ai-seo

Files (4)

• SKILL.md
• content_scorer.py · scripts/
• keyword_analyzer.py · scripts/
• serp_simulator.py · scripts/

SKILL.md (first lines)

# AI SEO

Generative engine optimization (GEO) for getting cited by AI search platforms — not just ranked in traditional results.

---

## Table of Contents

- [Keywords](#keywords)
- [Quick Start](#quick-start)
- [How AI Search Differs from Traditional SEO](#how-ai-search-differs-from-traditional-seo)
- [The Three Pillars of AI Citability](#the-three-pillars-of-ai-citability)
- [Core Workflows](#core-workflows)
- [Content Patterns That Get Cited](#content-patterns-that-get-cited)
- [Schema Markup for AI Discovery](#schema-markup-for-ai-discovery)
- [Bot Access Configuration](#bot-access-configuration)
- [Monitoring and Tracking](#monitoring-and-tracking)
- [Best Practices](#best-practices)
- [Anti-Patterns](#anti-patterns)
- [Integration Points](#integration-points)

---

## Keywords

AI SEO, generative engine optimization, GEO, AI overviews, Google SGE, ChatGPT citations, Perplexity SEO, Claude citations, AI search optimization, semantic search, entity optimization, LLM visibility, AI-generated answers, structured data, schema markup, content extractability, AI citability, GPTBot, PerplexityBot, ClaudeBot, answer engine optimization

---

## Clarify First

Before optimizing, settle the inputs below. When one is missing or vague and would change the result, ask about it; when it wouldn't, use a sensible default and say which one you used.

- **Target queries:** the questions you want to be cited for (drives which pages to optimize and the extractable blocks to add).
- **Target AI platform(s):** Perplexity / ChatGPT / Google AI Overviews / Claude (crawling, indexing, and citation behavior differ per platform).
- **Brand/entity name:** exact wording to track (drives citation testing and entity optimization).
- **The page/content to optimize:** the URL or draft being restructured (drives extractability scoring + schema selection).

Ask about the two or three inputs that matter most for this request, not the whole list. If the user wants a result straight away, produce it and state your assumptions at the top.

## Quick Start

### Run an AI Visibility Audit

1. Check robots.txt for AI bot access — the search/retrieval crawlers first (OAI-SearchBot, Claude-SearchBot, PerplexityBot, Googlebot), then the training crawlers (GPTBot, ClaudeBot, Google-Extended)
2. Test top 10 target queries on Perplexity, ChatGPT, and Google AI Overviews
3. Document which queries cite you, which cite competitors, and what content format wins
4. Score key pages against the Extractability Checklist
5. Prioritize pages with highest gap between search volume and current AI citation presence

### Optimize a Page for AI Citation

1. Add a clear definition block in the first 200 words for informational queries
2. Structure content with self-contained H2 sections that can be extracted independently
3. Add numbered steps for process queries, comparison tables for "X vs Y" queries
4. Replace all vague claims with attributed statistics ("According to [Source], [Year]")
5. Implement schema that matches the page type (Article, Product, Organization, BreadcrumbList) — for accurate entity understanding, not as an AI-citation shortcut (Google states no special schema is needed for AI features)
6. Verify AI bots are allowed in robots.txt

---

## How AI Search Differs from Traditional SEO

### The Fundamental Shift

Traditional SEO gets your page ranked. AI SEO gets your content cited. These are different optimization targets.

| Dimension | Traditional SEO | AI SEO |
|-----------|----------------|--------|
| Goal | Rank on page 1 | Get cited in AI-generated answers |
| Success metric | Click-through rate | Citation frequency |
| Content priority | Keyword density | Answer extractability |
| Authority signal | Backlinks + domain authority | Backlinks + answer quality + attribution |
| User interaction | User clicks your link | AI extracts your answer; user may never visit |
| Content format | Long-form comprehensive | Self-contained extractable blocks |
| Optimization unit | The page | The paragraph or section |

### What Carries Over from Traditional SEO

- Domain authority still matters. AI systems prefer credible sources.
- Backlinks still signal trust and expertise.
- Technical SEO fundamentals (page speed, mobile-friendly, clean HTML) still apply.
- Quality content with original insights still wins.

### What Changes

- Keyword density matters less than answer clarity and directness
- Page-level optimization expands to section-level and paragraph-level optimization
- Internal linking serves discoverability for AI crawlers, not just PageRank flow
- Structured data helps machines disambiguate entities and page type, but it is not a gate: Google states there is no special schema.org markup required to appear in AI Overviews or AI Mode (as of September 2026)

---

## The Three Pillars of AI Citability

### Pillar 1: Structure (Extractable)

AI systems pull content in chunks. They find the paragraph, list, or definition that directly answers a query and extract it. Your content must be structured so answers are self-contained.

**Extractability requirements:**
- Definition blocks for "what is X" queries — tight, 1-2 sentence definitions in the first 200 words
- Numbered steps for "how to do X" queries — verb-first, self-contained steps
- Comparison tables for "X vs Y" queries — clean table format with headers
- FAQ blocks for question-based queries — explicit Q&A pairs
- Statistics with full attribution for data-oriented queries

**Anti-patterns that kill extractability:**
- Burying the answer in paragraph 8 of a 4,000-word essay
- Requiring context from previous sections to understand any individual section
- Using narrative prose for comparisons that should be tables
- Placing key definitions only in the conclusion

### Pillar 2: Authority (Citable)

AI systems do not just extract the most relevant answer — they extract the most credible one.

**Authority signals in the AI era:**
- **Domain authority** — High-DA domains get preferential citation
- **Author attribution** — Named authors with credentials outperform anonymous pages
- **Citation chains** — Your content cites credible sources, making you credible in turn

From borghei/Claude-Skills, MIT.

More from borghei/Claude-Skills