菜单
Run a full GEO audit on a URL. Computes 0-100 composite score across Technical/Citability/Schema/Entity vectors. Returns confidence-labeled findings. Use when the user asks to "audit", "check", "diagnose", or "score" a website's AI search visibility.
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
The best AEO/GEO skill for Claude Code. Audits, fixes, and monitors website visibility across ChatGPT, Claude, Perplexity, Gemini, and Google AI Overviews. Computes a 0-100 composite GEO Score across 4 vectors (Technical, Citability, Schema, Entity), backed by 33 evidence collectors and 100+ research-validated optimization rules. Use this skill when the user mentions "GEO", "AEO", "AI search optimization", "ChatGPT visibility", "answer engine optimization", "generative engine optimization", "llms.txt", "AI Overviews", "AI citation", "Perplexity ranking", "Claude search visibility", or asks how to make a website citable by LLM-powered search engines.
Head-to-head GEO Score comparison vs 2-5 competitors. Detects per-vector deltas, "they have / you don't" gaps, "you have / they don't" advantages, generates action sequence to leapfrog. Use when the user asks to "compare", "benchmark vs competitors", or "how do I beat X".
Rewrite content for AI citability. Adds expert quotes (+41% citations), inserts statistics (+40% visibility), embeds source attributions (+115% citation likelihood). Idempotent. Use when the user asks to "rewrite", "fix content", "add quotes", "improve citability", or "make my article more citable".
Generate /llms.txt per llmstxt.org spec. Creates AI-engine catalog with H1, summary, primary pages, optional reference. Anthropic honors this for ClaudeBot. Use when the user asks for "llms.txt", "AI catalog", or "llmstxt spec".
Patch robots.txt to explicitly allow 27 AI bots (GPTBot, ClaudeBot, PerplexityBot, Google-Extended, etc.). Diff-aware — never overwrites existing rules. Use when the user asks to "allow AI bots", "fix robots.txt", "block GPTBot", or "patch robots".
Generate JSON-LD structured data. Auto-creates FAQPage (highest AI citation surface), Article, Organization, HowTo, Speakable, Product, BreadcrumbList, Person schemas. Validates with Schema.org. Use when the user asks for "schema", "structured data", "JSON-LD", "FAQ schema", or "rich results markup".
| name | audit |
| parent | best-aeo-skill |
| description | Run a full GEO audit on a URL. Computes 0-100 composite score across Technical/Citability/Schema/Entity vectors. Returns confidence-labeled findings. Use when the user asks to "audit", "check", "diagnose", or "score" a website's AI search visibility. |
Diagnose a URL's AI search visibility. Returns a 0–100 composite GEO Score with ranked, confidence-labeled findings.
--url <URL> (required) — single page audit--sitemap <URL> (alt) — batch up to 100 pages--profile [default|saas|ecommerce|publisher|local|agency|devtools|academic]--format [terminal|markdown|json]python3 scripts/audit.py --url https://example.com --profile saas
See scripts/audit.py.