audit
The audit command evaluates web assets across multiple dimensions including on-page SEO quality, CORE-EEAT content standards, technical infrastructure health, AI visibility readiness, and domain authority metrics. Use it to assess existing pages before publication, identify quality gaps and trust blockers, and receive actionable hardening recommendations, with optional flags for technical SEO, AI-GEO visibility, domain authority analysis, and competitive benchmarking.
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/aaron-he-zhu/seo-geo-claude-skills/HEAD/commands/audit.md -o ~/.claude/commands/audit.mdaudit.md
# Audit Command Evaluate and harden any existing asset — page quality, technical health, AI visibility, and domain trust. ## Route - on-page-seo-auditor - content-quality-auditor - technical-seo-checker - geo-content-optimizer - entity-optimizer - domain-authority-auditor - backlink-analyzer ## Rules - Default (page audit): check on-page SEO, metadata, headings, images, links, and CORE-EEAT risk. Return `ready`, `ready_with_concerns`, `blocked`, or `needs_input` with evidence and next fixes. Use `--full` to run the full publish-readiness gate when evidence is available. - `--tech`: crawlability, indexation, Core Web Vitals, mobile, security, structured-data exposure, robots, sitemap, canonical, redirect, and migration risk. Do not guess CWV or crawl data; mark missing evidence and next checks. - `--visibility`: AI answer inclusion and GEO citation readiness, entity clarity, and trust blockers. Do not claim observed citation proof; require content-quality-auditor before any publish-ready, cite-ready, or GEO Score readiness verdict. - `--authority`: CITE / domain-trust analysis, backlink quality, and entity credibility; flag trust blockers, toxic-link risks, missing entity proof, and authority-building opportunities. `--competitors` adds comparison. - Do not produce a publish-ready verdict without full veto-aware audit coverage. ## Output Return inline artifacts by default. Files may be written only when the user explicitly asks and the runtime can write.
Use when the user asks to "optimize for AI citations"; improves citation readiness for ChatGPT, Perplexity, AI Overviews, Gemini, and Claude. Not for structural on-page SEO — use on-page-seo-auditor; not for net-new drafting — use seo-content-writer. AI引用优化/GEO优化/AI搜索
Use when the user asks to "optimize meta tags"; improves titles, descriptions, Open Graph, Twitter cards, and CTR test variants. Not for JSON-LD structured data — use schema-markup-generator; not for body copy — use seo-content-writer. 标题优化/元描述/CTR
Use when the user asks to "generate schema"; creates JSON-LD for FAQ, HowTo, Article, Product, and LocalBusiness rich-result candidates. Not for title/meta-description tags — use meta-tags-optimizer; not for crawl/index technical issues — use technical-seo-checker. Schema标记/结构化数据
Use when the user asks to "write SEO content"; drafts new posts, articles, and landing pages with keywords, headers, snippets, and evidence boundaries. Not for AI-citation/GEO readiness scoring — use geo-content-optimizer; not for updating decaying existing content — use content-refresher. SEO文章写作/内容优化
Run the SEO/GEO pack-local Aaron workflow implied by a natural-language goal, at the smallest safe depth. Add --deep for exhaustive, maximum-rigor, or stress-test runs.
Produce SEO/GEO content end-to-end: brief, draft one asset or a series, refresh stale content, and prepare a CMS-neutral publish package. Not sure? Use /aaron:auto.
Understand the opportunity: keyword demand, SERP intent, competitors, content gaps, and site/topic/entity maps. Not sure? Use /aaron:auto.
Track and remember over time: rankings, alerts, performance reports, and project memory. Not sure? Use /aaron:auto.