Token导航 LogoToken导航

Agent Skill · 研究检索

seo-expert(SEO expert 搜索)

seo-expert 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-expert 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,权限为操作浏览器;许可证信息还不明确,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 29,279。

总安装 3,081周安装 131GitHub Stars 4下载 1,079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-expert(SEO expert 搜索)
来源仓库:https://github.com/dengineproblem/agents-monorepo
仓库路径:skills/seo-expert
安装命令:
npx skills add https://github.com/dengineproblem/agents-monorepo --skill seo-expert
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/dengineproblem/agents-monorepo --skill seo-expert

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。

seo-expert 提供搜索引擎优化领域的深度专业知识,涵盖技术、页面内和页面外 SEO 核心能力。适用于需要关键词研究、站点架构优化、内容策略或竞品分析等 SEO 相关任务的场景。通过结构化能力清单输出建议,需结合具体项目目标使用,避免泛化推荐。

安装前请确认是否涉及外部数据抓取或自动化操作,注意遵守目标网站的 robots.txt 及相关政策。seo-expert 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-expert

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/dengineproblem/agents-monorepo --skill seo-exp…;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

    它需要操作浏览器,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-expert 怎么安装?

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

seo-expert 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-expert 需要什么权限?

权限级别是操作浏览器。该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

seo-expert 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-expert 用的人多吗?

公开数据是累计安装 3,081 次,近一周安装 131 次,下载 1,079 次,GitHub 4 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-expert 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。

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-expert

SEO expert 搜索 · 本页

3,0814操作浏览器未明确有提醒

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

SEO Expert

Deep expertise in search engine optimization including technical, on-page, and off-page SEO.

Core Competencies

technical_seo:
  - "Site architecture"
  - "Crawlability and indexation"
  - "Core Web Vitals"
  - "Schema markup"
  - "Mobile optimization"
  - "Site speed"

on_page_seo:
  - "Keyword research"
  - "Content optimization"
  - "Meta tags"
  - "Header structure"
  - "Internal linking"
  - "Image optimization"

off_page_seo:
  - "Link building"
  - "Digital PR"
  - "Brand mentions"
  - "Guest posting"
  - "Partnership links"
  - "Competitor analysis"

Keyword Research

keyword_research_process:
  step_1_seed:
    action: "Identify core topics"
    tools: ["Brainstorming", "Competitor analysis"]
    output: "10-20 seed keywords"

  step_2_expansion:
    action: "Expand keyword list"
    sources:
      - "Google Autocomplete"
      - "People Also Ask"
      - "Related searches"
      - "Ahrefs/SEMrush suggestions"
    output: "200-500 keyword variations"

  step_3_analysis:
    metrics:
      volume: "Monthly search volume"
      difficulty: "Keyword difficulty score"
      intent: "Informational/Commercial/Transactional"
      trend: "Rising, stable, declining"

  step_4_mapping:
    action: "Assign keywords to pages"
    rules:
      - "One primary keyword per page"
      - "3-5 secondary keywords"
      - "Group by intent"

  step_5_prioritization:
    formula: |
      Score = (Volume × Intent Weight) / Difficulty
    priority:
      high: "High volume, low difficulty, high intent"
      medium: "Moderate on all factors"
      low: "Low volume or high difficulty"

search_intent:
  types:
    informational:
      signals: ["what", "how", "why", "guide", "tutorial"]
      content: "Blog posts, guides, tutorials"
      example: "what is SEO"

    navigational:
      signals: ["brand name", "login", "site name"]
      content: "Homepage, product pages"
      example: "ahrefs login"

    commercial:
      signals: ["best", "top", "review", "comparison", "vs"]
      content: "Comparison pages, reviews"
      example: "best SEO tools 2024"

    transactional:
      signals: ["buy", "price", "discount", "coupon"]
      content: "Product pages, pricing"
      example: "buy ahrefs subscription"

On-Page Optimization

on_page_checklist:
  title_tag:
    length: "50-60 characters"
    structure: "Primary Keyword | Secondary | Brand"
    tips:
      - "Front-load primary keyword"
      - "Include power words"
      - "Make it compelling"

  meta_description:
    length: "150-160 characters"
    tips:
      - "Include primary keyword"
      - "Add call-to-action"
      - "Highlight unique value"
      - "Match search intent"

  url_structure:
    format: "/category/keyword-slug"
    rules:
      - "Short and descriptive"
      - "Include target keyword"
      - "Use hyphens, not underscores"
      - "Lowercase only"
      - "No stop words"

  headings:
    h1:
      count: "One per page"
      content: "Primary keyword variation"
    h2_h3:
      usage: "Logical content structure"
      keywords: "Include secondary keywords"

  content:
    first_100_words: "Include primary keyword"
    density: "1-2% keyword density (natural)"
    length: "Match or exceed competitors"
    format:
      - "Short paragraphs"
      - "Bullet points"
      - "Tables where appropriate"
      - "Images every 300-500 words"

  internal_linking:
    anchor_text: "Descriptive, keyword-rich"
    quantity: "3-5 internal links per 1000 words"
    strategy: "Link to relevant, important pages"

  images:
    filename: "descriptive-keyword.jpg"
    alt_text: "Descriptive, include keyword"
    compression: "WebP format preferred"
    lazy_loading: "Enable for below-fold images"

  schema_markup:
    types:
      article: "Blog posts"
      product: "E-commerce pages"
      faq: "FAQ sections"
      how_to: "Tutorial content"
      local_business: "Location pages"

Technical SEO

technical_audit:
  crawlability:
    robots_txt:
      - "Allow important pages"
      - "Block admin, duplicates"
      - "Include sitemap reference"

    xml_sitemap:
      - "Include all indexable URLs"
      - "Update automatically"
      - "Submit to Search Console"
      - "Split if >50k URLs"

    canonicalization:
      - "Self-referencing canonicals"
      - "Handle duplicate content"
      - "Consistent URL format"

  indexation:
    checks:
      - "site: search coverage"
      - "Index coverage in GSC"
      - "No unintended noindex"

    issues:
      - "Thin content"
      - "Duplicate content"
      - "Orphan pages"
      - "Redirect chains"

  site_speed:
    core_web_vitals:
      lcp:
        metric: "Largest Contentful Paint"
        target: "<2.5s"
        fixes:
          - "Optimize images"
          - "Preload critical resources"
          - "Use CDN"

      fid:
        metric: "First Input Delay"
        target: "<100ms"
        fixes:
          - "Minimize JavaScript"
          - "Use web workers"
          - "Code splitting"

      cls:
        metric: "Cumulative Layout Shift"
        target: "<0.1"
        fixes:
          - "Set image dimensions"
          - "Reserve ad space"
          - "Avoid dynamic content insertion"

    optimization:
      - "Enable compression (Gzip/Brotli)"
      - "Minify CSS/JS"
      - "Leverage browser caching"
      - "Reduce server response time"
      - "Implement lazy loading"

  mobile:
    requirements:
      - "Mobile-first indexing ready"
      - "Responsive design"
      - "Touch-friendly elements"
      - "Readable font sizes"
      - "No horizontal scrolling"

  security:
    https:
      - "SSL certificate valid"
      - "Force HTTPS redirect"
      - "No mixed content"

Link Building

link_building_strategies:
  content_marketing:
    linkable_assets:
      - "Original research/data"
      - "Comprehensive guides"
      - "Free tools/calculators"
      - "Infographics"
      - "Expert roundups"

    promotion:
      - "Outreach to industry sites"
      - "Social amplification"
      - "PR distribution"

  digital_pr:
    tactics:
      - "News hijacking"
      - "Expert commentary"
      - "Data-driven stories"
      - "Brand mentions → links"

    targets:
      - "News sites"
      - "Industry publications"
      - "Podcasts"

  guest_posting:
    process:
      - "Find relevant sites"
      - "Check domain authority"
      - "Pitch unique topics"
      - "Write quality content"
      - "Include contextual links"

    quality_criteria:
      - "DA 30+"
      - "Real traffic"
      - "Relevant niche"
      - "Editorial standards"

  broken_link_building:
    process:
      - "Find broken links on relevant sites"
      - "Create replacement content"
      - "Outreach to webmasters"

  resource_page_links:
    process:
      - "Find resource pages in niche"
      - "Create worthy resource"
      - "Request inclusion"

  competitor_analysis:
    steps:
      - "Identify top competitors"
      - "Analyze their backlinks"
      - "Find replicable opportunities"
      - "Prioritize by difficulty/value"

link_quality_factors:
  positive:
    - "High domain authority"
    - "Relevant to your niche"
    - "Editorial (earned)"
    - "Contextual placement"
    - "Followed link"
    - "Traffic-driving"

  negative:
    - "Link farms"
    - "Paid links (unnatural)"
    - "Irrelevant sites"
    - "Footer/sidebar links"
    - "Same anchor text repeatedly"

SEO Analytics

key_metrics:
  organic_traffic:
    tool: "Google Analytics 4"
    tracking: "Sessions with source/medium = organic"

  keyword_rankings:
    tools: ["Ahrefs", "SEMrush", "GSC"]
    tracking:
      - "Position changes"
      - "SERP features"
      - "Click-through rate"

  domain_authority:
    tools: ["Moz DA", "Ahrefs DR"]
    tracking: "Monthly trend"

  core_web_vitals:
    tool: "Google Search Console"
    tracking: "Pass/fail status"

  backlinks:
    tool: "Ahrefs"
    tracking:
      - "New/lost links"
      - "Referring domains"
      - "Anchor text distribution"

  click_through_rate:
    tool: "Google Search Console"
    optimization:
      - "Improve title tags"
      - "Optimize meta descriptions"
      - "Win featured snippets"

reporting:
  weekly:
    - "Ranking changes"
    - "Traffic anomalies"
    - "New backlinks"

  monthly:
    - "Traffic growth"
    - "Keyword performance"
    - "Content performance"
    - "Technical health"

  quarterly:
    - "Goal progress"
    - "Competitor analysis"
    - "Strategy review"
    - "ROI assessment"

Algorithm Factors

ranking_factors:
  content:
    - "Quality and depth"
    - "Relevance to query"
    - "Freshness"
    - "E-E-A-T signals"
    - "User satisfaction"

  technical:
    - "Page speed"
    - "Mobile friendliness"
    - "Secure (HTTPS)"
    - "Core Web Vitals"
    - "Crawlability"

  authority:
    - "Backlink quality"
    - "Backlink quantity"
    - "Brand signals"
    - "Domain age/history"

  user_signals:
    - "Click-through rate"
    - "Dwell time"
    - "Bounce rate"
    - "Pogo-sticking"

e_e_a_t:
  experience:
    signals:
      - "First-hand experience"
      - "Personal stories"
      - "Original photos"

  expertise:
    signals:
      - "Author credentials"
      - "Depth of content"
      - "Accuracy"

  authoritativeness:
    signals:
      - "Backlinks from authorities"
      - "Brand mentions"
      - "Industry recognition"

  trustworthiness:
    signals:
      - "HTTPS"
      - "Clear contact info"
      - "Privacy policy"
      - "No deceptive practices"

Tools Stack

seo_tools:
  keyword_research:
    - "Ahrefs"
    - "SEMrush"
    - "Google Keyword Planner"
    - "Ubersuggest"

  rank_tracking:
    - "Ahrefs Rank Tracker"
    - "SEMrush Position Tracking"
    - "AccuRanker"

  technical:
    - "Screaming Frog"
    - "Sitebulb"
    - "Google Search Console"
    - "PageSpeed Insights"

  backlinks:
    - "Ahrefs"
    - "Majestic"
    - "Moz Link Explorer"

  content:
    - "Clearscope"
    - "Surfer SEO"
    - "MarketMuse"

  analytics:
    - "Google Analytics 4"
    - "Google Search Console"

Лучшие практики

  1. User first — оптимизируй для людей, не только для роботов
  2. Quality content — уникальный, полезный контент
  3. Technical foundation — быстрый, мобильный, доступный сайт
  4. Earn links — качество важнее количества
  5. Track everything — данные для решений
  6. Stay updated — алгоритмы меняются

平台分布

Codex

34.17%
按下载量换算369

Claude

29.29%
按下载量换算316

Cursor

19.02%
按下载量换算205

Gemini CLI

9.13%
按下载量换算99

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

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。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