20 Advanced Claude Prompts for Technical SEO Audits, Site Architecture, and AEO

Act as a Senior Technical SEO Architect. I am auditing [Insert URL / Domain]. Here is a raw export of technical SEO errors from my audit tool:

[Paste crawl error data, e.g., 404s, 5xx errors, redirect chains, missing canonicals, or broken assets]

Analyze these issues and prioritize them based on their direct risk to Google's crawl budget, indexation, and organic rankings. For each issue:
1. Identify the Root Cause in plain English.
2. Assign a Priority Level (Critical, High, Medium, Low).
3. Provide a Step-by-Step Action Plan to resolve it.
4. Specify whether this requires developer intervention or can be fixed via CMS settings.

Act as an Enterprise Technical SEO Consultant. Here is a list of URLs from my website currently flagged in Google Search Console under Page Indexing:

Status: [Specify either: "Discovered – currently not indexed" OR "Crawled – currently not indexed"]
[Paste URL list along with page titles or page categories]

Analyze these patterns and tell me:
1. If "Discovered": Is this a crawl budget deficit, server performance limitation, or internal link depth problem?
2. If "Crawled": Is this an indicator of thin content, programmatic duplication, or weak search intent alignment?
3. Group these URLs by their likely root cause and provide an actionable triage roadmap to get them moved into the "Valid / Indexed" state.

Act as a Senior Technical SEO Engineer. Here is a raw export of server access logs for Googlebot hits on my website:

[Paste sample log lines: IP, Timestamp, HTTP Method, Requested URL, Status Code, User Agent]

Analyze this log sample and report on:
1. Status Code Breakdown: What percentage of Googlebot requests return 200, 301/302, 404, or 5xx responses?
2. Directory Crawl Distribution: Which URL directories receive the highest crawl attention, and which priority sections are being ignored?
3. Crawl Waste Indicators: Are there excessive hits to faceted navigation, sorting parameters, staging paths, or non-critical static assets?
4. Concrete Recommendations: Provide specific robots.txt rules and server response optimizations to conserve crawl equity for high-converting pages.

Act as a Technical SEO Auditor. Here is my current robots.txt file and a sample of key URLs with their respective meta robots tags and canonical directives:

[Paste robots.txt content]
[Paste URLs with their current Canonical tag, Meta Robots directives, and internal linking status]

Audit these instructions for contradictions:
1. Are any URLs disallowed in robots.txt while also containing canonical tags or incoming internal links?
2. Are any pages set to `noindex` that serve as self-canonicals or canonical targets for other pages?
3. Do any robots.txt rules block critical CSS or JavaScript files required by Googlebot's Web Rendering Service (WRS)?

Provide a corrected robots.txt configuration and an implementation checklist for page-level meta directives.

My website uses faceted filtering and URL query parameters for user sorting, filtering, and session tracking. Here are examples of parameter URLs generated by users:

[Paste parameterized URLs, e.g., ?sort=price, ?filter_color=blue, ?category=tech&session=abc]

Build a clean parameter handling framework:
1. Identify which parameters add organic search value (justifying dedicated indexable landing pages) and which represent duplicate content.
2. Define the proper handling mechanism for each parameter type (Canonicalization, Robots.txt Disallow, `noindex, follow`, or removal via CMS config).
3. Provide instructions on how frontend internal links within filter components should be coded to prevent search bots from falling into crawler traps.

I am auditing a JavaScript-heavy page on my site. Below are two versions of the HTML:

1. Raw Server Response HTML (View Page Source):
[Paste raw HTML]

2. Rendered DOM HTML (Browser Inspect Element):
[Paste rendered DOM]

Compare both versions and identify:
1. What critical content elements (H1-H3 headings, body text, image tags) exist only in the rendered DOM and are missing from the raw server response?
2. Are there internal links injected purely via client-side JavaScript that risk remaining unparsed during Google's first-wave crawl?
3. Were canonical tags, title tags, or structured data altered or injected after client-side scripts executed?
4. Recommend whether Server-Side Rendering (SSR) or Static Site Generation (SSG) adjustments are required for this template.

Here is the schema markup code currently implemented on my page (or state "None, build from scratch" for [Insert Page Topic/Type]):

[Paste JSON-LD code block if available]

Review this code against the latest Schema.org specifications and Google Search Central guidelines:
1. Validate Schema types used (e.g., Organization, TechArticle, FAQPage, Person, Product).
2. Check for missing required properties and absent recommended fields that unlock rich snippets.
3. Fix syntax or nesting errors (such as missing commas, incorrect `@context`, or unclosed brackets).

Provide a completeness score out of 10, explain any vulnerabilities, and output the corrected, production-ready JSON-LD code.

I am providing the HTML source code of my page [Insert URL]. Analyze the Hn heading structure (H1, H2, H3 hierarchy), the Title tag, and the Meta Description:

[Paste HTML source]

Identify:
1. Missing, duplicate, or multiple H1 tags.
2. Broken heading hierarchies (e.g., skipping from an H1 directly to an H3).
3. Title tag length, keyword placement, and click-through optimization.
4. Meta description alignment with search intent and length guidelines.

Present your findings in a Markdown table with columns: Element, Current State, Issue Detected, and Recommended Fix.

Act as a Technical SEO and Web Performance Specialist. My website scored [X] on mobile and [X] on desktop in Google PageSpeed Insights. My field Core Web Vitals metrics are:
- Largest Contentful Paint (LCP): [X]
- Interaction to Next Paint (INP): [X]
- Cumulative Layout Shift (CLS): [X]

The flagged diagnostic issues include:
[Paste flagged items from PageSpeed Insights, e.g., render-blocking resources, unoptimized images, main-thread work]

Tell me:
1. Which of these issues directly harm search rankings under Google's Page Experience signals versus those that are purely UX recommendations?
2. Prioritize the fixes by SEO impact versus engineering effort.
3. Provide a step-by-step implementation guide my development team can follow immediately.

I am auditing multi-regional and multi-language variations for my website. Here are the target URLs and the hreflang tags currently implemented in the HTML header:

[Paste `` code blocks]

Verify this implementation against Google's internationalization standards:
1. Confirm ISO 639-1 language codes and ISO 3166-1 Alpha-2 country codes are formatted accurately (e.g., en-US, es-ES).
2. Check for missing reciprocal self-referential tags across all URL variations.
3. Ensure an appropriate `x-default` URL is defined for unmatched visitor regions.
4. Output the fully corrected, production-ready `` snippet.

Here is the URL structure and XML sitemap data for my site:

[Paste URL list or XML sitemap content]

Act as an Enterprise Technical SEO Architect. Analyze this architecture and identify:
1. Potential orphan pages (URLs isolated from the logical directory taxonomy).
2. URL format inconsistencies (such as mixed casing, missing trailing slashes, or unnecessary query strings).
3. Topical hub opportunities: How can these URLs be reorganized into clear topic clusters that distribute internal PageRank effectively?

Provide a prioritized list of architectural cleanups.

I am restructuring URLs on my website. Here is my list of legacy URLs and the proposed target URLs:

[Paste old URLs alongside new URLs or structural path changes]

Build a tiered redirect mapping plan:
1. Group URLs by redirect pattern (exact 1-to-1 match, regex directory-level rewrite, query string consolidation).
2. Write production-ready configuration rules for my web server environment ([Specify: Nginx, Apache .htaccess, Cloudflare, or Next.js config]).
3. Identify potential redirect chains or loops in this mapping.
4. Outline pre-launch QA testing steps to ensure zero loss of backlink equity.

Act as an SEO Strategist specializing in site architecture. My website covers these main topic areas and pillar pages:

[List your primary pillar hubs and supporting cluster articles]

Build an internal linking matrix for this content cluster:
1. Define which pages serve as primary pillar hubs versus supporting child nodes.
2. Outline the exact linking flow: Which pages should link up, across, or down within the cluster?
3. Provide recommended contextual anchor text variations for each link to maximize semantic relevance without triggering spam filters.

Here is an export of internal links pointing to my primary landing page [Insert Target URL]:

[Paste list of Source URLs and their respective Anchor Texts]

Review this internal anchor text profile:
1. Flag instances of exact-match over-optimization that appear artificial or manipulative.
2. Identify vague or non-descriptive anchors (e.g., "read more", "link", "here") that fail to provide topical context to search engines.
3. Rewrite these anchor texts into natural, entity-rich variations that clearly describe the destination content.

Act as an expert SEO analyst. Here is a list of raw keywords related to [Topic]:

[Paste raw keyword list]

Group these keywords into distinct clusters based on shared search intent:
1. Group into: Informational, Navigational, Commercial Investigation, or Transactional intent.
2. For each cluster, designate one primary H1 title for a main pillar page and three supporting subtopic titles.
3. Flag any keywords that should NOT be targeted on separate pages to prevent internal cannibalization.

Here is a list of articles on my website targeting similar search queries, along with their performance metrics:

[Paste list of URLs, target keywords, monthly impressions, and organic clicks]

Audit this content cluster for keyword cannibalization and topical overlap:
1. Identify the single "Hero" URL that should remain as the primary authoritative resource.
2. Recommend which secondary pages should be pruned, updated, or merged into the hero page.
3. Provide explicit HTTP status instructions for each URL: 301 redirect to hero, 410 Gone for worthless thin pages, or keep with refined search intent.

Act as an Answer Engine Optimization (AEO) and Generative Engine Optimization (GEO) expert. Below is a section from my article on [Topic]:

[Paste article excerpt]

Rewrite this section so it is primed for extraction by Google AI Overviews, Perplexity, and Claude:
1. Lead with a direct, 40-to-50-word definitive answer sentence right at the top (formatted as an extraction block).
2. Incorporate recognized named entities, formal terminology, and related industry concepts.
3. Add a clean Markdown table or bulleted list that summarizes key comparisons or components for easy automated parsing.

I am writing an in-depth guide on [Topic] targeting the keyword [Keyword]. Here are the heading outlines (H1, H2, H3) from the top three ranking articles on Google:

[Paste competitor outlines]

Analyze their structure and identify:
1. Content gaps: What critical technical details, edge cases, or practical steps did all three competitors omit?
2. Redundancies: What surface-level filler can be removed to improve content conciseness?
3. Generate a comprehensive, differentiated content outline that provides deeper technical value and outperforms their content.

Act as a Generative Search Optimization specialist. Below is a draft section from my article on [Topic]:

[Paste article excerpt]

Rewrite this text using the C.I.T.E.D. optimization model to maximize citation probability across generative answer engines:
1. **C - Concise Answer:** Provide a self-contained 40-word definition at the beginning.
2. **I - Identified Entities:** Disambiguate all concepts using official organization names, technical standards, and recognized protocols.
3. **T - Truth Signals:** Insert specific metrics, benchmarks, or data references that validate the statements.
4. **E - Explicit Structure:** Use Markdown bolding, tables, and ordered lists to organize technical steps.
5. **D - Direct Context:** Eliminate vague transitional phrasing ("In today's fast-paced world...") and focus purely on actionable guidance.

I want to establish an AI crawler governance policy and generate an `llms.txt` file for my website.

Here is my site information:
- Domain: [Your Domain]
- Primary Focus: [Describe site topic, e.g., Technical SEO & AI Automation]
- Core Pillar URLs to Promote: [Paste 5–8 high-priority URLs]
- Paths to Restrict from AI Scraping: [e.g., admin, client portals, internal search results]

Provide:
1. An updated `robots.txt` configuration defining explicit crawl rules for `GPTBot`, `ClaudeBot`, `PerplexityBot`, and `Google-Extended`.
2. A standards-compliant `/llms.txt` file in clean Markdown that summarizes the site's authoritative resources for LLM reading engines.