Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
Muse
Dots+21 moreClaude CodeCursorCodex CLIMuseDots
Manus
Grok
Grok Bot+18 agentsSEO + AI Search: Rank on Google & Get Cited by AI
This skill inspects your actual pages or repo, ranks issues by impact with evidence, and implements the fixes.
Free
SEO + AI Search: Rank on Google & Get Cited by AI
Example session with this skill installed
Our Next.js site for a boat rental company in Lisbon gets almost no Google traffic and never shows up in ChatGPT. Audit it and fix what you can in the repo.
- Read your context and instructions
- Compiled the seo + ai
- Generated the image
Summary
Audited 14 pages (repo + live HTML). The main blocker: every page canonicalised to the home page, so Google indexed 1 of 14. Fixed 11 issues in the repo; 3 need your input.
Findings (top first)
| # | Issue | Evidence | Impact | Fix |
|---|---|---|---|---|
| 1 | All pages canonical to / | app/layout.tsx:12 alternates.canonical: '/' | High | per-page canonical via generateMetadata |
| 2 | Boat pages rendered client-side only | app/boats/[slug]/page.tsx uses 'use client' + fetch in useEffect | High | server component + generateStaticParams |
| 3 | No sitemap, robots blocks /_next/ | public/robots.txt | High | app/sitemap.ts, app/robots.ts |
| 4 | Same title on 14 pages | "Boat Rentals" | Med | unique titles per boat/route |
| 5 | Hero image 2.4 MB JPG, LCP 5.1 s | Lighthouse mobile | Med | next/image AVIF + priority; LCP 1.9 s |
| 6 | No LocalBusiness schema; NAP differs from Google Business Profile | footer vs GBP | Med | JSON-LD + aligned address/phone |
| 7 | No direct answers for price/licence questions | FAQ missing | Med (AI) | answer-first FAQ + FAQPage schema |
Changes (PR-ready)
generateMetadataon all routes: unique titles like "Rent a Boat Without Licence in Lisbon - from 120 €/day"app/sitemap.ts(14 URLs),app/robots.ts(allows OAI-SearchBot, PerplexityBot, Claude-SearchBot; training bots left as before for you to decide)components/JsonLd.tsx: LocalBusiness, Product+Offer per boat, BreadcrumbList, FAQPage - all JSON.parse-validated- New FAQ section with 6 answer-first entries (licence, price, deposit, fuel, cancellations, kids)
- Build passes; Lighthouse SEO 100, Performance 94 (was 61)
Need from you
- Real prices and deposit amount to confirm FAQ answers
- Allow GPTBot (training)? Business decision
- 3 thin route pages: merge into one "Routes from Lisbon" guide?
30-day plan
Submit sitemap in Search Console + Bing, write 2 guides (best coves, licence rules), add internal links from guides to boats, test 10 target questions in ChatGPT/Perplexity monthly.
layout.tsx
PNG · 1536×1024
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
SEO that fixes things, plus visibility in AI answers
Most SEO prompts return a generic checklist. This skill inspects your actual pages or repo, ranks issues by impact with evidence, and implements the fixes. It also optimises for the new front door: ChatGPT, Perplexity, Claude and Google AI Overviews.
What it does
- Crawl & index blockers first: robots.txt, stray
noindex, canonicals, sitemaps, redirect chains, JS-only content, hreflang. - On-page: titles, meta descriptions, one H1 and heading hierarchy, URLs, alt text, internal links, Open Graph cards.
- Structured data: validated JSON-LD for Organization, WebSite, Article, Product, LocalBusiness, FAQ and Breadcrumbs, only for content that is really on the page.
- Core Web Vitals: LCP <= 2.5 s, INP <= 200 ms, CLS <= 0.1, with concrete image, font, JS and third-party fixes.
- Content & trust: search intent, E-E-A-T signals, thin pages, keyword cannibalisation.
- Real ranking data on Agensi: the keywords your domain already ranks for (position, volume, CPC), live Google results incl. AI Overviews for your target keywords, and Google Maps checks for local businesses - to find quick wins in positions 4-20. Your agent shows the price (cents) and asks before each use; works without them too.
- AI search (GEO): answer-first passages, question headings, quotable facts with sources, entity clarity, freshness, AI crawler access table (OAI-SearchBot, PerplexityBot, ClaudeBot, Google-Extended...), optional llms.txt, and how to measure AI referrals.
- Implements in your stack: Next.js metadata API and sitemap/robots routes, Nuxt
useSeoMeta, Astro, WordPress (Yoast/Rank Math), plain HTML. - Report: issue, evidence, impact, effort, fix, quick wins first, plus a 30-day plan.
- White-hat only: no keyword stuffing, fake reviews/ratings markup, cloaking or AI spam.
Includes
- SKILL.md workflow
- references/checklist.md - full audit checklist + local SEO + framework snippets
- references/schema.md - validated JSON-LD templates
- references/geo.md - AI search optimisation patterns, AI bots table, measurement
Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI and any SKILL.md-compatible agent.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Frontend & Web Apps.
Cannot fix server-side hosting bottlenecks. Does not provide live ranking data or backlink counts. Rankings take weeks to update. Requires manual submission to GSC/Bing.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
This skill has been used 7 times.
Trust & safety
Security scan
Security scan passed 2 days ago
- Free with an Agensi account