SEO for your site, run by your AI agent
Paste one link into Claude, ChatGPT, Cursor or Codex. Your agent audits the live site, checks how AI search and agents see it, reads your real search data if you share it, fixes what it can, and tells you what's left.
Paste this into your agent
Audit and fix the SEO for https://example.com using https://uplift.page/seo
Swap in your own site. Agents that can only read text can use the one-file version: https://uplift.page/seo.md
Run the audit script, edit your code and show you the diff.
Fetch your live pages, check them and hand you a ranked fix list.
What it checks
- · Titles, descriptions, canonicals and headings in the raw HTML
- · Sitemap, robots rules and real 404s
- · Structured data that matches the page
- · Access for AI search crawlers and user-triggered agents
- · llms.txt, Markdown versions and accessible names
- · For local businesses: name, address and phone, LocalBusiness data and the Business Profile checklist
- · Clicks, impressions and Core Web Vitals, from Google and Bing's own data
The steps your agent follows
For AI agents: You were given this link to improve a website's search, AI-answer and agent visibility. Follow the steps below in order. Step 4 is only for a local business: skip it otherwise. Everything in one file, with each skill's full text: https://uplift.page/seo.md
1. Ask, then say what goes where
Ask for the site's URL and whether you can edit its code. Before fetching anything, tell the user: you will fetch pages only from their site; Search Console or Bing data only if they give you access; nothing goes to third-party SEO scanners or graders.
2. Audit the live site
skill: SEO and AEO audit · SKILL.md
If you can run commands (Node 18 or later):
curl -fsSL https://uplift.page/tools/seo-audit.mjs -o seo-audit.mjs node seo-audit.mjs https://example.com --save seo-before.jsonRead its errors, warnings and notes.
If you can only fetch pages, read the raw HTML of the home page and three important pages and check: one unique
<title>and meta description each, a canonical pointing at itself, one H1, real content without JavaScript, valid JSON-LD that matches the visible text, and nonoindex. Then check that/robots.txtloads and names the sitemap, that/sitemap.xmllists those pages and they return 200, and that a made-up URL returns a real 404.3. Check how AI search and agents see it
skill: Agent readiness · SKILL.md
Check that robots.txt doesn't block search crawlers (Googlebot, Bingbot, OAI-SearchBot, Claude-SearchBot, PerplexityBot) and repeats every rule in each group that names a crawler. Check
/llms.txt, Markdown versions of key pages, accessible names on links and buttons, and stable layout. The audit script prints these asagents:lines; add--lighthouse 3for Lighthouse's agent checks.4. Local business only: check local search
Only if the site belongs to a business with an address customers visit or a service area it travels to (a clinic, shop, restaurant, trade, law or dental office). Online-only businesses, SaaS and publishers: skip this step and don't install the skill.
Check that the name, address and phone match everywhere on the site, that the structured data uses the most specific type (
MedicalClinic,Dentist,Plumber…) with a fullPostalAddress, phone, hours andsameAslinks to the Google Business Profile, and that each real service and location has its own page. List what only the owner can check: the Business Profile's category, hours and reviews, and the same details on Bing, Apple and industry directories.5. Read real search data, if shared
skill: Search performance · SKILL.md
Only if the user can share Google Search Console or Bing Webmaster Tools (API access or an export): compare the last 28 days with the 28 before, and find pages with many impressions but few clicks, queries at positions 5 to 15, and pages with no impressions four weeks after publishing. Without that data, say rankings and indexing are unknown. Never estimate them.
6. Fix what you can
With code access, fix provable faults first, in this order: anything blocking crawling or indexing, wrong canonicals and soft 404s, missing or duplicate titles and descriptions, the sitemap and robots rules, structured data, then agent files. Derive metadata from each page's own data in one helper; never write SEO by hand per page. Show the diff, and don't deploy without the user's OK.
Without code access, give a fix list ranked by impact, with the exact text or code for each fix.
7. Verify and report
After the fixes go live, run the audit again with
--compare seo-before.json. Tell the user to submit the sitemap and request indexing for changed pages in Search Console, and offer IndexNow for Bing (--indexnow <key>). Report a short table (check, result, fixed or not), the next three fixes, and what you couldn't check.
Rules
- · Never invent numbers, ratings, authors, dates or rankings.
- · Never promise rankings or AI citations.
- · No pages per keyword variation, no FAQ or HowTo markup for rich results, no fake reviews.
- · Ask before deploying, submitting to Search Console or pinging IndexNow.
Where your data goes
Your agent fetches pages only from your site. Search Console and Bing Webmaster Tools data is read only if you give access, and goes only to Google or Microsoft. Nothing is sent to third-party SEO scanners or score sites, and uplift.page never sees your site's data.
The skills behind it
Creates and verifies the search, answer-engine and agent setup for a site's public pages, from titles, canonicals and structured data to sitemaps, robots rules, llms.txt and the files AI agents look for, then gates it on checks that catch real failures. Use when adding or auditing SEO, AEO or GEO, when a site publishes pages from a database or library, or when new pages should appear in search automatically.
Checks and fixes how AI agents and answer engines reach a site, from robots.txt groups and Content-Signal per AI crawler to llms.txt, Markdown versions of pages, /.well-known discovery files, real 404s, accessible names and Lighthouse's Agentic Browsing score. Use when asked whether AI agents can read or use a site, about llms.txt, Content-Signal, ai-catalog.json, WebMCP or agent-friendly pages, or when seo-aeo-audit reports agent findings.
Reads how a site really performs in search from first-party sources (Google Search Console, Bing Webmaster Tools, Chrome UX Report field data and PageSpeed Insights) and turns it into a short list of fixes. Use when asked about rankings, clicks, impressions, indexing, Core Web Vitals, or whether an SEO change worked, or when seo-aeo-audit passes but pages still aren't found.
Checks and fixes how a local business shows up in local and map search, from its Google Business Profile and name, address and phone consistency to LocalBusiness structured data, location and service pages and reviews. Use only when the site belongs to a business with a physical location customers visit or a service area it travels to (clinics, shops, restaurants, trades, law and dental offices); skip it for online-only businesses, SaaS and publishers.
Install it instead
Keep the skills in your repo so your agent uses them on every change, not just when you paste the link.
curl -fsSL https://uplift.page/p/seo-aeo-audit/SKILL.md --create-dirs -o .agents/skills/seo-aeo-audit/SKILL.md curl -fsSL https://uplift.page/p/agent-readiness/SKILL.md --create-dirs -o .agents/skills/agent-readiness/SKILL.md curl -fsSL https://uplift.page/p/search-performance/SKILL.md --create-dirs -o .agents/skills/search-performance/SKILL.md
curl -fsSL https://uplift.page/p/local-seo/SKILL.md --create-dirs -o .agents/skills/local-seo/SKILL.md
MCP server: https://uplift.page/mcp
Tool: pull_skill {"slug": "seo-aeo-audit"}By Uplift Duo. The skills update in the uplift.page library and this page follows within five minutes.