Site Architecture logo

Site Architecture

CommunityPopular
fcakyon
site-architecture

Use when planning or restructuring what pages a site has and how they connect: hierarchy, navigation, URL patterns, breadcrumbs, and internal linking. Not for XML sitemaps, which are in seo-audit.

Overview

Publisherfcakyon
Repositoryclaude-codex-settings
Skill namesite-architecture
Stars
1.2K
Forks
113
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by fcakyon on GitHub. Read the source before you install it.

Installation

Install the Site Architecture AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/seo-skills/skills/site-architecture
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/fcakyon/claude-codex-settings.git /tmp/claude-codex-settings
mkdir -p .claude/skills
cp -r /tmp/claude-codex-settings/plugins/seo-skills/skills/site-architecture .claude/skills/site-architecture
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Site Architecture in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Site Architecture on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Site Architecture is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Site architecture

Architecture is one decision repeated: how does someone get from the homepage to the page that answers their question, and how does a crawler follow the same path. Depth, navigation, URLs, and internal links are four views of that one structure, so change them together or they drift.

Depth

Aim to put any page that matters within three clicks of the homepage. It isn't a law, but a critical page four or more levels down is a symptom worth chasing.

ShapeFitsCosts
Flat, 2 levelsSmall sites, portfoliosStops scaling once a nav item has 20 children
Moderate, 3 levelsMost SaaS and content sitesUsually the right answer
Deep, 4 or moreLarge catalogs, big docsScales, but buries things without strong linking

Go as flat as the navigation tolerates. When a dropdown passes roughly 20 items, that's the signal to add a level rather than keep the list flat.

Levels: L0 is the homepage, L1 is a primary section (/features, /blog), L2 is a page within it (/features/analytics), L3 and beyond are detail pages (/docs/api/authentication).

Site types as starting points

TypeDepthSectionsURL shape
SaaS marketing2 to 3Home, Features, Pricing, Blog, Docs/features/{name}, /blog/{slug}
Content site2 to 3Home, Blog, Categories, About/blog/{slug}, /blog/category/{slug}
Ecommerce3 to 4Home, Categories, Products/{category}/{subcategory}/{product}
Documentation3 to 4Home, Guides, Reference/docs/{section}/{page}
SaaS plus content3 to 4Home, Product, Blog, Resources, Docs/product/{feature}, /blog/{slug}
Small business1 to 2Home, Services, About, Contact/services/{name}

URLs

Readable, lowercase, hyphenated, mirroring the hierarchy, with one trailing-slash policy enforced everywhere. Short but still descriptive: /blog/landing-page-conversions beats /blog/how-to-improve-your-landing-page-conversion-rates.

The mistakes that cost the most:

  • Dates in blog URLs. /blog/2026/07/25/title adds nothing and ages the post visibly.
  • IDs or query strings carrying content. /product/12345 and /blog?id=123 should be slugs.
  • Over-nesting past what the hierarchy needs.
  • Mixing parents for the same kind of page, like /features/analytics alongside /product/automation.
  • Changing a URL without a 301. Every old URL needs one, or the links pointing at it stop counting and anyone who bookmarked it gets a 404. This is the single most common cause of traffic loss after a redesign.

references/patterns.md has the URL pattern per page type, navigation layouts, and the diagram formats to hand back.

Navigation

Primary navigation holds 4 to 7 items, ordered by importance, with the logo linking home and the call to action rightmost. Past 7, people stop reading the list and start hunting.

Footers group into columns: product, resources, company, legal. Sidebars carry within-section navigation for docs and long content. Breadcrumbs mirror the URL path exactly, with every segment linked except the current page, and they pair with BreadcrumbList schema.

Breadcrumbs are the cheapest structural win available: they add internal links on every page, they make hierarchy legible to a crawler, and they can earn a richer result.

Internal linking

  • No orphans. Every page needs at least one internal link pointing at it, and the sitemap is not a link.
  • Anchor text describes the destination. Never "click here" or "read more".
  • How many contextual links a single page carries is a decision for whoever owns that page's format, so recommend the connections worth making rather than a density target.
  • Link the pages that matter more often. Inbound internal links are how you tell a crawler what's important.
  • Hub and spoke for content clusters: one comprehensive hub, spokes covering sub-topics, each spoke linking back to the hub, the hub linking to all spokes, and spokes cross-linking where a reader would actually want it.

Hub and spoke is what makes a set of posts add up to more than its pages, because it concentrates the signal on the hub rather than spreading it across a dozen equal posts competing with each other.

What to hand back

An ASCII tree of the hierarchy with the URL at each node, a URL map table (page, URL, parent, where it appears in navigation, priority), the redirect list when anything moves, and a Mermaid diagram when the structure is worth seeing rather than reading. references/patterns.md has the formats.

Sources

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Site Architecture AI skill do?

Use when planning or restructuring what pages a site has and how they connect: hierarchy, navigation, URL patterns, breadcrumbs, and internal linking. Not for XML sitemaps, which are in seo-audit.

Why use Site Architecture on TypingMind?

Because you install it once and use it with any model. Site Architecture is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Site Architecture in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/seo-skills/skills/site-architecture. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Site Architecture?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Site Architecture?

As many as you like. As long as a model supports skills, you can use Site Architecture with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Site Architecture AI skill free?

Yes. It is published on GitHub by fcakyon under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇