SEO & GEO/AEO

Verified against ChatGPT · 2026-07-24

Plan the internal links a new page needs before it goes live

Maps which existing pages should link to a new page, with what anchor text, which sections of the new page should link back out, and whether the new page is at real risk of launching as an orphan with no natural path in.

ChatGPTClaudeGemini3 fillable variables

The prompt

Ready to copy — highlighted parts are example details you can swap.

You are an information architect optimizing internal link equity, not scattering related-posts links after the fact.

NEW PAGE: Title: "How Much Does a Website Redesign Cost in 2026?" — target keyword: website redesign cost — summarizes pricing ranges by project size
EXISTING PAGES ON THE SITE (with a one-line topic note each): /services/web-development — service overview page
/blog/signs-you-need-a-website-redesign — high-traffic blog post
/pricing — general pricing page
CURRENT SITE NAVIGATION STRUCTURE: Top nav: Home, Services, Blog, Pricing, Contact — Services has a dropdown for Web Development, Branding, SEO

TASK

1. INBOUND LINKS. Which existing pages should link TO the new page, and why specifically? Prioritize pages that are topically close and already carry meaningful traffic or authority — a high-traffic blog post is worth far more as a linking source than a page nobody visits, even if the second page is a closer topical match on paper. For each recommended source, name the exact paragraph or section where the link would sit naturally, not just "somewhere on this page."
2. ANCHOR TEXT. Suggest the exact anchor text for each inbound link. Descriptive and topically relevant, never "click here" or a bare URL — and varied enough across the different source pages that it doesn't read as manufactured, since identical anchor text repeated from many sources is itself a pattern search engines discount.
3. OUTBOUND LINKS. Which sections of the new page should link OUT to existing pages? Map specific subtopics in the new page to the single most relevant existing page for that subtopic — not a generic "related posts" block bolted onto the bottom.
4. PILLAR VS. SIBLING. Flag any existing page that's a natural pillar this new page should feed into and be linked from prominently, versus pages that are lateral siblings deserving a mention but not a hub relationship.
5. ORPHAN RISK. If too few existing pages are topically close enough to justify a natural, non-forced link, say so plainly — that's usually a sign the page needs a home in the nav or category structure rather than more inline links stretched to reach it. Check Top nav: Home, Services, Blog, Pricing, Contact — Services has a dropdown for Web Development, Branding, SEO specifically for whether this new page has any structural path a crawler would actually follow, independent of inline links.
6. LINK DEPTH. Estimate how many clicks from the homepage the new page will sit at once these links are in place, and flag it if that depth is deeper than 3-4 clicks, since pages buried that deep get crawled and re-crawled less frequently regardless of how relevant their inbound anchors are.

OUTPUT
A table: Source page | Anchor text | Links to | Reason. Follow it with the pillar/sibling notes, the orphan-risk verdict, and the estimated click depth.

Customize

Optional — swap in your own details for the highlighted parts above.

Why this works

Internal links distribute authority from a site's stronger pages to newer or weaker ones — a new page linked prominently from a high-traffic post inherits some of that page's crawl priority and topical signal, while an unlinked page can sit un-crawled or under-indexed regardless of how good the content itself is, which is why the prioritization rule favors traffic and authority over a merely closer topical match on paper. Descriptive, varied anchor text gives search engines an explicit topical signal about the destination page that goes beyond what the destination page says about itself — and the variety requirement specifically guards against a pattern that reads as manufactured: identical anchor text repeated from many different source pages toward one destination is a signature search engines are tuned to discount rather than reward, so uniformity is a cost, not free reinforcement. The click-depth estimate matters because crawl frequency correlates with how deep in a site's structure a page sits, independent of how relevant its inbound links are — a page that's topically perfect but four or five clicks from the homepage still gets crawled less often than a shallower, less-linked one, which is exactly the kind of structural problem inline anchor-text tweaks alone cannot fix and that only shows up when depth is measured explicitly rather than assumed to be fine.

What you get back

Source page | Anchor text | Links to | Reason /blog/signs-you-need-a-website-redesign | "what a redesign typically costs" | new page | High-traffic post, directly upstream in the reader's decision path, natural mid-article insertion point /services/web-development | "see current redesign pricing" | new page | Service page already discusses redesign; natural pillar relationship Pillar: /services/web-development is the pillar; new page and /blog/signs-you-need-a-website-redesign are siblings feeding into it. Orphan risk: none — two strong natural sources exist. Click depth: 2 clicks from homepage (Home > Services > new page), well within a healthy range.

Verified against

ChatGPT GPT-5.1 · 2026-07-24

Gemini Gemini 3 Pro · 2026-07-19

Changelog

  • 2026-07-24 Initial publish, verified against ChatGPT and Gemini 3 Pro.
  • 2026-08-01 Added the click-depth estimate after realizing a page can pass every anchor-text and pillar check while still being buried too deep in nav structure for regular re-crawling.

Building this for real?

This is a free starting point. If you'd rather have SEO built and running for your business, that's Scult's day job.

EXPLORE SEO
All SEO & GEO/AEO prompts

Check your AI visibility

One URL in, a 0–100 score and the exact fixes out.

RUN THE CHECK

Browse all the tools

15 tools across six categories
13 of them never send your data anywhere

Free · No signup · No trial clock

SEE THE DIRECTORY