search-page-audit
Use this skill to run a scored 38-point audit of a URL covering SEO fundamentals, content structure, AI-search/GEO readiness, and E-E-A-T signals. Trigger it when auditing a page, diagnosing search visibility, reviewing content before publication, or prioritizing SEO and AI-search fixes.
superamped · 已有静态检查记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add superamped/ai-marketing-skills --skill search-page-audit技能说明
name: search-page-audit description: "Use this skill to run a scored 38-point audit of a URL covering SEO fundamentals, content structure, AI-search/GEO readiness, and E-E-A-T signals. Trigger it when auditing a page, diagnosing search visibility, reviewing content before publication, or prioritizing SEO and AI-search fixes." license: MIT compatibility: "Requires internet access to fetch URLs, robots.txt, sitemap.xml, and llms.txt" metadata: author: superamped version: "1.0" website: "https://superamped.com"
Search Audit
Usage
Ask your AI tool to audit a URL for search and AI readiness. You can optionally request a focus area — seo-only, geo-only, eeat-only, or content-only.
Process
Step 1: Fetch & Parse
Fetch the page at the provided URL. Extract:
- Full HTML source (for schema, meta tags, heading structure)
- Rendered page content (for content evaluation)
Then fetch these three files from the same domain:
{domain}/robots.txt— check for AI crawler directives{domain}/sitemap.xml— check for existence{domain}/llms.txt— check for existence
Step 2: SEO Fundamentals (10 checks)
Evaluate traditional SEO hygiene. These are prerequisites — if broken, nothing else matters.
- HTTPS — Page is served over HTTPS
- Title tag — Exists, 50-60 characters, descriptive
- Meta description — Exists, 150-160 characters, includes target intent
- Single H1 — Exactly one H1 tag present
- Heading hierarchy — Logical order (H1 > H2 > H3), no skipped levels, no empty headings
- Image alt text — All images have descriptive alt attributes
- Clean URL — Descriptive, readable, no excessive parameters
- Internal links — Links to and from related pages on the site
- Crawlable content — Key content in standard HTML, not hidden behind JavaScript rendering
- Page speed — No obvious performance issues (heavy uncompressed images, render-blocking scripts, excessive DOM size)
Step 3: Content Structure (10 checks)
Evaluate how well the content is structured for both human readers and AI extraction.
- Direct answer up front — Each section leads with the key insight in the first 1-2 sentences
- Question-based headings — H2s/H3s mirror how users phrase queries (What is..., How do I..., Why does...)
- Short paragraphs — 2-4 sentences per paragraph, no wall-of-text blocks
- FAQ section — Dedicated Q&A section with real customer/user questions, 1-3 sentence answers
- Comparison tables — Side-by-side content uses tables (35% higher AI extractability)
- Lists for structure — Numbered lists for processes, bullet points for features/options
- "[TERM] is..." definitions — Key concepts defined with at least two defining sentences
- Conversational keywords — 5+ natural, long-tail query variations woven into content
- Intent clusters — Covers related follow-up questions a user would likely ask next
- Multimedia — Images, video, or infographics present as content signals
Step 4: AI & GEO Readiness (10 checks)
Evaluate technical signals that determine whether AI systems can find, extract, and cite this page.
- AI crawler access — robots.txt does not block GPTBot, ClaudeBot, or other AI user agents
- llms.txt exists — Domain has an llms.txt file communicating AI crawling policies
- Organization schema — JSON-LD with @type Organization present (site-wide entity definition)
- Article/Page schema — Appropriate JSON-LD for the content type (Article, HowTo, Product) with dateModified
- FAQPage schema — Separate FAQPage JSON-LD if FAQ section exists
- Author schema — Author entity linked in structured data
- BreadcrumbList schema — JSON-LD clarifying site hierarchy
- Schema validates — All structured data passes validation (well-formed JSON, no errors)
- Mobile responsive — Content readable and functional across screen sizes
- Sitemap inclusion — Domain has a sitemap.xml and it's accessible
Step 5: E-E-A-T & Authority (8 checks)
Evaluate trust signals that determine whether AI systems choose to cite this page over competitors.
- Author identified — Content has a named author, not "admin" or anonymous
- Author bio present — Author bio with credentials, expertise, and link to author page
- Author page exists — Dedicated author page with full credentials, external profiles, and publication history
- Sources cited — Key claims backed by specific data points with clear attribution
- Original data or insight — Contains first-party research, proprietary analysis, or unique expert perspective
- Freshness signals — Publication date and/or last-updated date visible on page
- Trust pages accessible — Privacy policy, terms, and relevant compliance pages exist and are linked
- About page with entity info — About Us/About page clearly defines the business entity
Output Format
Present the report in this exact structure:
# Page Audit Report
**URL:** [url]
**Date:** [current date]
**Overall Score:** X/38
---
## SEO Fundamentals (X/10)
✓/✗ HTTPS
✓/✗ Title tag — [note: actual title, character count]
✓/✗ Meta description — [note: actual description, character count]
✓/✗ Single H1
✓/✗ Heading hierarchy
✓/✗ Image alt text — [note: X of Y images have alt text]
✓/✗ Clean URL
✓/✗ Internal links
✓/✗ Crawlable content
✓/✗ Page speed
## Content Structure (X/10)
✓/✗ Direct answer up front
✓/✗ Question-based headings
✓/✗ Short paragraphs
✓/✗ FAQ section
✓/✗ Comparison tables
✓/✗ Lists for structure
✓/✗ "[TERM] is..." definitions
✓/✗ Conversational keywords
✓/✗ Intent clusters
✓/✗ Multimedia
## AI & GEO Readiness (X/10)
✓/✗ AI crawler access — [note: which crawlers blocked/allowed]
✓/✗ llms.txt
✓/✗ Organization schema
✓/✗ Article/Page schema — [note: type found, dateModified present?]
✓/✗ FAQPage schema
✓/✗ Author schema
✓/✗ BreadcrumbList schema
✓/✗ Schema valid
阅读完整来源 ↗