360 Secure SkillHub
360 安全技能中心

ai-visibility-quick-score

基于服务器端渲染 HTML 对单个网页 URL 做 0–100 的 AI 搜索可见性（GEO/AEO）就绪度评分：检查 robots.txt 中 AI 爬虫许可、JSON-LD 结构化数据、标题与元描述长度、H1 与问答式小标题、答案前置开头、llms.txt 及日期信号，并给出分值最高的五项修复建议。衡量的是抓取与解析就绪度，而非是否已被 AI 引用。

未知作者
热度 0.00
最近更新 2026-10-18 21:39:30
分类：营销依赖：代码执行 / 第三方 API应用场景：市场分析 / 报告撰写

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add seoskills.sh/ai-visibility-quick-score
Metadata
name
ai-visibility-quick-score
description
Give one web page a quick 0-100 AI search visibility (GEO/AEO readiness) score from its server-rendered HTML - AI crawler access, Organization/WebSite JSON-LD, structured data, title/meta, question headings, answer-first opening, llms.txt and freshness - with the top 5 fixes. Use when the user asks if a page is ready for ChatGPT, Perplexity, Google AI Overviews or other AI search, or wants a GEO/AEO score.
license
MIT

AI visibility quick score (one page)

Scores a single URL the way most AI crawlers see it: raw HTML, no JavaScript. It returns a 0–100 score, a band and the five fixes worth the most points.

When to use

  • "Is my homepage ready for AI search?", "GEO score for this URL", "why doesn't ChatGPT mention us?" (as a first check).

How to run

python3 scripts/quick_score.py https://example.com/

Needs outbound HTTPS; makes 3 requests (the page, robots.txt, llms.txt).

Scoring (100 points)

check points
AI crawlers allowed in robots.txt (−5 per blocked bot) 25
Organization / WebSite / Person entity in JSON-LD 15
Other valid JSON-LD (Article, Product, FAQPage…) 10
Title 15–65 chars, meta description 70–170 chars 10
One H1 and question-style H2/H3s 15
Answer-first opening paragraph and 300+ server-rendered words 15
/llms.txt present 5
Date signal (dateModified, article time, <time>) 5

Bands: 80+ STRONG, 65+ GOOD, 50+ FAIR, 35+ POOR, below 35 CRITICAL.

Read the result honestly

This measures readiness (can AI systems fetch, parse and trust the page), not whether you are cited today. A JavaScript-only site will score low because its server HTML is empty, and that low score is accurate for crawlers that do not run JavaScript.

Example

https://plausible.io/ → 72/100 GOOD; fixes: add page-type JSON-LD, a direct-answer opening, /llms.txt, a date signal, and a shorter title.

Want a full-site score and report?