site-architecture

Trigger phrases

Phrases that activate this skill when typed to Claude Code:

• site map
• site structure
• page hierarchy
• information architecture
• URL structure

What it does

site-architecture is a Claude Code skill from Corey Haines’s marketing-skills repo. It turns Claude into an information architect who plans the page hierarchy, navigation, URL patterns, breadcrumb structure, and internal-linking topology so users and search engines both find their way. The skill activates when you mention “sitemap”, “site structure”, “page hierarchy”, “information architecture”, or “URL structure”.

The output of a session is a site-architecture plan: visual hierarchy (hub-and-spoke or pyramid), navigation menus (primary/secondary/footer), URL pattern rules, breadcrumb logic, internal-linking strategy with priority pages, and a redirect map if migrating from an existing structure.

When to use it

Reach for it when:

• You’re building a new site or launching a major redesign and want architecture-first
• You inherited a site whose URL structure is incoherent and SEO is suffering
• You’re planning a content program (clusters, programmatic SEO) and need the IA to support it

When not to reach for it:

• It’s a single landing page; architecture is overkill
• You need an XML sitemap; that’s a technical SEO output, not architecture (use seo-audit)

Install

The skill is distributed via Corey Haines’s marketing-skills repo. Install via the repo’s recommended path — copy the site-architecture SKILL.md into your project’s .claude/skills/site-architecture/ directory, or use the repo’s plugin install if you’ve set it up.

Once installed, the skill activates on the trigger phrases above. The first time it runs, it will check for .agents/product-marketing-context.md (or .claude/product-marketing-context.md) — populating that file with your product context first dramatically improves output quality across all of Haines’s marketing skills.

What a session looks like

A typical session has three phases:

1. Page inventory + intent map. Every page mapped to a search intent and a buyer-journey stage. Pages with no intent and no journey-stage are flagged for cut.
2. Hierarchy + URLs. Hub-and-spoke or pyramid based on content type, URL pattern rules (no dates in URLs, lowercase, hyphens), breadcrumb logic.
3. Internal-linking + migration. Priority pages identified for hub-link concentration, link patterns from clusters to hubs, redirect map if migrating from old structure.

The discipline that makes it work: every page has to earn its URL. Architecture punishes pages that can’t articulate their intent and journey-stage.

Receipts

Honest reporting on what site-architecture produces and where it has limits:

Where it works well:

• The intent + journey-stage filter cuts dead pages that quietly weigh down crawl budget
• Hub-and-spoke hierarchies built into the IA make internal linking mechanical instead of guesswork
• URL-pattern rules prevent the “/blog/2019/05/12/post-name” mistake that haunts sites for years

Where it backfires:

• IA without content is a wireframe; the skill scopes the structure but you still need to populate it
• Redirect maps for big migrations are tedious; the skill scopes but doesn’t substitute for QA

Pattern that works: lock the URL pattern at architecture time. URL changes after launch require redirects, and redirects accumulate compounding tech debt.

Source and attribution

Originally written by Corey Haines. The canonical SKILL.md and any supporting files live in the site-architecture folder of his marketing-skills repository.

License: MIT. You can install, adapt, and redistribute the skill, with attribution preserved.

This page documents the skill from a practitioner’s perspective. For the formal spec and any updates, defer to the source repo.