geo-fundamentals
Generative Engine Optimization for AI search engines (ChatGPT, Claude, Perplexity).
- License 许可
- MIT
- 最近更新
- 2026-11-14
- Stars
- ★ 3.3w
- Forks
- 3.9k
01 前言 Front Matter
- name
- geo-fundamentals
- description
- Generative Engine Optimization for AI search engines (ChatGPT, Claude, Perplexity).
- allowed-tools
- Read, Glob, Grep
02 资源文件 1
- 脚本scripts/geo_checker.py9.5 KB
03 SKILL.md 正文
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 | 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> |
04 同仓库更多 Skills
wealthville-pool-scoring
Score DeFi liquidity pools before providing liquidity. Returns a 0-100 pool score and an Enter/Hold/Exit/Reduce/Avoid verdict with calibrated confidence for ~68,800 Solana pools and 575 EVM pools, plus a public miss-inclusive track record. Use when asked whether a pool is worth LPing into, which pools look best right now, or how accurate the scores have actually been.
technical-debt-auditor
Scans a codebase and produces a quantified technical debt report with a prioritized remediation plan. Analyzes dead code, TODO/FIXME/HACK markers, dependency staleness, complexity hotspots, code duplication signals, test coverage gaps, unused exports, and outdated patterns. Use this skill when the user asks to audit their codebase for tech debt, wants a health check of their code quality, says things like "where should I focus refactoring", "find code smells", "audit my codebase", "what technical debt do we have", "prioritize cleanup work", or asks about code quality metrics. Also trigger when the user mentions "code rot", "legacy cleanup", "refactoring priorities", or wants to understand the overall health of a project before a major effort. Trigger even if the user doesn't say "technical debt" explicitly — any request to systematically assess code quality and identify improvement priorities belongs here.
readonly-sql-guard
Make an agent's database access provably read-only. Use when an agent runs caller-supplied SQL against a production/ERP/analytics database (a "query" MCP tool, text-to-SQL, an admin console), or when reviewing DB-access code for write/DDL/side-effect/transaction-escape risks. Checks what a statement CALLS, not just its shape.
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
discernment-nudge
After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.