
If you're publishing content and want AI engines like ChatGPT or Perplexity to actually cite you instead of just training on your words, this gives you the framework. It breaks down how RAG retrieval works, what content structures get pulled into responses (original data, clean definitions, FAQ sections), and includes a Python auditor script to check your citation readiness. The SEO versus GEO comparison tables are genuinely useful. Fair warning that measurement is still mostly manual monitoring since there's no Google Search Console equivalent for AI citations yet. Treat this as the early playbook for a space that's still figuring itself out.
$ npx -y skills add sickn33/antigravity-awesome-skills --skill geo-fundamentals --agent claude-codeInstalls into .claude/skills of the current project.
Optimization for AI-powered search engines.
GEO = Generative Engine Optimization
| Goal | Platform |
|---|---|
| Be cited in AI responses | ChatGPT, Claude, Perplexity, Gemini |
| Aspect | SEO | GEO |
|---|---|---|
| Goal | #1 ranking | AI citations |
| Platform | AI engines | |
| Metrics | Rankings, CTR | Citation rate |
| Focus | Keywords | Entities, data |
| Engine | Citation Style | Opportunity |
|---|---|---|
| Perplexity | Numbered [1][2] | Citation behavior varies by query/product |
| ChatGPT | Inline/footnotes | Custom GPTs |
| Claude | Contextual | Long-form content |
| Gemini | Sources section | SEO crossover |
Potential retrieval considerations include relevance, source quality, freshness and diversity. The platforms do not publish a universal weighting formula; do not assign invented percentages or infer citation probability from this checklist.
| 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 |
| Action | Purpose |
|---|---|
| Google Knowledge Panel | Entity recognition |
| Wikipedia (if notable) | Authority source |
| Consistent info across web | Entity consolidation |
| Industry mentions | Authority signals |
| Crawler | Engine |
|---|---|
| GPTBot | OpenAI training crawler; search/user agents are separate |
| ClaudeBot / Claude-SearchBot / Claude-User | Distinct purposes; verify current official crawler docs |
| PerplexityBot | Perplexity |
| Googlebot | Google Search; verify separate product controls |
| Strategy | When |
|---|---|
| Selective access | Match owner policy to documented training/search/user crawler purposes |
| Block GPTBot | Don't want OpenAI training |
| Selective | Allow some, block others |
| Metric | How to Track |
|---|---|
| AI citations | Manual monitoring |
| "According to [Brand]" mentions | Search in AI |
| Competitor citations | Compare share |
| AI-referred traffic | UTM parameters |
| ❌ 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 | Purpose | Command |
|---|---|---|
scripts/geo_checker.py | GEO audit (AI citation readiness) | python scripts/geo_checker.py <project_path> |
This skill is applicable to execute the workflow or actions described in the overview.
User request:
Use @geo-fundamentals for this task: Generative Engine Optimization for AI search engines (ChatGPT, Claude, Perplexity).
The bundled checker scans at most30 selected source files; it does not crawl/render pages, validate schema, verify original data or measure AI citation probability. Public Markdown/docs can be relevant but are excluded by this heuristic. Missing files mean not assessed, not passed. FAQ markup and crawler access do not guarantee citations; verify current platform eligibility and measure dated, reproducible query samples.
Sponsors