菜单
When the user wants content cited by LLMs or surfaced in AI-generated answers — 'AI SEO,' 'AEO,' 'GEO,' 'LLMO,' 'answer engine optimization,' 'AI Overviews,' 'optimize for ChatGPT/Perplexity/Claude,' 'AI citations,' 'zero-click search.' For traditional technical/on-page audits, see seo-audit. For structured data, see schema-markup.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
When the user wants to write, rewrite, or improve marketing copy for any page — homepage, landing, pricing, feature, about, or product pages; "headline help," "CTA copy," "value proposition," "tagline," "hero section," "make this more compelling," "conversion copy," or complete Figma-ready full-page copy (see Full-Page Mode below). For email copy, see email-sequence. For popups, see popup-cro. For editing existing copy, see copy-editing.
When the user wants to increase conversions on any marketing page — homepage, landing, pricing, feature, or blog; "CRO," "this page isn't converting," "low conversion rate," "bounce rate," "my landing page sucks" — or just shares a URL asking for feedback. For signup flows, see signup-flow-cro; post-signup activation, onboarding-cro; forms, form-cro; popups, popup-cro.
When the user wants to audit or diagnose SEO issues — "technical SEO," "why am I not ranking," "meta tags review," "my traffic dropped," "Google update hit me," "core web vitals," "crawl errors," "indexing issues," or even a vague "my SEO is bad." For pages at scale, see programmatic-seo. For structured data, see schema-markup. For AI search, see ai-seo.
Coder<->reviewer handoff loop (Claude<->Codex, roles swappable) with self-instrumented per-round cost tracking. Loops locally via HANDOFF.md until approved, then opens a PR with the full transcript.
Act as a Senior Accessibility Engineer to audit a page, component, or design against WCAG 2.2 AA. Produces a triaged finding list (critical/serious/moderate), focus-order map, contrast report, ARIA decision tree, and a screen-reader test plan. Use when shipping new UI, hardening an existing flow, or preparing for VPAT/accessibility conformance.
When the user wants to plan, design, or implement an A/B test or experiment — "split test," "variant copy," "multivariate test," "hypothesis," "statistical significance," "how long should I run this test," or comparing two versions. For tracking implementation, see analytics-tracking. For page-level conversion optimization, see page-cro.
| name | ai-seo |
| description | When the user wants content cited by LLMs or surfaced in AI-generated answers — 'AI SEO,' 'AEO,' 'GEO,' 'LLMO,' 'answer engine optimization,' 'AI Overviews,' 'optimize for ChatGPT/Perplexity/Claude,' 'AI citations,' 'zero-click search.' For traditional technical/on-page audits, see seo-audit. For structured data, see schema-markup. |
| category | marketing |
| tier | on-demand |
Make content discoverable, extractable, and citable by AI systems — Google AI Overviews, ChatGPT, Perplexity, Claude, Gemini, and Copilot — so it gets cited as a source in AI-generated answers.
Product context: If .agents/product-marketing-context.md exists (or .claude/product-marketing-context.md in older setups), read it first and tailor output to it; only ask for what it doesn't cover.
Gather this context (ask if not provided):
| Platform | How It Works | Source Selection |
|---|---|---|
| Google AI Overviews | Summarizes top-ranking pages | Strong correlation with traditional rankings |
| ChatGPT (with search) | Searches web, cites sources | Draws from wider range, not just top-ranked |
| Perplexity | Always cites sources with links | Favors authoritative, recent, well-structured content |
| Gemini | Google's AI assistant | Pulls from Google index + Knowledge Graph |
| Copilot | Bing-powered AI search | Bing index + authoritative sources |
| Claude | Brave Search (when enabled) | Training data + Brave search results |
For per-platform source selection and optimization, see references/platform-ranking-factors.md.
Traditional SEO gets you ranked; AI SEO gets you cited. A well-structured page can get cited even from page 2 or 3 — AI systems select sources on content quality, structure, and relevance, not just rank position.
Critical stats:
Assess your current AI search presence before optimizing.
Test 10-20 of your most important queries across platforms:
| Query | Google AI Overview | ChatGPT | Perplexity | You Cited? | Competitors Cited? |
|---|---|---|---|---|---|
| [query 1] | Yes/No | Yes/No | Yes/No | Yes/No | [who] |
| [query 2] | Yes/No | Yes/No | Yes/No | Yes/No | [who] |
Query types to test:
Where competitors get cited and you don't, examine:
For each priority page, verify:
| Check | Pass/Fail |
|---|---|
| Clear definition in first paragraph? | |
| Self-contained answer blocks (work without surrounding context)? | |
| Statistics with sources cited? | |
| Comparison tables for "[X] vs [Y]" queries? | |
| FAQ section with natural-language questions? | |
| Schema markup (FAQ, HowTo, Article, Product)? | |
| Expert attribution (author name, credentials)? | |
| Recently updated (within 6 months)? | |
| Heading structure matches query patterns? | |
| AI bots allowed in robots.txt? |
Each AI platform has its own crawler; blocking it means that platform can't cite you:
Check robots.txt for Disallow rules targeting these. If blocked, it's a business decision: blocking prevents AI training on your content but also prevents citation. A middle ground is blocking training-only crawlers (like CCBot from Common Crawl) while allowing the search bots above.
See references/platform-ranking-factors.md for the full robots.txt configuration.
1. Structure (make it extractable)
2. Authority (make it citable)
3. Presence (be where AI looks)
AI systems extract passages, not pages. Every key claim should work as a standalone statement.
Content block patterns:
For templates for each block type, see references/content-patterns.md.
Structural rules:
AI systems prefer sources they can trust.
The Princeton GEO research (KDD 2024, studied across Perplexity.ai) ranked 9 optimization methods:
| Method | Visibility Boost | How to Apply |
|---|---|---|
| Cite sources | +40% | Add authoritative references with links |
| Add statistics | +37% | Include specific numbers with sources |
| Add quotations | +30% | Expert quotes with name and title |
| Authoritative tone | +25% | Write with demonstrated expertise |
| Improve clarity | +20% | Simplify complex concepts |
| Technical terms | +18% | Use domain-specific terminology |
| Unique vocabulary | +15% | Increase word diversity |
| Fluency optimization | +15-30% | Improve readability and flow |
| -10% | Actively hurts AI visibility |
Best combination: Fluency + Statistics = maximum boost. Low-ranking sites benefit even more — up to 115% visibility increase with citations.
Statistics and data (+37-40% citation boost)
Expert attribution (+25-30% citation boost)
Freshness signals
E-E-A-T alignment
AI systems cite where you appear, not just your website. Third-party sources matter more than your own site:
Actions:
Structured data helps AI systems understand your content. Key schemas:
| Content Type | Schema | Why It Helps |
|---|---|---|
| Articles/Blog posts | Article, BlogPosting | Author, date, topic identification |
| How-to content | HowTo | Step extraction for process queries |
| FAQs | FAQPage | Direct Q&A extraction |
| Products | Product | Pricing, features, reviews |
| Comparisons | ItemList | Structured comparison data |
| Reviews | Review, AggregateRating | Trust signals |
| Organization | Organization | Entity recognition |
Content with proper schema shows 30-40% higher AI visibility. For implementation, use the schema-markup skill.
Prioritize these formats:
| Content Type | Citation Share | Why AI Cites It |
|---|---|---|
| Comparison articles | ~33% | Structured, balanced, high-intent |
| Definitive guides | ~15% | Comprehensive, authoritative |
| Original research/data | ~12% | Unique, citable statistics |
| Best-of/listicles | ~10% | Clear structure, entity-rich |
| Product pages | ~10% | Specific details AI can extract |
| How-to guides | ~8% | Step-by-step structure |
| Opinion/analysis | ~10% | Expert perspective, quotable |
Underperformers for AI citation:
| Metric | What It Measures | How to Check |
|---|---|---|
| AI Overview presence | Do AI Overviews appear for your queries? | Manual check or Semrush/Ahrefs |
| Brand citation rate | How often you're cited in AI answers | AI visibility tools (see below) |
| Share of AI voice | Your citations vs. competitors | Peec AI, Otterly, ZipTie |
| Citation sentiment | How AI describes your brand | Manual review + monitoring tools |
| Source attribution | Which of your pages get cited | Track referral traffic from AI sources |
| Tool | Coverage | Best For |
|---|---|---|
| Otterly AI | ChatGPT, Perplexity, Google AI Overviews | Share of AI voice tracking |
| Peec AI | ChatGPT, Gemini, Perplexity, Claude, Copilot+ | Multi-platform monitoring at scale |
| ZipTie | Google AI Overviews, ChatGPT, Perplexity | Brand mention + sentiment tracking |
| LLMrefs | ChatGPT, Perplexity, AI Overviews, Gemini | SEO keyword → AI visibility mapping |
Monthly manual check:
Goal: Get cited in "What is [category]?" and "Best [category]" queries.
Optimize:
Goal: Get cited as an authoritative source on topics in your space.
Optimize:
Goal: Get cited in "[X] vs [Y]" and "Best [X] alternatives" queries.
Optimize:
Goal: Get cited in "How to [X] with [your product]" queries.
Optimize:
For implementation, see the tools registry.
| Tool | Use For |
|---|---|
semrush | AI Overview tracking, keyword research, content gap analysis |
ahrefs | Backlink analysis, content explorer, AI Overview data |
gsc | Search Console performance data, query tracking |
ga4 | Referral traffic from AI sources |