aeo-seo-site-audit
starsforks
How to install aeo-seo-site-audit?
yoyothesheep/claude-skills/aeo-seo-site-audit
$npx -y skills add yoyothesheep/claude-skills --skill aeo-seo-site-auditAnalyze webpages for content quality, schema markup completeness, and AEO (Answer Engine Optimization). Designed to complement Ahrefs Site Audit findings.
SKILL.md
| 1 | # AEO & Content Analysis Skill (Ahrefs Complement) |
| 2 | |
| 3 | This skill analyzes content quality, JSON-LD schema validation, and AEO (Answer Engine Optimization) for pages you specify. It complements Ahrefs Site Audit (which handles technical SEO) by focusing on aspects that require content analysis and AI-readiness assessment. |
| 4 | |
| 5 | **Use this skill when Ahrefs Site Audit cannot:** |
| 6 | - Validate JSON-LD schema completeness and correctness |
| 7 | - Assess content quality and depth |
| 8 | - Evaluate how well pages answer user questions directly |
| 9 | - Identify authority/expertise signals |
| 10 | - Recommend AI-friendly content restructuring |
| 11 | - Assess natural language optimization |
| 12 | - Flag citability gaps |
| 13 | |
| 14 | ## When to Use This Skill |
| 15 | |
| 16 | Trigger this skill when the user: |
| 17 | - Has run an Ahrefs Site Audit and wants to go deeper on content |
| 18 | - Asks "why isn't my content ranking for [query]?" |
| 19 | - Wants to "optimize for AI search" or "ChatGPT search" |
| 20 | - Asks "how do I get cited by AI" or "appear in AI overviews" |
| 21 | - Wants to "improve schema markup for content types" |
| 22 | - Asks "how can I make my content more AI-friendly?" |
| 23 | - Wants "content quality analysis" beyond technical SEO |
| 24 | |
| 25 | ## Core Workflow |
| 26 | |
| 27 | Steps 1-2. **[Coordinator]** Gather Input — get URLs, Ahrefs project ID (optional), business context |
| 28 | Steps 3–8. **[Haiku Agents]** Fetch Ahrefs data (if provided) + extract entity/structure signals + crawl pages + content gap analysis |
| 29 | Steps 9–16. **[Sonnet Agent]** Validate schema, assess entity/cluster authority, analyze content quality, prioritize gaps, generate report |
| 30 | |
| 31 | ## Agent Architecture |
| 32 | |
| 33 | ### Coordinator (main Claude) |
| 34 | Handles Steps 1–2: gathers user input and orchestrates the two agents. Passes URLs + Ahrefs project ID to the Haiku agent(s), then passes all Haiku output payloads to the Sonnet agent. |
| 35 | |
| 36 | ### Haiku Research Agents |
| 37 | - One agent per URL, launched in parallel |
| 38 | - One additional agent for the Ahrefs API call (if project ID provided) |
| 39 | - Job: mechanical data extraction only — no analysis or judgment |
| 40 | - Output: structured JSON payload per URL (see Haiku Output Contract section below) |
| 41 | |
| 42 | ### Sonnet Synthesis Agent |
| 43 | - Single agent, runs after all Haiku agents complete |
| 44 | - Receives all Haiku JSON payloads + Ahrefs data |
| 45 | - Job: schema validation, content analysis, gap prioritization, report writing |
| 46 | - Output: final report |
| 47 | --- |
| 48 | |
| 49 | ## Environment Detection |
| 50 | |
| 51 | Before starting the audit, check which tools are available and adjust accordingly: |
| 52 | |
| 53 | | Environment | Tools Available | Schema Inspection | JSON-LD Extraction Method | |
| 54 | |---|---|---|---| |
| 55 | | **Claude Code** (CLI) | `Bash`, `WebFetch`, file I/O | ✅ Full | Use `curl + grep` or Python to extract from raw HTML | |
| 56 | | **Claude Web** | `WebFetch` only | ⚠️ Partial (stripped) | Use `strings` from curl or ask user for Rich Results Test output | |
| 57 | |
| 58 | **Note:** JSON-LD extraction is NOT optional. Audits claiming "no schema found" without explicit JSON-LD extraction attempts are incomplete and inaccurate. Always verify schema presence before reporting it as missing. |
| 59 | |
| 60 | ## Critical: Distinguish "Crawlable" from "Indexable" |
| 61 | |
| 62 | ⚠️ **Modern Googlebot executes JavaScript.** A site with empty static HTML (SPA, client-side rendering) may still be indexed by Google. The presence of a `<div id="root"></div>` does NOT mean the site is "not indexed." |
| 63 | |
| 64 | **Crawlable** = Static HTML contains content (good for all crawlers, fastest for Googlebot) |
| 65 | **Indexable** = Google can find and index the content (true even if JS-rendered; Googlebot waits for JS execution) |
| 66 | **Optimal for AI crawlers** = Static HTML with schema markup (most AI answer engines have limited JS execution) |
| 67 | |
| 68 | **Do not conclude a site is "not indexed" based solely on static HTML analysis.** Always verify actual indexing status first (see Step 1 below). |
| 69 | |
| 70 | --- |
| 71 | |
| 72 | ## COORDINATOR |
| 73 | |
| 74 | ## Step 1: Gather Input & Verify Indexing Status |
| 75 | |
| 76 | Ask the user for: |
| 77 | |
| 78 | **Required:** |
| 79 | - **Target URLs or Local Files**: The pages or codebase files to analyze. |
| 80 | - If user provides live URLs: Proceed with the multi-agent web crawling in Steps 2-8. |
| 81 | - If user asks you to audit a local codebase (e.g., within Claude Code): **Skip Steps 2 through 8**. Use your file reading tools to inspect the source files directly, extract schema/structure, and begin your evaluation directly at **Step 9**. |
| 82 | |
| 83 | **⚠️ Before proceeding, verify actual Google indexing status:** |
| 84 | |
| 85 | If user reports the site is "not indexed": |
| 86 | 1. Ask: "Have you checked Google Search Console coverage report?" or "Have you tried `site:yourdomain.com` in Google search?" |
| 87 | 2. If uncertain, recommend they verify using: |
| 88 | - Google Search Console (Coverage > Indexed pages) |
| 89 | - `site:yourdomain.com` search operator |
| 90 | - Google's URL Inspection tool (one specific URL) |
| 91 | 3. **Do not assume** a site is unindexed based on static HTML analysis alone. Modern Googlebot executes JavaScript and can index SPAs. |
| 92 | 4. If the site is |
People who liked this also viewed
6 picksType
- seo-auditWhen the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tagSkillsJul 2026
- copywritingWhen the user wants to write, rewrite, or improve marketing copy for any page — including homepage, landing pages, pricing pages, feature pages, about pages, or product pages. Also use when the user sSkillsJul 2026
- marketing-psychologyWhen the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'mental models,' 'cognitive bias,' 'persuasion,'SkillsJul 2026
- content-strategyWhen the user wants to plan a content strategy, decide what content to create, or figure out what topics to cover. Also use when the user mentions "content strategy," "what should I write about," "conSkillsJul 2026
- programmatic-seoWhen the user wants to create SEO-driven pages at scale using templates and data. Also use when the user mentions "programmatic SEO," "template pages," "pages at scale," "directory pages," "location pSkillsJul 2026
- marketing-ideasWhen the user needs marketing ideas, inspiration, or strategies for their SaaS or software product. Also use when the user asks for 'marketing ideas,' 'growth ideas,' 'how to market,' 'marketing stratSkillsJul 2026
