geo-fundamentals – skill Khác cho agent AI

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] | Citation behavior varies by query/product |

| ChatGPT | Inline/footnotes | Custom GPTs |

| Claude | Contextual | Long-form content |

| Gemini | Sources section | SEO crossover |

---

3. RAG Retrieval Factors

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 The platforms do not publish a universal weighting formula; do not assign invented percentages or infer citation probability from this checklist.

---

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 | 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 |

Access Decision

| 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 |

---

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> |

When to Use

This skill is applicable to execute the workflow or actions described in the overview.

Example

User request:

> Use @geo-fundamentals for this task: Generative Engine Optimization for AI search engines (ChatGPT, Claude, Perplexity).

Limitations

• Use this skill only when the task clearly matches the scope described above.
• Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
• Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

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.