CCM
/Skills
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Claude Code Marketplaces

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Skill index
  • MCP index
  • Marketplace index
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by mertbuilds.com

Independent project, not affiliated with Anthropic
julianoczkowski avatar

Information Architecture

julianoczkowski/designer-skills
4.6k installs497 stars
Summary

You're about to wire up routing or build navigation and realize you should probably figure out where everything goes first. This sits between the design brief and actual implementation, mapping out your site structure, navigation patterns, URL conventions, and user flows. It reads your existing routing setup (Next.js app directory, React Router, whatever you have), interviews you about how users will actually move through the thing, then writes a structured IA document. The real win is it forces you to answer the hard questions about navigation depth and content priority before you're three components deep and regretting your choices. Run it after you know what you're building but before you create tasks.

Install to Claude Code

npx -y skills add julianoczkowski/designer-skills --skill information-architecture --agent claude-code

Installs into .claude/skills of the current project.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Files
SKILL.mdView on GitHub

This skill defines the structural skeleton of a product or site. It sits between the design brief and the build. Run this after the brief is written and before tasks are created.

Example prompts

  • "Plan the IA for this app before I start building"
  • "Map out the navigation and page structure"
  • "I need to organize the content for a documentation site"
  • "Define user flows for the onboarding experience"

Process

  1. Look for an existing design brief at .design/*/DESIGN_BRIEF.md. If multiple subfolders exist, use the most recently modified one, or ask the user which feature they are working on. If no brief exists, ask the user what they are building and for whom.

  2. Explore the existing codebase to understand what structure already exists:

    • Routing: Next.js app/ or pages/ directory, React Router config, Vue Router, SvelteKit routes, or static HTML page files
    • Navigation components: header, sidebar, navbar, breadcrumb, footer components
    • Layout components: root layouts, nested layouts, page wrappers, container components
    • Page directories: how pages are currently organized in the file system
    • URL patterns: existing slugs, dynamic segments, query parameter conventions
    • CMS or data layer: content models, API routes, data fetching patterns, MDX/content directories
    • If structure exists, this skill extends and improves it. Do not propose a new architecture that ignores what is already built.
  3. Interview the user about structural decisions. For each question, provide your recommended answer.

    Cover at minimum:

    • What are the primary things a user needs to find or do? Rank by frequency.
    • How many levels of navigation depth are acceptable?
    • What content will grow over time vs. what is fixed?
    • Are there distinct user types who need different entry points?
    • What is the one page/view where the user spends 80% of their time?
  4. Once you have a shared understanding, produce the IA document using the template below and save it as INFORMATION_ARCHITECTURE.md in the same .design/<feature-slug>/ subfolder as the design brief.

IA Document Template

# Information Architecture: [Product/Site Name]

## Site Map

A hierarchical map of every page or view. Use indentation to show nesting. Include the URL pattern for each.

- Home `/`
  - Feature A `/feature-a`
    - Sub-page `/feature-a/detail`
  - Feature B `/feature-b`
- Settings `/settings`
  - Profile `/settings/profile`

## Navigation Model

Describe the navigation system:
- **Primary navigation**: What appears in the main nav? Maximum items.
- **Secondary navigation**: Sidebar, tabs, or contextual links within sections.
- **Utility navigation**: Account, settings, help, and anything outside the main content hierarchy.
- **Mobile navigation**: How navigation adapts. Hamburger, bottom tabs, or something else.

## Content Hierarchy

For each major page or view, define the content priority:

### [Page Name]
1. [Highest priority content] -- Why this comes first
2. [Second priority] -- Why this comes second
3. [Third priority] -- Rationale
4. [Below the fold / secondary]

## User Flows

The critical paths through the product. Each flow is a sequence of steps with decision points noted.

### [Flow Name] (e.g., "New user onboarding" or "Create a project")
1. User lands on [page]
2. User sees [content/prompt]
3. User takes action: [action]
   - If [condition A] -> [outcome]
   - If [condition B] -> [outcome]
4. User arrives at [destination]

## Naming Conventions

A glossary of terms used in the interface. Consistency matters. Pick one word and use it everywhere.

| Concept | Label in UI | Notes |
|---------|-------------|-------|
| [thing] | [what we call it] | [why this word] |

## Component Reuse Map

Which structural components (layouts, containers, navigation elements) are shared across pages.

| Component | Used on | Behavior differences |
|-----------|---------|---------------------|
| [layout/component] | [pages] | [any variations] |

## Content Growth Plan

Which sections of the site will accumulate content over time and how the IA accommodates that growth (pagination, filtering, search, archive patterns).

## URL Strategy

Rules for URL construction:
- Pattern: [e.g., `/section/subsection/item-slug`]
- Dynamic segments: [what is parameterized]
- Query parameters: [filtering, sorting, pagination]
Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Categories
Code Review & QualityProductivity & PlanningDesign & UI/UX
First SeenMay 16, 2026
View on GitHub

More from julianoczkowski/designer-skills

All 8 skills →
  • Design Review4.6k
  • Frontend Design4.5k
  • Grill Me4.5k
  • Design Brief4.4k
  • Design Flow4.4k
  • Brief To Tasks4.3k
  • Design Tokens4.6k

Recommended

More Code Review & Quality →
julianoczkowski avatar
design-review

julianoczkowski/designer-skills

Run a structured design critique against the brief and codebase. Checks visual hierarchy, consistency, responsiveness, accessibility, and aesthetic fidelity. Use when user wants a design review, critique, QA pass, polish pass, or mentions "review" after building.
4.6k
497
affaan-m avatar
quality-nonconformance

affaan-m/everything-claude-code

quality nonconformance
4.6k
229.1k
claude-office-skills avatar
contract-review

claude-office-skills/skills

Analyze contracts for risks, check completeness, and provide actionable recommendations. Supports employment contracts, NDAs, service agreements, and more.
4.5k
368
vinvcn avatar
improve-codebase-architecture

vinvcn/mattpocock-skills-zh-cn

扫描代码库中的深化机会,生成可视化 HTML 报告,然后围绕你选中的候选项继续追问。
4.2k
3k
affaan-m avatar
hexagonal-architecture

affaan-m/everything-claude-code

hexagonal architecture
4.2k
229.1k
alwaysmeticulous avatar
meticulous-review

alwaysmeticulous/skills

Analyze a completed Meticulous test run — fetch the diff summary, inspect representative screenshots, DOM diffs, and timelines. Resolves the test run from the local repo's current commit (the default), or from an explicit test-run ID or commit SHA. Use when asked to review Meticulous test results, or while reviewing or babysitting a pull/merge request to assess and fix a failing Meticulous Tests CI check.
4k
7