Security
Read the complete source ↗
geo-platform-optimizer
Platform-specific AI search optimization — audit and optimize for Google AI Overviews, ChatGPT, Perplexity, Gemini, and Bing Copilot individually
geo-seo-claude · Static checks on file
Installation
Read the source and dependencies before running a command. Copying does not install or execute anything.
npx skills add TheSmokeDev/geo-skills --skill geo-platform-optimizerAbout this skill
name: geo-platform-optimizer description: Platform-specific AI search optimization — audit and optimize for Google AI Overviews, ChatGPT, Perplexity, Gemini, and Bing Copilot individually metadata: version: "1.0.0" author: geo-seo-claude tags: [geo, ai-search, platform-optimization, chatgpt, perplexity, gemini, aio]
GEO Platform Optimizer
Core Insight
Only 11% of domains are cited by BOTH ChatGPT and Google AI Overviews for the same query. Each AI search platform uses different indexes, ranking logic, and source preferences. A page optimized for Google AI Overviews may be invisible to ChatGPT, and vice versa. Platform-specific optimization is not optional — it is the foundation of any serious GEO strategy.
How to Use This Skill
- Collect the target URL and the site's primary topic/industry
- Run each platform checklist below against the site
- Score each platform on the 0-100 rubric
- Generate GEO-PLATFORM-OPTIMIZATION.md with per-platform scores, gaps, and action items
Platform 1: Google AI Overviews (AIO)
How AIO Selects Sources
- Only 38% of AIO-cited URLs rank in the organic top 10 — down from 76% (Ahrefs, 863K SERPs / 4M URLs, Mar 2026). 31% of citations come from positions 11-100 and 31% from beyond position 100. The cause is Gemini 3 (Jan 2026) query fan-out pulling from sub-query SERPs — page-3 organic is NOT disqualifying
- Fan-out coverage is the new meta-factor (Zyppy scores it 9.3/10, Jun 2026): engines rewrite one prompt into a cluster of sub-queries and retrieve per sub-query. Win the cluster, not the head term
- AIO strongly favors pages with clean structure, direct answers, and scannable formatting
- Featured snippet optimization has meaningful overlap with AIO optimization
- AIO prefers concise, factual, unambiguous answers — hedging and filler reduce citation probability
- Google AI Mode is a separate surface, not a bigger AIO: AIO↔AI Mode URL overlap is only 13.7%, and AI Mode has 1B MAU (AIO 2.5B) with scarcer citation slots — 4.3 citations per response vs 10.3 in classic search (Shadow, Jul 2026 — ⚠️ secondary source). Optimize for them as distinct targets
2026 Citation Surfaces Beyond the AIO Box
Google's citation real estate now extends beyond AIO and AI Mode themselves:
- Preferred Sources — users can star favorite outlets and get boosted Top Stories placement plus a dedicated "From your sources" section (Google Search blog, Aug 2025, US/India English launch; broader rollout through 2026). This is a Top Stories surface, NOT an AIO mechanism — but for news-adjacent queries it is part of the brand's total Google citation footprint. Earning a user's "preferred" star compounds like a subscription; publishers can link directly to a follow flow.
- "Highly Cited" badges, Community Perspectives, and link carousels — additional in-SERP citation modules attributed to the Google I/O May 2026 announcements. ⚠️ Thin-sourced: this comes from rival skill-pack I/O 2026 notes and we have NOT independently confirmed rollout status or the exact selection mechanics. Treat as watch items — if these modules appear in your SERPs, they are additional extractable surfaces — but do not score them in the rubric until the mechanics are verified.
- Common thread: every new surface still extracts from the same primitives — direct answers, tables, dated authorship, entity clarity. Optimizing the fundamentals covers surfaces that ship faster than any checklist can track.
Optimization Checklist
- Question-Based Headings: Use H2/H3 headings phrased as questions matching real user queries. Check Google's "People Also Ask" for the target topic and mirror those exact phrasings.
- Direct Answer in First Paragraph: After each question heading, provide a clear 1-2 sentence answer immediately. Then expand with supporting detail. The first sentence should be a standalone citation candidate.
- Tables and Structured Comparisons: AIO heavily cites tables. Convert any comparison, pricing, specification, or feature data into HTML tables. Use clear column headers.
- Ordered and Unordered Lists: Step-by-step processes should use ordered lists. Feature lists should use unordered lists. AIO extracts these directly.
- FAQ Sections: Add a dedicated FAQ section with 5-10 real questions. Use proper H3 headings for each question. While FAQPage schema rich results are restricted to govt/health sites since Aug 2023, the content pattern still helps AIO extraction.
- Definitions and Glossary Boxes: For any industry-specific term, provide a clear definition. Format: "[Term] is [concise definition]." AIO frequently cites definitions.
- Statistics with Sources: Include specific numbers with attribution. "According to [Source], [statistic]." AIO prefers citeable, specific claims over vague assertions.
- Publication Date: Include a visible publication date and last-updated date. AIO deprioritizes undated content for time-sensitive queries.
- Author Byline: Display author name with credentials. Link to an author page with bio, credentials, and sameAs links.
- Page Depth: Keep target pages within 3 clicks of homepage. AIO rarely cites deep, orphaned content.
Scoring Rubric (0-100)
| Criterion | Points | How to Score |
|---|---|---|
| Ranks for target queries / covers fan-out sub-queries | 20 | 20 if top 10, 10 if top 100 or strong sub-query coverage, 0 if invisible |
| Question-based headings present | 10 | 2 points per question heading, max 10 |
| Direct answers after headings | 15 | 3 points per direct answer, max 15 |
| Tables present for comparison data | 10 | 10 if tables used appropriately, 5 if partial, 0 if absent |
| Lists for processes/features | 10 | 10 if present, 5 if partial |
| FAQ section with 5+ questions | 10 | 10 if 5+, 5 if 1-4, 0 if none |
| Statistics with citations | 10 | 2 points per cited stat, max 10 |
| Publication/updated date visible | 5 | 5 if both dat |