SEO for AI AgentsA drop-in skill pack for AI coding agents.
Build sites that search engines rank and AI answer engines cite.
$ claude "audit my site's SEO"
Analyzing built output from /dist...
✓ Rung 1: Reach (HTML serves content)
✓ Rung 2: Read (Metadata & Core Vitals)
✗ Rung 3: Understand (Missing JSON-LD)
Fixing Rung 3...
↳ Injected SoftwareApplication schema into index.html
↳ Added Organization schema to /about
Ready for review. Run `git diff` to see changes.
Sound familiar?
You vibe-coded a new app over a weekend. It looks great, the design is clean, the demo works. You ship it, and weeks later: nothing. No search traffic, no AI tools mentioning it.
The build is quietly full of SEO problems you can't see in a browser: an empty HTML shell that crawlers receive, missing titles and metadata, no structured data, pages wired to nothing. The site exists for a human with a browser, and barely exists for a search engine. That's the gap this closes.
Built for developers shipping real sites
Whether you're starting fresh, improving a site you built, or pointing an agent at an existing codebase, the audit is the same. Only the emphasis changes.
Starting a new site
Build it SEO-correct from the first commit, instead of fixing it after launch.
Improving a site you built
Audit what's live and raise it, without regressing pages that already rank.
An existing codebase + agent
Point your coding agent at the repo and have it diagnose and fix the SEO.
What's going wrong → what the pack does
My AI-built site isn't showing up in Google
Finds why crawlers can't see it, and fixes it
I edited the code but search didn't change
Verifies on the served HTML, not the source
I want to rank, not just look good
Works the SEO fundamentals in order, up to Rank
My site is slow or clunky on mobile
Diagnoses Core Web Vitals and mobile, fixes the causes
Engines don't understand my pages
Adds valid, honest structured data they can read
I can't risk breaking what already ranks
Audits safely, preserving URLs, canonicals and what works
Fixes keep silently breaking on deploys
Re-audits and catches regressions, even in CI
I'd also like AI answers to cite me
Adds the AEO layer, once the page can rank
Why doesn't it rank?
AI-built sites often look perfect in a browser but are nearly invisible to crawlers. Coding agents frequently edit JSX and declare "meta tags added" without verifying what's actually served in the built HTML. If a crawler receives a blank <div id="root">, your site can't rank, because to a search engine it isn't there.
Ranking in search is the goal, and it still starts with the fundamentals: a site that's crawlable, readable, well structured, and trustworthy. Get those right and the same foundations also make your pages eligible to be surfaced by AI answer engines like AI Overviews, ChatGPT and Perplexity. That's a layer on top, after the basics, not a replacement for them.
Most AI-built sites fail at the very bottom of the ladder. This skill pack fixes that, from the ground up.
See it on the served HTML
A site built as a single-page app looks perfect in your browser, and serves crawlers an empty shell. The pack checks what's actually served, and fixes it.
<body>
<div id="root"></div>
<script src="/app.js"></script>
</body>
# curl returns an empty shell.
# No headings, no copy. Invisible.<main>
<h1>Web design that converts</h1>
<p>Award-winning studio in Leeds…</p>
</main>
# curl now returns real content.
# Crawlable. Indexable. Citable.<head>
<meta charset="utf-8">
<meta name="viewport" ...>
</head>
# No title, no description.
# Nothing to show in the results.<head>
<title>Web design that converts | Studio</title>
<meta name="description" content="…">
<link rel="canonical" href="…">
</head>
# A real title and snippet.
# A reason to click.<!-- nothing here -->
# Engines can't identify what
# this page actually is.<script type="application/ld+json">
{ "@type": "Product",
"name": "…", "offers": {…} }
</script>
# A real entity, honestly marked up.
# Eligible for rich results.Verified by re-fetching the page, not by trusting that a source edit worked.
The Visibility Ladder
Begin with the foundation
Search visibility is built in a fixed order. The first four rungs make a page eligible; the fifth, Rank, is whether it's good and relevant enough to actually win. Diagnose top to bottom, fix bottom to top. AEO (being cited by AI answers) is the layer on top, after a page ranks, never instead of it.
Reach
Rung 1 of 5Can a crawler reach the page and see real content in the HTML it is served?
Read
Rung 2 of 5Is there genuine, readable content, accurate metadata, and a fast mobile experience?
Understand
Rung 3 of 5Can engines tell what the page is about, through valid structured data?
Connect
Rung 4 of 5Is the page wired into a coherent site, with internal links and clean canonicals?
Rank
Rung 5 of 5Is it the best, most relevant answer for the query? Real intent match, depth, and earned authority.
The first four rungs make a page eligible to compete. Rung five, Rank, is whether it deserves to win: the best match for the query, genuine depth, and authority you have actually earned. AEO, being cited in AI answers, is a layer on top for pages that already rank, never a replacement for ranking.
It's an audit that remembers
Not a one-shot fix. The pack writes a .seo/ folder into your project, so every run builds on the last, and catches regressions before they cost you.
First run
Audits all five rungs, fixes the safe wins, and records a baseline, a readable report, an issue tracker, and a history.
Every re-run
Re-verifies past fixes on the served HTML, catches regressions (a fix that quietly broke in a deploy), finds what's new, and advances.
In CI, automatically
Wire it into a deploy/PR check so a change that makes your site uncrawlable fails the build, not weeks later in lost traffic.
.seo/
├── audit.md # readable scorecard
├── state.json # every issue + status
└── log.md # dated run historyA skill for every part of SEO
The orchestrator routes broad requests; reach for a specialist when you already know the job. Technical foundations first, strategy and automation on top. Hover any skill for the technical detail.
Start here
The five rungs
On top of the ladder (AEO)
Technical specialists
Content & strategy
Automation & advanced
How do I install SEO for AI Agents?
Fastest start, paste this into your agent
No setup. Drop this prompt into Claude Code, Cursor, or any AI coding agent and let it run the audit on your site.
Use the seo-for-ai-agents skill pack (https://github.com/manibharij/seo-for-ai-agents): audit my site with the Visibility Ladder, verify on the served HTML, fix the lowest failing rung first, and explain each change in plain English. Never fabricate authors, reviews, or trust signals.
More prompts you can paste straight away
Once the pack is installed, reach for the right job. Each prompt routes to the correct skill on its own. Swap the bracketed parts for your own details.
Using seo-for-ai-agents, diagnose why [paste URL] isn't ranking. Work top-to-bottom through the Visibility Ladder on the served HTML, tell me the lowest failing rung, and explain the root cause before fixing anything.
Using seo-for-ai-agents, audit my live site without changing anything yet. Write the findings to .seo/, preserve all URLs and canonicals, and give me a prioritised list of fixes in dependency order with the risk of each.
Using seo-for-ai-agents, add valid, honest structured data to my pages. Only mark up entities that genuinely exist on the page, validate against rich-result requirements, and never fabricate reviews, ratings, or authors.
Using seo-for-ai-agents, I'm about to change my URLs / redesign / move domains. Inventory the current URLs, produce a 1:1 301 redirect map, update canonicals and sitemaps, and give me a post-launch checklist to confirm rankings transferred.
Using seo-for-ai-agents, set up the automation skill so served-HTML SEO checks run on every deploy and pull request and fail the build on a critical regression. Show me the GitHub Action and what it gates on.
Using seo-for-ai-agents, my page already ranks. Apply the AEO layer on top: make the answers extractable and quotable for AI answer engines, keep entities consistent, and don't touch what already works for search.
Install into your agent
Drop the skills folder into your agent's config directory or copy-paste a mini. No complex setup.
Ask it to audit your site
Tell your agent: 'Audit my SEO'. It detects your stack, finds the lowest failing rung, and dispatches fixes.
Review and approve
The agent explains every change in plain English. You decide what to publish. All fixes are reversible.
Supported Environments
Claude Code
~/.claude/skills/
Cursor
.cursor/rules/
AGENTS.md
For Codex, Zed, Gemini CLI
Copy-paste Minis
Zero config needed
Is SEO for AI Agents right for you?
For
- Developers and marketers who vibe-code with AI agents
- Anyone building a new site with Claude Code, Cursor, or Codex
- Developers whose AI-built site isn't showing up in Google
- Agencies and consultants who audit client sites
- Existing sites that need SEO health maintained over time
Not For
- Anyone expecting guaranteed rankings or citations
- People without an AI coding agent
- Those wanting live rank-tracking or backlink tools
- Black-hat or spam SEO
What doesn't SEO for AI Agents do?
Key distinctions
- Fixes owned-media SEO only (not link-building, not rank-tracking)
- Verifies on served HTML, not just source code edits
- Strictly white-hat, never fabricates authors, E-E-A-T signals, or reviews
- Works for existing sites too (protects URLs and canonicals that already rank)
Before you start
What this is, and what it isn't
This is an open-source skill pack that gives your AI agent a rigorous, white-hat SEO method. It is a capable assistant, not an autopilot, and not a replacement for judgement or experience.
Experimental, review everything
It is early and evolving. An AI agent can misread context or over-reach, so every change is yours to review before it ships. Human evaluation is still essential, treat the output as a well-argued draft, not gospel.
Ideal for newer builds
It is at its best on new or recent builds that aren't ranking yet, where it can lay clean foundations from the start and catch the issues AI-built sites tend to ship with.
On established sites, it supports an expert
For sites that already rank, treat it as support for an SEO professional, not a replacement. It preserves URLs and canonicals and flags risk, but a human should own changes to pages with traffic to protect.
It also cannot guarantee rankings or citations, those depend on factors outside any tool's control. Built on a fifteen-year, white-hat SEO mindset, designed to do the right things well, not to promise outcomes.
Frequently asked questions
Does it guarantee rankings or AI citations?
No, and anything that promises guaranteed rankings is misleading. It fixes build-time, owned-media SEO and improves your eligibility to rank and be cited. Whether a search engine ranks you, or an AI engine cites you, depends on competition, demand, and authority outside any tool's control.
Does it work on existing sites, or only new ones?
Both. On an existing site it audits without regressing what already ranks: it preserves URLs (adding redirects if any must change), respects intentional canonicals and noindex rules, and flags bigger changes for you to approve first.
What about WordPress, Shopify, or Webflow?
The diagnosis works on any site, because it reads the served HTML. On hosted platforms the fixes often live in the platform's settings or theme rather than code, so the agent tells you exactly what to change, rather than editing code it doesn't control.
Is it free? Do I need paid data tools or API keys?
It's free and open-source (MIT), and needs no paid data to work. You can optionally connect your own Search Console, DataForSEO, or Ahrefs keys to sharpen the audit, but nothing is paywalled or required.
Will it change my code without asking?
It applies safe, clearly-correct fixes and explains each one in plain English. Risky changes like restructuring URLs, removing content, or authorship and trust decisions are flagged for you to approve. You review before publishing, and everything stays in version control.
Which AI coding agents does it work with?
Claude Code, Cursor, and AGENTS.md hosts (Codex, Gemini CLI, Zed) via the skills, or a copy-paste mini in any chat. It's a skill pack the agent reads, not a separate app to run.