AEO answer optimizer Claude skill

Use this when buyers ask AI assistants which tool to use and your brand is missing or described wrongly. AI answers favour sources that state facts clearly, answer the question directly and are confirmed by other sources.

Inputs

• The category, product and the facts that define it (who it is for, pricing model, key capabilities, integrations).
• The pages that should be cited: home, product, pricing, comparisons, docs.
• The questions buyers ask (from sales calls, search and support).

The play

1. Map the questions

Group buyer questions by type: "what is", "best tools for", "x vs y", "how to", "how much does", "is x good for <use case>". Prioritise commercial questions where a recommendation is made.

2. Audit current answers

Ask several assistants the top questions. Record whether you are mentioned, what is said, which sources are cited and what is wrong or outdated. Repeat monthly; answers change.

3. Rewrite pages for extraction

Read references/aeo-checklist.md for the page-level checklist. The core:

• Lead each section with a direct, one or two sentence answer, then the detail.
• State facts plainly and consistently across pages: what it is, who it is for, price, limits.
• Use comparison tables with clear criteria; assistants reuse tables well.
• Name entities precisely: product names, categories, integrations, use cases.
• Keep facts fresh and dated where they change.

4. Make it machine-readable

Organization, Product or SoftwareApplication, FAQPage and Article schema; a clean sitemap; fast, crawlable HTML (key text not hidden behind scripts); an llms.txt summary with links to the most important pages; and no blocking of the AI crawlers you want to be cited by.

5. Build corroboration

Assistants trust facts confirmed elsewhere: review sites, directories, partner pages, community answers, credible articles. Make sure third-party descriptions match your own.

Output format

Question map: <question - type - priority - currently mentioned? - cited sources>
Wrong or missing facts: <...>
Page fixes: <page - change - why>
Schema and technical: <...>
Corroboration targets: <sources to update or earn>
Re-check: <date and questions to re-run>

What good looks like

• One consistent fact sheet about the product, reused everywhere.
• Comparison and "best for" pages that are honest about fit; assistants pick up balanced sources.
• Progress measured by mentions and citations on the priority questions, checked monthly.
• The common mistake is writing for keywords alone, with answers buried in paragraph four of a long intro.

Rules

• MUST keep every claim accurate and consistent across pages.
• MUST measure with repeatable question sets over time, not one-off screenshots.
• NEVER publish fake reviews, fake third-party pages or hidden text aimed at AI crawlers.
• NEVER make claims about competitors you cannot support.

Example prompts

• "Audit how AI assistants describe us for ‘best AI SDR tools’ and fix our pages."
• "Rewrite our pricing page so answer engines quote it correctly."
• "Build a monthly AEO tracking sheet for our 20 most important buyer questions."

Content

• [ ] The page’s main question is answered in the first 1-2 sentences.
• [ ] Each H2 is a question or a clear topic, and its first sentence answers it.
• [ ] Facts are stated plainly: "X is a <category> for <who>. It costs <price> per <unit>."
• [ ] Product name, category and audience are used consistently with other pages.
• [ ] Comparison tables have explicit criteria and honest "best for" rows.
• [ ] Numbers carry a source or a date.
• [ ] A short FAQ answers the 5-8 most common questions in 40-80 words each.
• [ ] No important text exists only in images, tabs that need clicks, or scripts.

Technical

• [ ] Server-rendered HTML with the main content present on load.
• [ ] Organization schema (name, logo, sameAs profiles).
• [ ] SoftwareApplication or Product schema with offers where pricing is public.
• [ ] FAQPage schema matching the visible FAQ.
• [ ] Article schema with author and dates on content pages.
• [ ] Sitemap includes the page; canonical is correct.
• [ ] robots.txt allows the assistants’ crawlers the business wants to be cited by.
• [ ] llms.txt at the root lists the key pages with one-line descriptions.

Fact sheet (keep one, reuse everywhere)

Corroboration sources to check

• Review and software directory profiles.
• Integration partners’ listing pages.
• Community answers and forum threads about the category.
• Articles and lists that rank for "best <category>" queries.
• The company’s own social profiles and bios.

Each one should describe the product the same way as the fact sheet.