Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →aiskillstore/site-structure-optimizer
Use when the user asks to "plan my site structure", "design the page hierarchy / navigation / URL taxonomy", "fix internal linking", or "find orphan pages"; runs two modes — architecture (hierarchy, nav, URL patterns, hub/spoke clusters, Mermaid site maps) and linking (link graph, authority flow, anchor text, orphan disposition, source/target/anchor plan) — and outputs a structure score /100 plus a handoff summary. Not for external backlinks — use offsite-signal-analyzer; not for XML sitemap or
Passed 19 of 22 test cases with the skill, and 4 of 22 without it.
and 22 more in the full report
15 fixed4 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.
We want to save our completed architecture plan for domain example.com generated on 2026-03-30. What exact path should be used for storing the summary?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies directory path under memory/seo-geo/optimize/site-structure-optimizer/ | Missed | Passed |
The instructions your model reads when the skill loads.
Works one lever of site structure at two altitudes. Architecture mode designs the whole-site information architecture — page hierarchy, navigation, URL taxonomy, hub/spoke topic clusters, link topology — and renders Mermaid site maps that make orphans and link islands visible. Linking mode optimizes the links inside an existing structure — link graph, authority flow, anchor text, orphan disposition — and delivers a prioritized source/target/anchor plan. Both emit a structure score /100 and a handoff summary.
Scope guard: this skill does not compute the CORE-EEAT score or run vetoes (T04, C01, R10) — that is the content-quality-auditor gate. It does not analyze external backlinks (offsite-signal-analyzer) or diagnose XML sitemaps / indexation (technical-seo-checker). It works the structure lever and hands off.
| Mode | Altitude | Use when | Core outputs |
|---|---|---|---|
architecture | Whole-site layout | New build or restructure; the layout itself is the question | ASCII hierarchy tree, URL map table, nav spec, hub/spoke plan, Mermaid site map, architecture score /100 |
linking | Links inside an existing layout | Pages exist; the question is how they connect | Orphan list + disposition, anchor-text distribution, contextual link plan (source/target/anchor), structure score /100 |
Pick the mode from --mode if given. Otherwise infer: "plan / design structure / URL taxonomy / hub-spoke / sitemap" → architecture; "fix internal linking / orphan pages / anchor text / authority flow" → linking. If the request spans both (e.g., "restructure the site AND fix the links"), run architecture first, then hand off to linking (see Next Best Skill) — do not silently interleave.
Start with one of these prompts, then finish with the standard handoff summary from Skill Contract.
# architecture mode
Plan the site structure for a new SaaS marketing site
Restructure my existing site — pages feel buried and disorganized
Design the URL taxonomy and navigation for [domain]
Map hub/spoke topic clusters for my blog around [topic]
# linking mode
Analyze internal linking structure for [domain/sitemap]
Find orphan pages on [domain]
Suggest internal links for this new article: [content/URL]
Optimize anchor text across the site
Expected output (mode-dependent): architecture mode → a page hierarchy (ASCII tree), a URL map table, a navigation spec, a hub/spoke link plan, a Mermaid site map flagging orphans/islands, an architecture score /100. Linking mode → a scored diagnosis, orphan list with disposition, anchor distribution check, and a prioritized source/target/anchor plan (structure score /100). Both emit a short handoff summary ready for memory/seo-geo/optimize/site-structure-optimizer/.
memory/seo-geo/optimize/site-structure-optimizer/.memory/open-loops.md with status pending-decision.test cases passed, vs 4 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.