本文へ移動
cccskills
無料GitHub で公開

seo-ai-optimization

Audit a site or page against Google's OFFICIAL AI optimization guidance — readiness for AI Overviews and AI Mode, grounded in Google's published ai-optimization-guide and ai-features docs (not third-party GEO theory). Use when user says "AI optimization", "AI Overviews", "AI mode", "AI search readiness", "optimize for AI", or "GEO audit".

インストール方法を見る

含まれるファイル(1)

  • SKILL.md6.7 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Google AI Search Readiness Audit (AI Overviews + AI Mode)

<!-- Updated: 2026-06-10 -->

This skill audits strictly against Google's own guidance: https://developers.google.com/search/docs/fundamentals/ai-optimization-guide and https://developers.google.com/search/docs/appearance/ai-features. For multi-engine GEO (ChatGPT, Perplexity, Bing Copilot), use /seo-geo; for llms.txt generation, use /seo-llms-txt — but note Google's position below.

Core Facts (from Google's docs — anchor every finding here)

  • No special markup is needed. "There are no additional requirements to appear in AI Overviews or AI Mode, nor other special optimizations necessary."
  • Eligibility = indexed + snippet-eligible. A page must be indexed and eligible to be shown in Google Search with a snippet (Search technical requirements). Nothing more — and inclusion is never guaranteed.
  • How the features work: RAG (grounding on the Search index) + query fan-out (concurrent related queries). Core ranking and quality systems decide what gets retrieved and cited — SEO is still the lever.
  • "AEO"/"GEO" = SEO, per Google. Optimizing for generative AI search is optimizing for the search experience.
  • Snippet controls govern AI features: nosnippet, data-nosnippet, max-snippet, and noindex limit what appears in AI Overviews/AI Mode.
  • Google-Extended controls Gemini training and grounding in OTHER Google systems — it does NOT control appearance in AI Overviews or AI Mode. Googlebot in robots.txt is the Search-access control.
  • Measurement: AI Overviews/AI Mode clicks are inside the Search Console Performance report under the "Web" search type (no separate report).

Inputs

  • URL (page-level audit) or domain (site-level audit)
  • Optional: a local content draft (Read tool) for content-quality checks only

Execution

1. Indexability & snippet eligibility (eligibility gate)

curl -sL <url> -o /tmp/ai-audit-page.html -w "%{http_code}\n"
curl -sL <origin>/robots.txt -o /tmp/ai-audit-robots.txt

Check, in order:

  • HTTP 200 and not blocked for Googlebot in robots.txt (also CDN/WAF blocks)
  • No noindex (meta robots or X-Robots-Tag)
  • Snippet/preview controls: nosnippet, max-snippet:[n] (a low value restricts AI feature usage), data-nosnippet spans wrapping main content
  • Google-Extended in robots.txt — report it, but state explicitly: this affects Gemini training/grounding elsewhere, NOT AI Overviews appearance
  • Canonical sanity (page not canonicalized away)

Any failure here = NOT ELIGIBLE for AI features; stop and report the fix.

2. Content value checks (the biggest lever per Google)

Heuristics on the fetched main content:

  • Unique point of view / non-commodity test: first-hand evidence, original data, named experience ("we tested", photos, case numbers) vs. commodity listicle patterns ("7 Tips for...") that restate common knowledge
  • People-first organization: clear paragraphs, sections, descriptive headings that aid navigation
  • Multimodal support: relevant high-quality images/video supporting the text (AI features can surface them)
  • Important content available as text (not locked in images/canvas/video only)
  • Fan-out coverage WITHOUT page proliferation: flag many near-duplicate pages targeting query variations — Google warns this violates the scaled content abuse spam policy and doesn't work
  • If AI-assisted content: must meet Search Essentials + spam policies (see /seo-helpful-content)

3. Technical structure

  • Internal links make the content findable
  • Page experience basics: renders on mobile, main content distinguishable, reasonable latency
  • JavaScript: critical content present in served HTML or properly rendered
  • Duplicate content reduced
  • Semantic HTML where easy — human readability over perfect code

4. Business data consistency (where applicable)

  • Structured data matches the visible text (consistency, not extra schema — Google: "no special schema.org markup you need to add")
  • Ecommerce: Merchant Center feed current; Local: Business Profile current

5. Mythbusting pass

Flag (as wasted effort, per Google's own mythbusting list) if the site is:

  • Relying on llms.txt or "AI text files" for Google visibility (no special treatment — note this when cross-referencing /seo-llms-txt)
  • "Chunking" content into fragments for AI
  • Rewriting copy "for AI" / stuffing long-tail variants (AI systems understand synonyms and meaning)
  • Buying/seeking inauthentic mentions
  • Over-investing in structured data purely for AI features

Output

## Google AI Search Readiness — <URL or domain>

### Eligibility Gate
| Check | Status | Evidence |
|---|---|---|
| Indexed / indexable | PASS/FAIL | ... |
| Googlebot allowed (robots.txt + CDN) | PASS/FAIL | ... |
| No noindex | PASS/FAIL | ... |
| Snippet controls (nosnippet/max-snippet/data-nosnippet) | PASS/WARN | ... |
| Google-Extended present? | INFO | affects Gemini training, NOT AI Overviews |

### AI-Readiness Scorecard (0-100)
| Pillar | Weight | Score | Notes |
|---|---|---|---|
| Indexability & snippet eligibility | 30 | XX | hard gate |
| Unique, non-commodity content | 35 | XX | biggest long-run lever per Google |
| Technical structure & page experience | 20 | XX | ... |
| Multimodal + business data consistency | 15 | XX | ... |

### Wasted-Effort Flags (Google mythbusting)
- ...

### Top 3 Actions
1. ...

Close with: track AI feature traffic in Search Console Performance report ("Web" search type); clicks from AI Overviews tend to be higher quality (longer time on site), per Google.

Cross-references

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

seo

無料

Comprehensive SEO analysis for any website or business type. Orchestrates 52 sub-skills (52 active): full site audits, technical SEO (CWV/INP), schema, E-E-A-T content quality, images, sitemaps, GEO for AI Overviews, llms.txt generation, AI crawler audit, plus live GSC and Ahrefs MCP data. GSC: overview, drops, opportunities, brand-vs-nonbrand, cannibalization, compare, content-decay, index-issues, new-keywords. Ahrefs: overview, backlinks, keywords, competitors, content-gap, broken-links, new-links, anchor-analysis, dr-history, top-pages. Cross-MCP: serp, content-brief, brand-radar, site-audit-pro, report. Local: log-analysis, ai-content-check, internal-links, local, migration-check, obsidian-kb. AI Readability: llms-txt, robots-ai. Performance: lighthouse-audit, core-web-vitals, page-experience. Quality & AI Search: rich-results, ai-optimization, eeat-audit, helpful-content. Triggers on: "SEO", "audit", "schema", "Core Web Vitals", "sitemap", "E-E-A-T", "AI Overviews", "GEO", "technical SEO", "content quality", "structured data", "GSC", "Ahrefs", "backlinks", "keywords", "search console", "domain rating", "local SEO", "migration", "lighthouse", "pagespeed", "LCP", "INP", "CLS", "page experience", "interstitials", "mobile friendly", "rich results", "rich snippets", "schema eligibility", "AI optimization", "AI search readiness", "EEAT", "trust signals", "helpful content", "people-first", "content quality gate".

日本語の概要は準備中です。原文の説明を表示しています。

lionkiii/claude-seo-skills212026年6月11日 更新

Analyze a domain's anchor text distribution from Ahrefs: see the breakdown of anchor text used across all backlinks and assess link profile health. Use when user says "anchor text", "anchor analysis", "anchor distribution", "link anchors", or "anchor text profile".

日本語の概要は準備中です。原文の説明を表示しています。

lionkiii/claude-seo-skills212026年6月11日 更新

Analyze a domain's backlink profile using Ahrefs: see who links to the domain, source Domain Rating, anchor text, link type, and when each link was first seen. Use when user says "Ahrefs backlinks", "backlink profile", "who links to", "link analysis", or "referring pages".

日本語の概要は準備中です。原文の説明を表示しています。

lionkiii/claude-seo-skills212026年6月11日 更新

Find broken backlinks pointing to a domain using Ahrefs: links targeting 404 pages that can be reclaimed. Prioritizes highest-DR lost links for maximum recovery impact. Use when user says "broken backlinks", "broken links", "link reclamation", "dead backlinks", or "404 backlinks".

日本語の概要は準備中です。原文の説明を表示しています。

lionkiii/claude-seo-skills212026年6月11日 更新

Discover a domain's top organic competitors from Ahrefs: competing domains, keyword overlap count, shared keywords, and unique competitor keywords. Use when user says "Ahrefs competitors", "organic competitors", "competing domains", "keyword overlap", or "who competes with".

日本語の概要は準備中です。原文の説明を表示しています。

lionkiii/claude-seo-skills212026年6月11日 更新

Find keywords that competitors rank for but the target domain does not, using Ahrefs data. Reveals content opportunities and topic gaps. Use when user says "content gap", "keywords competitors rank for", "missing keywords", "competitor keywords", or "content gap analysis".

日本語の概要は準備中です。原文の説明を表示しています。

lionkiii/claude-seo-skills212026年6月11日 更新

lionkiii のスキルをすべて見る

このスキルの問題を報告する