SEO + GEO + AEO audit for any website. Maps every check to Google's published best practices for Search, AI Overviews / AI Mode, Core Web Vitals (LCP/INP/CLS), and the cross-LLM retrieval layer (ChatGPT Search, Perplexity, Microsoft Copilot, Claude web search). Every finding cites a Google or provider doc. Verdict: Not Ready / Competitive / Leading.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Audit any website against the best practices Google itself publishes for Search, AI Overviews, AI Mode, and Core Web Vitals — plus the cross-LLM retrieval layer that gates visibility in ChatGPT Search, Perplexity, Microsoft Copilot, and Claude web search.
Why this exists: there are dozens of SEO audit tools. None of them strictly trace every check to a Google-published doc URL, and almost none audit the AI retrieval-bot layer (OAI-SearchBot, PerplexityBot, ChatGPT-User, Perplexity-User) that decides whether your site appears in AI answers at all. This skill does both, with severity that maps to action (MUST / SHOULD / NICE) and a single-line verdict: Not Ready / Competitive / Leading.
Every finding cites the Google or provider doc it traces to. Thresholds are Google's verbatim numbers (LCP ≤ 2.5 s, INP ≤ 200 ms, CLS ≤ 0.1) — not a Lighthouse 0–100.
What it covers:
npx skills add https://github.com/wishfyai/google-seo-geo-aeo-audit-skill --skill google-audit
Then in Claude Code:
/google-audit example.com
/google-audit https://example.com --max-pages 25
After npx skills add (or after cloning the repo), there is a one-shot
orchestration script:
SKILL_DIR=./.agents/skills/google-audit # path npx skills add lands the skill at
pip install -r "$SKILL_DIR/requirements.txt"
bash "$SKILL_DIR/scripts/run_audit.sh" https://wishfy.ai --max-pages 10
It writes audit.json + audit.md to /tmp/google-audit-<timestamp>/.
For richer field data, set PAGESPEED_API_KEY (free from Google) and/or
npm install -g lighthouse.
robots.txt, capped at --max-pages (default 50).robots.txt correctness, AI-retrieval-bot allow-list (OAI-SearchBot, PerplexityBot, ChatGPT-User, Perplexity-User, Bingbot), sitemap discipline, HTTPS, hreflang.docs/rules.yaml — every rule has a stable id, severity (must/should/nice), a Google doc citation, and a machine-evaluable check.audit.json — every rule, every page, with status (pass / needs_improvement / fail / nice_not_done), observed value, threshold, source URL.audit.md — human-readable summary with verdict at the top and clickable citation links.| Result | Verdict |
|---|---|
| Any MUST failing | Not Ready — fix before anything else. |
| All MUST pass, ≥ 80 % SHOULD pass | Competitive — eligible across Google + other AI engines. |
| All MUST + all SHOULD pass | Leading — focus on content quality, entity authority, monitoring. |
Field-data checks (Core Web Vitals) need a free Google API key:
export PAGESPEED_API_KEY=AIza...
The skill warns and continues without it — Lighthouse lab data still runs locally — but CrUX field data is the recommended signal for ranking.
Used for full Lighthouse audits when PSI rate-limits or for offline checks:
npm install -g lighthouse
pip install -r requirements.txt
The skill never emits outdated guidance. rules.yaml explicitly reflects the May 2026 state of Google's documentation:
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimnpx claudepluginhub wishfy-ai/google-seo-geo-aeo-audit-skillComplete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
greyhaven-aiComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
JeffallanA growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Yuan1z0825Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
OthmanAdiPermanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
1270011UI/UX design intelligence. 67 styles, 161 palettes, 57 font pairings, 25 charts, 15 stacks (React, Next.js, Vue, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Nuxt, Jetpack Compose). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.
nextlevelbuilder