image.jpg'
})
</script>

Workflow

Step 1: Audit

Run the audit script on the target URL:

node ~/.claude/skills/roier-seo/scripts/audit.js <URL>

Step 2: Identify framework

Check package.json dependencies and framework-specific files.

Step 3: Prioritize fixes

  1. Critical (red): Fix immediately
  2. Serious (orange): Fix soon
  3. Moderate (yellow): Fix when possible
  4. Minor (gray): Nice to have

Step 4: Implement

Use the fix patterns above, adapted to the user's framework.

Step 5: Re-audit

Run the audit again to verify improvements.

Requirements

  • Node.js 18+
  • Chrome/Chromium browser (for Lighthouse)
  • Audit script dependencies (installed via npm)

Resources

Version history

v1.0.0 (January 2026)

  • Initial release
  • Lighthouse audit integration
  • 50+ SEO fix patterns
  • Framework support for Next.js, React, Vue, Nuxt

平台分布

Claude Code

27.35%
按下载量换算568

OpenCode

21.98%
按下载量换算456

Cursor

16.44%
按下载量换算341

Antigravity

12.46%
按下载量换算259

Gemini CLI

8.12%
按下载量换算168

windsurf

3.27%
按下载量换算68

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

可写文件

该 Skill 可能写入或修改本地文件,使用前需要确认目标目录和修改范围。

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。

继续浏览同类 Skills