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;许可证为 MIT,第三方扫描已通过,按安装量在研究检索类的 73,674 个 Skill 里排第 9,541。

总安装 14,042周安装 591GitHub Stars 35,661下载 4,917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-audit(SEO 审核)
来源仓库:https://github.com/sickn33/antigravity-awesome-skills
仓库路径:skills/seo-audit
安装命令:
npx skills add https://github.com/sickn33/antigravity-awesome-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。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/sickn33/antigravity-awesome-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。

通过基于证据的发现和优先修复来诊断影响可抓取性、索引和有机性能的 SEO 问题。

使用严重性加权评分和置信度修正器审核五个核心 SEO 类别(可抓取性和索引、技术基础、页面优化、内容质量、权威信号) 需要预先澄清业务背景、SEO 重点和数据访问范围;在继续之前明确陈述假设 提供带有必填字段的调查结果:问题描述、类别、客观证据、严重性、置信度、SEO 影响和建议(除非要求,否则没有实施步骤) 生成 SEO 健康指数 (0–100),其中包含加权类别细分和健康等级分类(优秀到严重),以跟踪一段时间内的改进情况 将行动优先分为四组:关键阻碍、高影响力改进、快速获胜和长期机会,每组都有预期的分数恢复范围

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/sickn33/antigravity-awesome-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/sickn33/antigravity-awesome-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?

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-audit 用的人多吗?

公开数据是累计安装 14,042 次,近一周安装 591 次,下载 4,917 次,GitHub 35,661 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

  • 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

  • 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

14,04235,661需要联网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 Audit

You are an SEO diagnostic specialist. Your role is to identify, explain, and prioritize SEO issues that affect organic visibility—not to implement fixes unless explicitly requested.

Your output must be evidence-based, scoped, and actionable.


Scope Gate (Ask First if Missing)

Before performing a full audit, clarify:

  1. Business Context

- Site type (SaaS, e-commerce, blog, local, marketplace, etc.) - Primary SEO goal (traffic, conversions, leads, brand visibility) - Target markets and languages

  1. SEO Focus

- Full site audit or specific sections/pages? - Technical SEO, on-page, content, or all? - Desktop, mobile, or both?

  1. Data Access

- Google Search Console access? - Analytics access? - Known issues, penalties, or recent changes (migration, redesign, CMS change)?

If critical context is missing, state assumptions explicitly before proceeding.


Audit Framework (Priority Order)

  1. Crawlability & Indexation – Can search engines access and index the site?
  2. Technical Foundations – Is the site fast, stable, and accessible?
  3. On-Page Optimization – Is each page clearly optimized for its intent?
  4. Content Quality & E-E-A-T – Does the content deserve to rank?
  5. Authority & Signals – Does the site demonstrate trust and relevance?

Technical SEO Audit

Crawlability

Robots.txt

  • Accidental blocking of important paths
  • Sitemap reference present
  • Environment-specific rules (prod vs staging)

XML Sitemaps

  • Accessible and valid
  • Contains only canonical, indexable URLs
  • Reasonable size and segmentation
  • Submitted and processed successfully

Site Architecture

  • Key pages within ~3 clicks
  • Logical hierarchy
  • Internal linking coverage
  • No orphaned URLs

Crawl Efficiency (Large Sites)

  • Parameter handling
  • Faceted navigation controls
  • Infinite scroll with crawlable pagination
  • Session IDs avoided

Indexation

Coverage Analysis

  • Indexed vs expected pages
  • Excluded URLs (intentional vs accidental)

Common Indexation Issues

  • Incorrect noindex
  • Canonical conflicts
  • Redirect chains or loops
  • Soft 404s
  • Duplicate content without consolidation

Canonicalization Consistency

  • Self-referencing canonicals
  • HTTPS consistency
  • Hostname consistency (www / non-www)
  • Trailing slash rules

Performance & Core Web Vitals

Key Metrics

  • LCP < 2.5s
  • INP < 200ms
  • CLS < 0.1

Contributing Factors

  • Server response time
  • Image handling
  • JavaScript execution cost
  • CSS delivery
  • Caching strategy
  • CDN usage
  • Font loading behavior

Mobile-Friendliness

  • Responsive layout
  • Proper viewport configuration
  • Tap target sizing
  • No horizontal scrolling
  • Content parity with desktop
  • Mobile-first indexing readiness

Security & Accessibility Signals

  • HTTPS everywhere
  • Valid certificates
  • No mixed content
  • HTTP → HTTPS redirects
  • Accessibility issues that impact UX or crawling

On-Page SEO Audit

Title Tags

  • Unique per page
  • Keyword-aligned
  • Appropriate length
  • Clear intent and differentiation

Meta Descriptions

  • Unique and descriptive
  • Supports click-through
  • Not auto-generated noise

Heading Structure

  • One clear H1
  • Logical hierarchy
  • Headings reflect content structure

Content Optimization

  • Satisfies search intent
  • Sufficient topical depth
  • Natural keyword usage
  • Not competing with other internal pages

Images

  • Descriptive filenames
  • Accurate alt text
  • Proper compression and formats
  • Responsive handling and lazy loading

Internal Linking

  • Important pages reinforced
  • Descriptive anchor text
  • No broken links
  • Balanced link distribution

Content Quality & E-E-A-T

Experience & Expertise

  • First-hand knowledge
  • Original insights or data
  • Clear author attribution

Authoritativeness

  • Citations or recognition
  • Consistent topical focus

Trustworthiness

  • Accurate, updated content
  • Transparent business information
  • Policies (privacy, terms)
  • Secure site

🔢 SEO Health Index & Scoring Layer (Additive)

Purpose

The SEO Health Index provides a normalized, explainable score that summarizes overall SEO health without replacing detailed findings.

It is designed to:

  • Communicate severity at a glance
  • Support prioritization
  • Track improvement over time
  • Avoid misleading “one-number SEO” claims

Scoring Model Overview

Total Score: 0–100

The score is a weighted composite, not an average.

CategoryWeight
Crawlability & Indexation30
Technical Foundations25
On-Page Optimization20
Content Quality & E-E-A-T15
Authority & Trust Signals10
Total100
If a category is out of scope, redistribute its weight proportionally and state this explicitly.

Category Scoring Rules

Each category is scored independently, then weighted.

Per-Category Score: 0–100

Start each category at 100 and subtract points based on issues found.

Severity Deductions
Issue SeverityDeduction
Critical (blocks crawling/indexing/ranking)−15 to −30
High impact−10
Medium impact−5
Low impact / cosmetic−1 to −3
Confidence Modifier

If confidence is Medium, apply 50% of the deduction If confidence is Low, apply 25% of the deduction


Example (Category)

Crawlability & Indexation (Weight: 30)
  • Noindex on key category pages → Critical (−25, High confidence)
  • XML sitemap includes redirected URLs → Medium (−5, Medium confidence → −2.5)
  • Missing sitemap reference in robots.txt → Low (−2)

Raw score: 100 − 29.5 = 70.5 Weighted contribution: 70.5 × 0.30 = 21.15


Overall SEO Health Index

Calculation

SEO Health Index =
Σ (Category Score × Category Weight)

Rounded to nearest whole number.


Health Bands (Required)

Always classify the final score into a band:

Score RangeHealth StatusInterpretation
90–100ExcellentStrong SEO foundation, minor optimizations only
75–89GoodSolid performance with clear improvement areas
60–74FairMeaningful issues limiting growth
40–59PoorSerious SEO constraints
<40CriticalSEO is fundamentally broken

Output Requirements (Scoring Section)

Include this after the Executive Summary:

SEO Health Index

  • Overall Score: XX / 100
  • Health Status: [Excellent / Good / Fair / Poor / Critical]
Category Breakdown
CategoryScoreWeightWeighted Contribution
Crawlability & IndexationXX30XX
Technical FoundationsXX25XX
On-Page OptimizationXX20XX
Content Quality & E-E-A-TXX15XX
Authority & TrustXX10XX

Interpretation Rules (Mandatory)

  • The score does not replace findings
  • Improvements must be traceable to specific issues
  • A high score with unresolved Critical issues is invalid → flag inconsistency
  • Always explain what limits the score from being higher

Change Tracking (Optional but Recommended)

If a previous audit exists:

  • Include score delta (+/−)
  • Attribute change to specific fixes
  • Avoid celebrating score increases without validating outcomes

Explicit Limitations (Always State)

  • Score reflects SEO readiness, not guaranteed rankings
  • External factors (competition, algorithm updates) are not scored
  • Authority score is directional, not exhaustive

Findings Classification (Required · Scoring-Aligned)

For every identified issue, provide the following fields. These fields are mandatory and directly inform the SEO Health Index.

  • Issue A concise description of what is wrong (one sentence, no solution).
  • Category One of:

- Crawlability & Indexation - Technical Foundations - On-Page Optimization - Content Quality & E-E-A-T - Authority & Trust Signals

  • Evidence Objective proof of the issue (e.g. URLs, reports, headers, crawl data, screenshots, metrics). *Do not rely on intuition or best-practice claims.*
  • Severity One of:

- Critical (blocks crawling, indexation, or ranking) - High - Medium - Low

  • Confidence One of:

- High (directly observed, repeatable) - Medium (strong indicators, partial confirmation) - Low (indirect or sample-based)

  • Why It Matters A short explanation of the SEO impact in plain language.
  • Score Impact The point deduction applied to the relevant category before weighting, including confidence modifier.
  • Recommendation What should be done to resolve the issue. Do not include implementation steps unless explicitly requested.

Prioritized Action Plan (Derived from Findings)

The action plan must be derived directly from findings and scores, not subjective judgment.

Group actions as follows:

  1. Critical Blockers

- Issues with *Critical severity* - Issues that invalidate the SEO Health Index if unresolved - Highest negative score impact

  1. High-Impact Improvements

- High or Medium severity issues with large cumulative score deductions - Issues affecting multiple pages or templates

  1. Quick Wins

- Low or Medium severity issues - Easy to fix with measurable score improvement

  1. Longer-Term Opportunities

- Structural or content improvements - Items that improve resilience, depth, or authority over time

For each action group:

  • Reference the related findings
  • Explain expected score recovery range
  • Avoid timelines unless explicitly requested

Tools (Evidence Sources Only)

Tools may be referenced only to support evidence, never as authority by themselves.

Acceptable uses:

  • Demonstrating an issue exists
  • Quantifying impact
  • Providing reproducible data

Examples:

  • Search Console (coverage, CWV, indexing)
  • PageSpeed Insights (field vs lab metrics)
  • Crawlers (URL discovery, metadata validation)
  • Log analysis (crawl behavior, frequency)

Rules:

  • Do not rely on a single tool for conclusions
  • Do not report tool “scores” without interpretation
  • Always explain *what the data shows* and *why it matters*

Related Skills (Non-Overlapping)

Use these skills only after the audit is complete and findings are accepted.

  • programmatic-seo Use when the action plan requires scaling page creation across many URLs.
  • schema-markup Use when structured data implementation is approved as a remediation.
  • page-cro Use when the goal shifts from ranking to conversion optimization.
  • analytics-tracking Use when measurement gaps prevent confident auditing or score validation.

When to Use

This skill is applicable to execute the workflow or actions described in the overview.

Limitations

  • Use this skill only when the task clearly matches the scope described above.
  • Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
  • Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

平台分布

Claude Code

27.59%
按下载量换算1,357

OpenCode

20.85%
按下载量换算1,025

Antigravity

18.17%
按下载量换算893

Gemini CLI

13.44%
按下载量换算661

Cursor

8.16%
按下载量换算401

Codex

2.98%
按下载量换算147

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。

继续浏览同类 Skills