home / skills / vudovn / antigravity-kit / geo-fundamentals

geo-fundamentals skill

/.agent/skills/geo-fundamentals

This skill helps you optimize content for AI citations by applying GEO fundamentals to create clear, data-rich, easily extractable material.

npx playbooks add skill vudovn/antigravity-kit --skill geo-fundamentals

Review the files below or copy the command above to add this skill to your agents.

Files (2)
SKILL.md
3.4 KB
---
name: geo-fundamentals
description: Generative Engine Optimization for AI search engines (ChatGPT, Claude, Perplexity).
allowed-tools: Read, Glob, Grep
---

# GEO Fundamentals

> Optimization for AI-powered search engines.

---

## 1. What is GEO?

**GEO** = Generative Engine Optimization

| Goal | Platform |
|------|----------|
| Be cited in AI responses | ChatGPT, Claude, Perplexity, Gemini |

### SEO vs GEO

| Aspect | SEO | GEO |
|--------|-----|-----|
| Goal | #1 ranking | AI citations |
| Platform | Google | AI engines |
| Metrics | Rankings, CTR | Citation rate |
| Focus | Keywords | Entities, data |

---

## 2. AI Engine Landscape

| Engine | Citation Style | Opportunity |
|--------|----------------|-------------|
| **Perplexity** | Numbered [1][2] | Highest citation rate |
| **ChatGPT** | Inline/footnotes | Custom GPTs |
| **Claude** | Contextual | Long-form content |
| **Gemini** | Sources section | SEO crossover |

---

## 3. RAG Retrieval Factors

How AI engines select content to cite:

| Factor | Weight |
|--------|--------|
| Semantic relevance | ~40% |
| Keyword match | ~20% |
| Authority signals | ~15% |
| Freshness | ~10% |
| Source diversity | ~15% |

---

## 4. Content That Gets Cited

| Element | Why It Works |
|---------|--------------|
| **Original statistics** | Unique, citable data |
| **Expert quotes** | Authority transfer |
| **Clear definitions** | Easy to extract |
| **Step-by-step guides** | Actionable value |
| **Comparison tables** | Structured info |
| **FAQ sections** | Direct answers |

---

## 5. GEO Content Checklist

### Content Elements

- [ ] Question-based titles
- [ ] Summary/TL;DR at top
- [ ] Original data with sources
- [ ] Expert quotes (name, title)
- [ ] FAQ section (3-5 Q&A)
- [ ] Clear definitions
- [ ] "Last updated" timestamp
- [ ] Author with credentials

### Technical Elements

- [ ] Article schema with dates
- [ ] Person schema for author
- [ ] FAQPage schema
- [ ] Fast loading (< 2.5s)
- [ ] Clean HTML structure

---

## 6. Entity Building

| Action | Purpose |
|--------|---------|
| Google Knowledge Panel | Entity recognition |
| Wikipedia (if notable) | Authority source |
| Consistent info across web | Entity consolidation |
| Industry mentions | Authority signals |

---

## 7. AI Crawler Access

### Key AI User-Agents

| Crawler | Engine |
|---------|--------|
| GPTBot | ChatGPT/OpenAI |
| Claude-Web | Claude |
| PerplexityBot | Perplexity |
| Googlebot | Gemini (shared) |

### Access Decision

| Strategy | When |
|----------|------|
| Allow all | Want AI citations |
| Block GPTBot | Don't want OpenAI training |
| Selective | Allow some, block others |

---

## 8. Measurement

| Metric | How to Track |
|--------|--------------|
| AI citations | Manual monitoring |
| "According to [Brand]" mentions | Search in AI |
| Competitor citations | Compare share |
| AI-referred traffic | UTM parameters |

---

## 9. Anti-Patterns

| ❌ Don't | ✅ Do |
|----------|-------|
| Publish without dates | Add timestamps |
| Vague attributions | Name sources |
| Skip author info | Show credentials |
| Thin content | Comprehensive coverage |

---

> **Remember:** AI cites content that's clear, authoritative, and easy to extract. Be the best answer.

---

## Script

| Script | Purpose | Command |
|--------|---------|---------|
| `scripts/geo_checker.py` | GEO audit (AI citation readiness) | `python scripts/geo_checker.py <project_path>` |

Overview

This skill provides a Generative Engine Optimization (GEO) framework and an automated audit to improve the chance content is cited by AI-powered search engines (ChatGPT, Claude, Perplexity, Gemini). It combines content checklist, technical signals, and crawler/access recommendations to make pages easy for RAG systems to find and cite. The goal is measurable increases in AI citation rate and AI-referred traffic.

How this skill works

The skill inspects content and site technicals against a GEO checklist: semantic relevance, structured data, author and FAQ schemas, freshness, and page performance. It evaluates crawler access settings, identifies entity-building opportunities, and flags missing citation-friendly elements such as original data, clear definitions, and TL;DR summaries. The included audit script runs checks on files and returns actionable findings for remediation.

When to use it

  • Preparing content intended to be cited by AI assistants
  • Launching authority pages, reports, or original research
  • Optimizing site access for AI crawlers selectively
  • Assessing competitor AI citation strategies
  • Before publishing long-form or FAQ-rich content

Best practices

  • Use question-based titles and TL;DR summaries at the top for easy extraction
  • Include original statistics, named expert quotes, and clear definitions to improve citation likelihood
  • Publish author info with credentials and maintain a visible "last updated" timestamp
  • Add Article, Person, and FAQPage schema and keep HTML clean and fast (<2.5s)
  • Control crawler access intentionally (allow or block GPTBot, Claude-Web, PerplexityBot) based on citation and privacy goals

Example use cases

  • Run a GEO audit before launching a industry research report to maximize AI citations
  • Update product help articles with FAQ schema and TL;DRs to appear as direct AI answers
  • Configure selective crawler access to allow PerplexityBot but block GPTBot according to policy
  • Optimize corporate blog network for entity consolidation (consistent author and organization data)
  • Track AI-cited competitor mentions and iterate content strategy based on citation gaps

FAQ

How do I measure AI citations?

Combine manual spot checks in AI engines with site analytics using UTM tags and search for "According to [Brand]" style mentions to approximate citation share.

Which signals matter most for AI citation?

Semantic relevance and clear extractable answers matter most, followed by keyword match, authority signals, and freshness—optimize content structure accordingly.