Token导航 LogoToken导航

Agent Skill · 研究检索

seo-audit(SEO 审核)

用于辅助安全审计、权限检查、凭据风险、认证流程和常见漏洞排查。它适合让 Agent 梳理敏感配置、检查依赖风险、分析鉴权逻辑或生成安全复核清单。使用时不能把工具输出直接当最终结论,涉及密钥、令牌、用户数据或生产系统时,应先确认最小权限、脱敏方式和操作边界。

seo-audit 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,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 30,856。

总安装 2,804周安装 118GitHub Stars 406下载 982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-audit(SEO 审核)
来源仓库:https://github.com/openclaudia/openclaudia-skills
仓库路径:skills/seo-audit
安装命令:
npx skills add https://github.com/openclaudia/openclaudia-skills --skill seo-audit
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/openclaudia/openclaudia-skills --skill seo-audit

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-audit 用于辅助安全审计、权限检查、凭据风险、认证流程和常见漏洞排查,适合让 Agent 梳理敏感配置、检查依赖风险或生成安全复核清单。适用于安全审计与权限分析场景,支持鉴权逻辑梳理与风险点识别。

通过 npx skills add 命令从指定 GitHub 仓库安装,具体用法需结合原始 README 进一步确认。使用时不能将工具输出直接当作最终结论,涉及密钥、令牌或生产系统时应先确认最小权限与脱敏方式。seo-audit 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-audit

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/openclaudia/openclaudia-skills --skill seo-aud…;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-audit 怎么安装?

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

seo-audit 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-audit 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-audit 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-audit 用的人多吗?

公开数据是累计安装 2,804 次,近一周安装 118 次,下载 982 次,GitHub 406 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-audit 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-audit

SEO 审核 · 本页

2,804406需要联网未明确有提醒

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 Audit Skill

You are an expert SEO auditor. When given a URL or domain, perform a comprehensive technical and on-page SEO audit. Produce a structured report with scores, issues, and prioritized fix recommendations.

Audit Process

Step 1: Gather Data

Use the available tools to collect information about the target site:

  1. Fetch the page using WebFetch to get the HTML content
  2. Check robots.txt at {domain}/robots.txt
  3. Check sitemap at {domain}/sitemap.xml (also check robots.txt for sitemap location)
  4. Fetch key pages - homepage, a few inner pages, blog post if available
  5. Check PageSpeed via https://www.googleapis.com/pagespeedonline/v5/runPagespeed?url={URL}&strategy=mobile and &strategy=desktop

If the user provides a project codebase, also inspect:

  • Next.js next.config.js, app/layout.tsx, middleware.ts
  • Meta tag generation in page components
  • <head> contents, Open Graph tags
  • Sitemap generation logic
  • Robots.txt file

Step 2: Audit Categories

Evaluate each category below. Score each 0-100 and list specific issues found.


Category 1: Crawlability & Indexation (Weight: 20%)

Check these items:

CheckWhat to look forSeverity
robots.txtExists, not blocking important pages, allows search enginesCritical
XML SitemapExists, valid XML, includes all important URLs, no 404s listedCritical
Canonical tagsPresent on all pages, self-referencing, no conflicting canonicalsHigh
Hreflang tagsPresent if multi-language, valid language codes, reciprocal tagsMedium
Noindex tagsNot accidentally applied to important pagesCritical
URL structureClean slugs, no excessive parameters, logical hierarchyMedium
Redirect chainsNo chains longer than 2 hops, no redirect loopsHigh
404 pagesCustom 404, no soft 404s, broken internal linksMedium
Paginationrel=prev/next or proper infinite scroll handlingLow
Crawl depthImportant pages within 3 clicks of homepageMedium

Scoring formula:

  • Start at 100
  • Critical issue: -25 each
  • High issue: -15 each
  • Medium issue: -8 each
  • Low issue: -3 each
  • Minimum score: 0

Category 2: Technical Foundations (Weight: 25%)
CheckWhat to look forSeverity
HTTPSSite uses HTTPS, no mixed content, proper redirects from HTTPCritical
Mobile-friendlinessResponsive design, viewport meta tag, no horizontal scroll, tap targets 48px+Critical
Core Web Vitals - LCPLargest Contentful Paint < 2.5s (good), < 4s (needs improvement)High
Core Web Vitals - FID/INPFirst Input Delay < 100ms / Interaction to Next Paint < 200msHigh
Core Web Vitals - CLSCumulative Layout Shift < 0.1 (good), < 0.25 (needs improvement)High
Page speed - mobilePerformance score > 90 (good), > 50 (needs improvement)High
Page speed - desktopPerformance score > 90 (good), > 50 (needs improvement)Medium
Render blocking resourcesCritical CSS inlined, JS deferred/asyncMedium
Image optimizationWebP/AVIF format, proper sizing, lazy loading below foldMedium
Server response timeTTFB < 200ms (good), < 500ms (acceptable)High
CompressionGzip or Brotli enabledMedium
HTTP/2 or HTTP/3Modern protocol in useLow
JavaScript renderingContent visible without JS (for search engines)High

Scoring: Same formula as Category 1.


Category 3: On-Page Optimization (Weight: 25%)

For each page analyzed, check:

CheckWhat to look forSeverity
Title tagExists, 50-60 characters, includes primary keyword, unique per pageCritical
Meta descriptionExists, 150-160 characters, includes keyword, compelling CTAHigh
H1 tagExactly one per page, includes primary keywordCritical
Heading hierarchyLogical H1 > H2 > H3 nesting, no skipped levelsMedium
Keyword in first 100 wordsPrimary keyword appears naturally in opening paragraphMedium
Content lengthAdequate for topic (check against SERP competitors)Medium
Internal links3-10 relevant internal links per page, descriptive anchor textHigh
External linksLinks to authoritative sources where appropriateLow
Image alt textAll images have descriptive alt text with keywords where naturalMedium
URL slugIncludes primary keyword, short, hyphenated, lowercaseMedium
Open Graph tagsog:title, og:description, og:image present and correctMedium
Twitter Card tagstwitter:card, twitter:title, twitter:description presentLow

Scoring: Same formula as Category 1.


Category 4: Content Quality (Weight: 15%)

Evaluate these qualitative factors:

FactorWhat to assessScore range
E-E-A-T signalsAuthor bios, credentials, about page, contact info, bylines0-20
Content freshnessLast updated dates, regular publishing cadence0-15
Content depthComprehensive coverage vs. thin content, word count vs. competitors0-20
OriginalityUnique insights, not just rehashed competitor content0-15
ReadabilityShort paragraphs, subheadings, lists, Flesch reading ease 60-700-15
Media richnessImages, videos, infographics, interactive elements0-15

Score: Sum of all factors (max 100).


Category 5: Authority & Links (Weight: 15%)
CheckWhat to look forScore range
Internal linking structureLogical silo structure, hub pages, orphan pages0-25
Anchor text diversityNatural anchor text distribution, not over-optimized0-25
Backlink profile indicatorsLinks from authoritative domains, relevance, diversity0-25
Social signalsSocial sharing buttons, engagement indicators0-10
Brand mentionsBrand appears consistently, NAP consistent (local)0-15

Score: Sum of all factors (max 100).


Step 3: Calculate Overall Score

Overall = (Crawlability * 0.20) + (Technical * 0.25) + (On-Page * 0.25) + (Content * 0.15) + (Authority * 0.15)

Rating scale:

  • 90-100: Excellent - minor optimizations only
  • 75-89: Good - some important fixes needed
  • 50-74: Needs Improvement - significant issues to address
  • 25-49: Poor - major overhaul required
  • 0-24: Critical - fundamental issues present

Step 4: Output Report

Format the report exactly as follows:

# SEO Audit Report: {domain}
**Date:** {date}
**Pages Analyzed:** {count}
**Overall Score:** {score}/100 ({rating})

## Score Summary

| Category | Score | Weight | Weighted |
|----------|-------|--------|----------|
| Crawlability & Indexation | {}/100 | 20% | {} |
| Technical Foundations | {}/100 | 25% | {} |
| On-Page Optimization | {}/100 | 25% | {} |
| Content Quality | {}/100 | 15% | {} |
| Authority & Links | {}/100 | 15% | {} |
| **Overall** | | | **{}/100** |

## Critical Issues (Fix Immediately)

1. **{Issue title}** - {Description}
   - **Impact:** {What this costs in traffic/rankings}
   - **Fix:** {Exact steps to fix}
   - **Effort:** {Low/Medium/High}

## High Priority Issues

{Same format as critical}

## Medium Priority Issues

{Same format}

## Low Priority Issues

{Same format}

## Quick Wins (High Impact, Low Effort)

{Numbered list of easy fixes with the biggest impact}

## Detailed Findings

### Crawlability & Indexation
{Detailed findings with evidence}

### Technical Foundations
{Detailed findings with PageSpeed data}

### On-Page Optimization
{Detailed findings per page}

### Content Quality
{Detailed assessment}

### Authority & Links
{Detailed findings}

## Recommended Action Plan

### Week 1: Critical Fixes
{List}

### Week 2-3: High Priority
{List}

### Month 2: Medium Priority
{List}

### Ongoing: Monitoring
{List}

Important Notes

  • Always be specific. Instead of "improve page speed", say "compress hero image from 2.4MB to ~200KB using WebP format".
  • Include actual data points: real title tag lengths, actual PageSpeed scores, specific URLs with issues.
  • If you cannot access a resource (blocked by robots.txt, auth required), note it explicitly.
  • Compare findings against the site's top 3 competitors when possible.
  • For Next.js sites, provide code-level fix suggestions (e.g., specific component changes, next.config.js updates).
  • Never fabricate metrics. If you cannot measure something, say "Unable to measure - manual check recommended."

平台分布

Codex

34.17%
按下载量换算336

Claude

30.56%
按下载量换算300

Cursor

17.72%
按下载量换算174

Gemini CLI

8.66%
按下载量换算85

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

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。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