Architecture logo

Architecture

OrganizationPopular
markdown-viewer
architecture

Create layered system architecture diagrams using HTML/CSS templates with color-coded tiers and grid layouts. Best for technology stacks, microservices topology, and multi-tier application design.

Overview

Publishermarkdown-viewer
Repositoryskills
Skill namearchitecture
Stars
3.3K
Forks
190
Bundled files
25
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.

  • 25 bundled files

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

  • Open source

    Published by markdown-viewer on GitHub. Read the source before you install it.

Installation

Install the 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.
  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/markdown-viewer/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/architecture .claude/skills/architecture
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable 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 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 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.

Architecture Diagram Generator

Quick Start: Create HTML structure with flexible layout (single/double/triple column) → Define CSS styles for layers and grids → Add content with categorized panels → Use semantic colors for different layers.

Critical Rules

Rule 1: Direct HTML Embedding

IMPORTANT: Write architecture diagrams as direct HTML in Markdown. NEVER use code blocks (```html). The HTML should be embedded directly in the document without any fencing.

Rule 2: No Empty Lines in HTML Structure

CRITICAL: Do NOT add any empty lines within the HTML architecture diagram structure. Keep the entire HTML block continuous to prevent parsing errors.

Rule 3: Incremental Creation Approach

RECOMMENDED: Create architecture diagrams in multiple steps:

  1. First: Create the overall framework (wrapper, sidebars, main structure) and define all CSS styles
  2. Second: Add layer containers with titles
  3. Third: Fill in components layer by layer
  4. Fourth: Add detailed content and refinements

Rule 4: Flexible Layout Structure

Architecture diagrams can use flexible layouts based on complexity:

  • Single Column: Main content only (for simple architectures)
  • Two Column: Main content + one sidebar (left or right)
  • Three Column: Full layout with both sidebars (for complex systems)
    • Left Sidebar: Supporting systems (monitoring, operations, analytics)
    • Main Content: Core architecture layers (user, application, data, infrastructure)
    • Right Sidebar: Cross-cutting concerns (security, compliance, governance)

Rule 5: Layer-Based Organization

Each layer should have:

  • Clear semantic meaning (User, Application, AI/Logic, Data, Infrastructure)
  • Consistent color coding
  • Grid-based layout for components
  • Appropriate nesting for sub-components

Rule 6: Color Semantics

Use consistent semantic meaning for layers — the exact color palette varies by style (see examples). The standard semantic mapping:

  • User Layer — user-facing interfaces and clients
  • Application Layer — business logic and API services
  • AI/Logic Layer — intelligence, rules, processing engines
  • Data Layer — databases, caches, storage
  • Infrastructure Layer — containers, networking, DevOps
  • External Services — third-party APIs, cloud services (typically dashed border)

Style Examples

Choose a visual style that matches your project's tone and audience. Each example contains a complete, copy-ready HTML template.

#StyleFileSuitable For
1Steel Bluestyles/steel-blue.mdConsulting reports, banking/finance, government projects, RFP proposals
2Ember Warmstyles/ember-warm.mdRetail/e-commerce, education platforms, lifestyle brands, cultural institutions
3Neon Darkstyles/neon-dark.mdTech talks, developer conferences, gaming platforms, cybersecurity dashboards
4Stark Blockstyles/stark-block.mdCreative studios, education platforms, indie developers, tech blogs
5Ocean Tealstyles/ocean-teal.mdTravel platforms, logistics/shipping, green tech, weather/ocean projects
6Dusk Glowstyles/dusk-glow.mdSocial media, entertainment platforms, martech, content creation tools
7Rose Bloomstyles/rose-bloom.mdFashion/beauty, luxury brands, wedding platforms, premium memberships
8Sage Foreststyles/sage-forest.mdHealthcare, agritech, clean energy, sustainability, bioinformatics
9Frost Cleanstyles/frost-clean.mdDesign tools, developer docs, API references, minimalist SaaS
10Indigo Deepstyles/indigo-deep.mdBrand-consistent systems, enterprise white papers, internal platforms
11Pastel Mixstyles/pastel-mix.mdSaaS products, startups, general tech architecture, product docs
12Slate Darkstyles/slate-dark.mdEnterprise dark mode, internal tools, developer dashboards

Layout Examples

Choose a layout structure that fits your architecture's complexity. Layouts use wireframe style (no colors) to focus on structural patterns. Combine any layout with any style above.

#LayoutFileBest For
1Three-Columnlayouts/three-column.mdComplex systems with cross-cutting concerns and monitoring sidebars
2Single Stacklayouts/single-stack.mdSimple services, microservice detail views, focused documentation
3Left Sidebarlayouts/left-sidebar.mdSystems with operations/monitoring emphasis, DevOps-centric views
4Right Sidebarlayouts/right-sidebar.mdSystems with security/compliance emphasis, governance-focused views
5Pipelinelayouts/pipeline.mdData pipelines, CI/CD flows, ETL processes, horizontal stage-based flows
6Two-Column Splitlayouts/two-column-split.mdBefore/after comparisons, dual-system views, migration architecture
7Dashboardlayouts/dashboard.mdSystem overviews with KPIs, monitoring dashboards, executive summaries
8Grid Cataloglayouts/grid-catalog.mdService catalogs, component libraries, equal-weight microservices
9Banner + Centerlayouts/banner-center.mdGateway-centric architectures, user-facing systems with shared infrastructure
10Nested Containerslayouts/nested-containers.mdCloud deployments, VPC/network topology, environment isolation
11Layer Layoutslayouts/layer-layouts.mdPer-layer layout patterns: grid, sub-group, product group, KPI, vertical stack, zones, inline pipeline, mixed width
12Connectorslayouts/connectors.mdSVG overlay connectors between components: solid/dashed lines, arrows, labels, curved & orthogonal paths

Advanced Features

NOTE: These advanced components require additional CSS styles. Add these to your <style scoped> section:

css
.arch-product-group { display: flex; gap: 10px; }
.arch-product { flex: 1; border-radius: 8px; padding: 10px; background: rgba(255, 255, 255, 0.6); border: 1px dashed #d97706; }
.arch-product-title { font-size: 12px; font-weight: bold; color: #92400e; margin-bottom: 8px; text-align: center; }
.arch-subgroup { display: flex; gap: 8px; margin-top: 8px; }
.arch-subgroup-box { flex: 1; border-radius: 6px; padding: 8px; background: rgba(255, 255, 255, 0.5); border: 1px solid rgba(0, 0, 0, 0.08); }
.arch-subgroup-title { font-size: 10px; font-weight: bold; color: #374151; text-align: center; margin-bottom: 6px; }
.arch-user-types { display: flex; gap: 4px; justify-content: center; margin-top: 6px; }
.arch-user-tag { font-size: 9px; padding: 2px 6px; border-radius: 10px; background: rgba(59, 130, 246, 0.15); color: #1d4ed8; }
/* SVG connector lines between components */
.arch-conn { stroke: #94a3b8; stroke-width: 1.5; fill: none; }
.arch-conn-dashed { stroke: #94a3b8; stroke-width: 1.5; fill: none; stroke-dasharray: 6 4; }
.arch-conn-label { font-size: 9px; fill: #64748b; font-family: sans-serif; }

Custom Product Groups

For complex applications with multiple products/modules:

html
<div class="arch-product-group">
  <div class="arch-product">
    <div class="arch-product-title">🎯 Product A</div>
    <div class="arch-grid arch-grid-2">
      <div class="arch-box">Feature 1<br><small>Description</small></div>
      <div class="arch-box highlight">Feature 2<br><small>Key Feature</small></div>
    </div>
  </div>
  <div class="arch-product">
    <div class="arch-product-title">📊 Product B</div>
    <div class="arch-grid arch-grid-2">
      <div class="arch-box">Feature 3<br><small>Description</small></div>
      <div class="arch-box">Feature 4<br><small>Description</small></div>
    </div>
  </div>
</div>

Sub-grouped Components

For detailed breakdowns within layers:

html
<div class="arch-subgroup">
  <div class="arch-subgroup-box">
    <div class="arch-subgroup-title">Component Group A</div>
    <div class="arch-grid arch-grid-3">
      <div class="arch-box tech">Service 1<br><small>Details</small></div>
      <div class="arch-box tech">Service 2<br><small>Details</small></div>
      <div class="arch-box tech">Service 3<br><small>Details</small></div>
    </div>
  </div>
  <div class="arch-subgroup-box">
    <div class="arch-subgroup-title">Component Group B</div>
    <div class="arch-grid arch-grid-2">
      <div class="arch-box tech">Service 4<br><small>Details</small></div>
      <div class="arch-box tech">Service 5<br><small>Details</small></div>
    </div>
  </div>
</div>

User Types/Tags

html
<div class="arch-user-types">
  <span class="arch-user-tag">Admin Users</span>
  <span class="arch-user-tag">End Users</span>
  <span class="arch-user-tag">API Clients</span>
  <span class="arch-user-tag">Partners</span>
</div>

Metrics and KPIs

html
<div class="arch-sidebar-item metric">99.9% Uptime</div>
<div class="arch-sidebar-item metric">&lt;200ms Response</div>
<div class="arch-sidebar-item metric">1M+ Users</div>

SVG Connectors Between Components

Use an SVG overlay to draw orthogonal (right-angle) connectors between components. Always use <path> with M/L commands for strictly horizontal and vertical segments. Do NOT use <line>, Bézier curves, or diagonal lines. See layouts/connectors.md for full reference.

html
<!-- Wrap diagram content in a relative container -->
<div style="position: relative;">
  <!-- ...layers and components here... -->
  <!-- SVG overlay as last child -->
  <svg style="position: absolute; top: 0; left: 0; width: 100%; height: 100%; pointer-events: none; overflow: visible;">
    <defs>
      <marker id="arrowhead" markerWidth="8" markerHeight="6" refX="8" refY="3" orient="auto">
        <path d="M0,0 L8,3 L0,6" fill="none" stroke="#94a3b8" stroke-width="1"/>
      </marker>
    </defs>
    <!-- Orthogonal solid arrow (vertical → horizontal → vertical) -->
    <path d="M 200,72 L 200,90 L 400,90 L 400,108" class="arch-conn" marker-end="url(#arrowhead)"/>
    <!-- Orthogonal dashed line -->
    <path d="M 600,72 L 600,90 L 600,90 L 600,108" class="arch-conn-dashed" marker-end="url(#arrowhead)"/>
    <!-- Label -->
    <text x="420" y="86" class="arch-conn-label">data flow</text>
  </svg>
</div>

Styling Reference

Common Classes (shared across all styles)

  • .arch-wrapper — flex container for sidebar + main layout
  • .arch-sidebar — fixed-width sidebar column
  • .arch-main — flexible main content area
  • .arch-layer — layer container (add semantic class: .user, .application, .ai, .data, .infra, .external)
  • .arch-box — component box; .arch-box.highlight for key items; .arch-box.tech for smaller tech items
  • .arch-grid-2 to .arch-grid-6 — grid column layouts
  • .arch-sidebar-panel — sidebar panel container
  • .arch-sidebar-item — sidebar item; .arch-sidebar-item.metric for highlighted metrics

Best Practices

HTML Usage Guidelines

  1. Direct embedding only — Always embed HTML directly in Markdown, never use ```html code blocks
  2. No empty lines in structure — Keep the entire HTML block continuous without any empty lines
  3. Incremental development — Build diagrams step by step:
    • Start with basic framework and layout structure (single/two/three column as needed)
    • Add empty layer containers with proper CSS classes
    • Fill in content layer by layer from top to bottom
    • Refine content and add highlights last

Architecture Design

  1. Keep layers logically separated — Each layer should represent a clear architectural tier
  2. Use consistent naming — Follow naming conventions for components and services
  3. Highlight key components — Use .highlight class for critical components
  4. Add technical details — Include technology stack info in <small> tags
  5. Balance information density — Don't overcrowd components with text
  6. Use icons sparingly — Add emojis to titles for visual hierarchy
  7. Maintain color semantics — Stick to the established color meanings
  8. Consider responsive design — Grids automatically adapt to content

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 Architecture AI skill do?

Create layered system architecture diagrams using HTML/CSS templates with color-coded tiers and grid layouts. Best for technology stacks, microservices topology, and multi-tier application design.

Why use Architecture on TypingMind?

Because you install it once and use it with any model. 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 Architecture in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/markdown-viewer/skills/tree/main/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 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 Architecture?

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

Is the Architecture AI skill free?

It is published on GitHub by markdown-viewer. Check the repository for licensing terms. 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 👇