菜单
Audit and generate hreflang annotations for multilingual sites — check reciprocity, BCP-47 validity, self-reference, x-default, hreflang/canonical conflicts, and <html lang> agreement, and emit reciprocal hreflang link sets. Module M20 (conditional). Feeds the Search SEO score.
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
| name | seo-international |
| description | Audit and generate hreflang annotations for multilingual sites — check reciprocity, BCP-47 validity, self-reference, x-default, hreflang/canonical conflicts, and <html lang> agreement, and emit reciprocal hreflang link sets. Module M20 (conditional). Feeds the Search SEO score. |
| allowed-tools | Read, Grep, Glob, WebFetch, Bash |
hreflang tells search engines which language/region URL to serve. This module is conditional: it only runs when seo-vertical-detect flags a multilingual site (multiple lang/locale URLs, language switcher, or existing hreflang). On monolingual sites every finding is not_applicable at severity 0. Schema-type concerns defer to references/schema-tier1.md; this module owns link-level localization only.
Working from the PageSnapshot (rendered_dom if present, else raw_html). Read hreflang from <link rel="alternate" hreflang="..."> in <head> (also accept HTTP Link: headers / sitemap xhtml:link when present):
hreflang value is a valid language (en) or language-region (en-GB, pt-BR) tag; region is ISO-3166-1 alpha-2, not a country-of-language guess (en-UK is invalid; use en-GB).hreflang="x-default" for the language-selector / fallback URL.rel=canonical is a different page neutralizes the cluster (cross-check M2/seo-indexability).<html lang> agreement — the document lang attribute matches the locale this URL targets in its own hreflang entry.fixable: auto): when the locale→URL map is known (supplied by the user, a sitemap, or discovered alternates), generate a complete reciprocal hreflang link set — every locale + a single x-default — as a <head> diff for fix. Additive and deterministic.fixable: proposed): a partial set inferred from discovered alternates that needs the user to confirm the locale map before write.fixable: advisory): "this looks multilingual but no locale map exists" — never written by the tool.TODO(locale) placeholder and ask the user.node ${CLAUDE_SKILL_DIR}/../../scripts/hreflang-check.mjs --url <u> — parses the alternate set, validates BCP-47 tags, and checks reciprocity/self-reference/x-default across the discovered cluster.needs_api, never a false pass.Findings conform to schema/finding.schema.json. On a confirmed multilingual site severity is 4; otherwise the check is not_applicable at severity 0. Examples:
M20.hreflang.missing_reciprocal — page declares hreflang="de-DE" for a URL that does not point back (status: fail, severity 4, fixable: proposed, axis search, confidence established). evidence.observed quotes the one-way <link>; verification.reproduce runs the hreflang-check command above.M20.hreflang.invalid_bcp47 — hreflang="en-UK" (fail, severity 4, fixable: auto, axis search, confidence established; recommend en-GB).M20.hreflang.missing_xdefault — cluster has no x-default fallback (warn, severity 4, fixable: auto, axis search, confidence directional).M20.hreflang.not_applicable — monolingual site (not_applicable, severity 0).rel=canonical — the two work together.Audit a website or web codebase for SEO and AI-search (GEO/AEO) — produces two independent 0-100 scores (Search SEO + AI Visibility) plus a prioritized, evidence-backed report. Read-only; never writes files. Use when the user asks to audit, analyze, check, or score a site's SEO, structured data/schema, meta tags, Core Web Vitals, robots.txt, sitemaps, or llms.txt, or how it ranks in Google and is cited by AI engines (ChatGPT, Perplexity, Google AI Overviews, Gemini, Claude).
Opt-in fixer (the /claude-seo-ai:fix command). Applies the safe, deterministic SEO/AI-search fixes from an audit to the user's code — meta viewport/charset/lang, JSON-LD, robots.txt AI directives, hreflang, sitemaps, OG/Twitter cards, image dimensions, canonical, llms.txt. Dry-run preview by default; writes only after explicit per-change confirmation. Runs only when the user invokes it — never auto-triggered.
Analyze and score only a page's AI-search visibility (GEO/AEO) — answer extractability, fact density, AI-crawler access, entity linking, and llms.txt — and report an AI Visibility score with a citability breakdown. Read-only. Use for "will AI engines cite this?", GEO/AEO, or ChatGPT/Perplexity/Google AI Overviews/Gemini optimization.
Recompute and display the two scores (Search SEO + AI Visibility) from the most recent audit's findings, without re-crawling. Use to re-show or refresh the scores after an audit, or to score a saved findings JSON file.
Audit AI crawler access and citability for a page — confirm retrieval/citation bots (OAI-SearchBot, Claude-SearchBot, PerplexityBot) are allowed and the Googlebot vs Google-Extended split is correct, classify training vs search/retrieval vs user-fetch user-agents, check the page is server-rendered enough for non-JS AI crawlers, validate llms.txt / llms-full.txt (also covers M21), and generate a choice-gated robots.txt preset. Module M14. Feeds the AI Visibility score.
Audit Core Web Vitals & page performance — measure LCP, INP, and CLS against p75 field thresholds, diagnose render-blocking resources, unoptimized images, and layout-shift sources, and produce prioritized, advisory-only remediation guidance. Module M15. Feeds the Search SEO score (heavily) and the AI Visibility score (minimally).