Token导航 LogoToken导航

Agent Skill · 研究检索

seo-specialist(SEO specialist 搜索)

seo-specialist 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-specialist 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,权限为执行命令;许可证为 MIT,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 28,881。

总安装 3,144周安装 132GitHub Stars 76下载 1,045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:seo-specialist(SEO specialist 搜索)
来源仓库:https://github.com/404kidwiz/claude-supercode-skills
仓库路径:skills/seo-specialist
安装命令:
npx skills add https://github.com/404kidwiz/claude-supercode-skills --skill seo-specialist
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/404kidwiz/claude-supercode-skills --skill seo-specialist

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-specialist 专注搜索引擎优化,提供技术审计与内容策略建议。适用于站点结构优化、关键词研究与竞争对手差距分析等任务。支持 Schema 标记部署与索引问题诊断,助力提升自然流量。

安装方式:npx skills add https://github.com/404kidwiz/claude-supercode-skills --skill seo-specialist 涉及网站配置变更时应先备份,并在测试环境验证后再上线执行。

来源仓库内路径:skills/seo-specialist

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/404kidwiz/claude-supercode-skills --skill seo-…;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

    它需要执行命令,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-specialist 怎么安装?

在终端执行 npx skills add https://github.com/404kidwiz/claude-supercode-skills --skill seo-specialist。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

seo-specialist 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-specialist 需要什么权限?

权限级别是执行命令。安装流程涉及命令执行,可能通过 npx skills add https://github.com/404kidwiz/claude-supercode-skills --skill seo-specialist;npx skills add 404kidwiz/claude-supercode-skills --skill "seo-specialist" 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

seo-specialist 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。

seo-specialist 用的人多吗?

公开数据是累计安装 3,144 次,近一周安装 132 次,下载 1,045 次,GitHub 76 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-specialist 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。
  • 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。
  • 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

  • 需要执行命令,装到常用环境前要先评估影响面。
  • 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。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 不能接受 Skill 在你机器上执行命令的人。
  • 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-specialist

SEO specialist 搜索 · 本页

3,14476执行命令MIT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 Specialist

Purpose

Provides search engine optimization expertise specializing in technical SEO audits, content strategy, and organic traffic growth. Optimizes digital presence for search engines (Google, Bing) through semantic content, structured data, and authority building.

When to Use

  • Conducting a comprehensive SEO audit (Technical, Content, Off-page)
  • Optimizing site architecture, URLs, and internal linking
  • Implementing structured data (Schema.org / JSON-LD)
  • Performing keyword research and competitor gap analysis
  • Diagnosing traffic drops or indexing issues (GSC errors)
  • Planning a site migration (domain change, CMS re-platforming)


2. Decision Framework

SEO Priority Matrix

Where to focus?
│
├─ **Technical SEO** (Foundation) - *Fix First*
│  │
│  ├─ Crawlability? → **Robots.txt, Sitemap, Status Codes**
│  ├─ Indexability? → **Noindex tags, Canonicals**
│  └─ Performance? → **Core Web Vitals (LCP, CLS, INP)**
│
├─ **On-Page SEO** (Relevance) - *Fix Second*
│  │
│  ├─ Content? → **Keyword Targeting, E-E-A-T, Freshness**
│  ├─ Structure? → **Headings (H1-H6), Title Tags, Meta Desc**
│  └─ UX? → **Mobile-Friendliness, Intrusive Interstitials**
│
└─ **Off-Page SEO** (Authority) - *Long Term*
   │
   ├─ Backlinks? → **Digital PR, Guest Posting, Outreach**
   ├─ Brand? → **Social Signals, Brand Mentions**
   └─ Local? → **Google Business Profile, Citations**

Keyword Strategy

Intent TypeExample QueryContent FormatPriority
Informational"How to fix sink"Blog Post / Guide / VideoTop Funnel (Awareness)
Navigational"Home Depot login"Homepage / Login PageBrand Defense
Commercial"Best wrench set"Comparison / Review / ListicleMid Funnel (Consideration)
Transactional"Buy 10mm socket"Product Page / Category PageBottom Funnel (Conversion)

Red Flags → Escalate to frontend-developer or devops-engineer:

  • Website built entirely in client-side JavaScript (SPA) without SSR/Prerendering (SEO disaster)
  • Server response times (TTFB) > 2 seconds consistently
  • Hundreds of thousands of 404/500 errors
  • Security hacks or malware injections


3. Core Workflows

Workflow 1: Technical SEO Audit

Goal: Identify and fix technical blockers preventing indexing.

Steps:

  1. Crawl Analysis (Screaming Frog / Lumar)

- Run a full site crawl. - Filter by: - Status Codes: 4xx (Broken links), 5xx (Server errors). - Directives: Noindex, Nofollow, Canonicalized URLs. - Structure: Missing H1s, Duplicate Title Tags.

  1. Indexability Check (Google Search Console)

- Check "Pages" report. - Identify "Crawled - currently not indexed" (Quality issue?) vs "Discovered - currently not indexed" (Budget issue?). - Verify XML Sitemap submission.

  1. Performance Check (PageSpeed Insights)

- Analyze Core Web Vitals. - LCP (Loading): Target < 2.5s. - INP (Interactivity): Target < 200ms. - CLS (Stability): Target < 0.1.

  1. Remediation Plan

- Create Jira tickets for devs: "Fix 404s in nav menu", "Implement lazy loading for images".



Workflow 4: Content Pruning & Optimization

Goal: Improve site authority by removing or updating low-quality content.

Steps:

  1. Audit (GSC + Analytics)

- Identify pages with 0 clicks in last 12 months. - Identify pages with high bounce rate (> 90%) and low time on page (< 10s).

  1. Decision Matrix

- Keep & Optimize: Relevant topic, but poor content. Action: Rewrite. - Merge: Duplicate topics (e.g., "Best Shoes 2023" vs "Best Shoes 2024"). Action: 301 to newest. - Delete: Irrelevant/Outdated (e.g., "Christmas Party 2018"). Action: 410 Gone (or 301 if relevant category exists).

  1. Execution

- Update content with fresh data/examples. - Implement 301s. - Remove internal links to deleted pages.

  1. Submission

- Submit updated sitemap to GSC.



Workflow 6: Programmatic SEO

Goal: Create 1,000+ landing pages for "Best X for Y" at scale.

Steps:

  1. Database Creation (Airtable/Google Sheets)

- Columns: Location, Industry, Tool Type. - Rows: "CRM for Real Estate", "CRM for Dentists", "CRM for Startups".

  1. Template Design

- H1: "Best CRM Software for {Industry} in 2024" - Intro: Specific pain points of {Industry}. - Feature list: Filtered by relevance.

  1. Generation (Webflow / WordPress)

- Use CMS Collection pages. - Inject variables. - Quality Control: Manually review top 20 pages. Ensure unique value in intro.



5. Anti-Patterns & Gotchas

❌ Anti-Pattern 1: Keyword Stuffing (The "Dinosaur" Tactic)

What it looks like:

  • "We sell cheap shoes. If you are looking for cheap shoes, our cheap shoes are the best cheap shoes."
  • Hidden text (white text on white background).

Why it fails:

  • Google's Panda algorithm penalizes this heavily.
  • User experience is terrible → High Bounce Rate → Lower Rankings.

Correct approach:

  • Write naturally for the user.
  • Use synonyms and LSI (Latent Semantic Indexing) keywords (e.g., "affordable footwear", "budget sneakers", "footwear deals").
  • Focus on "Topic Coverage" rather than keyword density.

❌ Anti-Pattern 2: Buying Backlinks (Black Hat)

What it looks like:

  • Paying $50 to a shady site to link to you.
  • Private Blog Networks (PBNs).
  • Comment spamming.

Why it fails:

  • Google's Penguin algorithm penalizes unnatural link profiles.
  • Risk of Manual Action (de-indexing) which can kill a business overnight.

Correct approach:

  • Create "Linkable Assets" (Original data, Infographics, Free Tools).
  • Digital PR (News, Expert quotes via HARO).
  • Guest posting on reputable, relevant industry sites.

❌ Anti-Pattern 3: Blocking JavaScript (The "Empty Shell")

What it looks like:

  • Site content is loaded via AJAX/Fetch *after* page load.
  • Source code (View Source) shows an empty div id="app".
  • Content is visible to user but invisible to bots (or delayed).

Why it fails:

  • Googlebot *can* render JS, but it's slower (Deferral Queue) and unreliable.
  • Other bots (Bing, Facebook, Twitter/X) often fail completely.
  • "Text to Code Ratio" is near zero.

Correct approach:

  • Server-Side Rendering (SSR): Next.js, Nuxt.
  • Static Site Generation (SSG): Gatsby, Astro.
  • Dynamic Rendering: Serve static HTML to bots, JS to users (complex setup).
  • Hydration: Send HTML first, then attach JS interactions.

❌ Anti-Pattern 4: The "Soft 404" Trap

What it looks like:

  • Redirecting deleted product pages to the Homepage.
  • Showing a "Page Not Found" message but returning a 200 OK status code.

Why it fails:

  • Confuses Googlebot (thinks the homepage *is* the product page).
  • Frustrates users (they expected a specific product).

Correct approach:

  • 301 Redirect to the most relevant *category* or *similar product*.
  • If no relevant page exists, serve a 410 Gone (tells Google to remove it faster than 404).
  • Custom 404 page with search bar and popular links.


7. Quality Checklist

Technical Foundation:

  • HTTPS: Site is secure (SSL certificate valid).
  • Mobile: Pass Google's Mobile-Friendly Test (Responsive design).
  • Speed: LCP < 2.5s, CLS < 0.1, INP < 200ms (Core Web Vitals).
  • Indexing: No critical pages blocked by robots.txt or noindex tag.
  • Sitemap: Clean XML sitemap (no 404s/redirects) submitted to GSC.
  • Canonicals: Self-referencing canonicals on all pages to prevent duplication.

On-Page Elements:

  • Title Tags: Unique, keyword-optimized, < 60 chars (no truncation).
  • H1: Exactly one H1 per page, includes primary keyword.
  • Images: Compressed (WebP), includes descriptive alt text with keywords.
  • URLs: Short, descriptive, lowercase, hyphens (not underscores), no query strings if possible.
  • Internal Links: 2-5 internal links to other relevant content per post.

Off-Page & Authority:

  • Profile: Google Business Profile claimed, verified, and 100% completed (if local).
  • Links: Backlink profile audit conducted (disavow toxic links if manual action risk).
  • Social: Open Graph (OG) and Twitter Card tags configured for rich sharing.
  • Citations: NAP (Name, Address, Phone) consistent across all directories.

Anti-Patterns

Technical SEO Anti-Patterns

  • JavaScript Rendering Issues: Content loaded via JS not indexed - use SSR/SSG
  • Slow Page Speed: Core Web Vitals failing - optimize images, code, and caching
  • Duplicate Content: Multiple URLs serving same content - implement canonical tags
  • Broken Links: 404 errors wasting crawl budget - regular link audits and fixes

Content Anti-Patterns

  • Keyword Stuffing: Overusing keywords unnaturally - write for users, not bots
  • Thin Content: Pages with little value - provide comprehensive information
  • Ignoring User Intent: Content misaligned with search intent - understand user needs
  • Content Staleness: Outdated content not updated - refresh content regularly

Link Building Anti-Patterns

  • Paid Links: Buying links to manipulate rankings - earn links naturally
  • Link Schemes: Manipulative link patterns - avoid PBNs and spam
  • Broken Redirects: Redirect chains wasting crawl budget - direct redirects
  • Anchor Text Over-Optimization: Unnatural anchor text - diversify anchor text

Migration Anti-Patterns

  • URL Chaos: Changing URLs without redirects - preserve URL structure
  • Content Loss: Moving content without preserving it - maintain content inventory
  • Indexation Issues: Wrong pages indexed - control indexation properly
  • Traffic Drop: Not monitoring post-migration - set up monitoring

平台分布

Claude Code

27.79%
按下载量换算290

OpenCode

22.72%
按下载量换算237

Codex

20.49%
按下载量换算214

Gemini CLI

13.49%
按下载量换算141

Cursor

8.6%
按下载量换算90

Antigravity

3.28%
按下载量换算34

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

执行命令

安装流程涉及命令执行,可能通过 npx skills add https://github.com/404kidwiz/claude-supercode-skills --skill seo-specialist;npx skills add 404kidwiz/claude-supercode-skills --skill "seo-specialist" 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

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。

继续浏览同类 Skills