SVG Diagram Generation logo

SVG Diagram Generation

OrganizationPopular
CopilotKit
SVG Diagram Generation

Generating rich inline SVG diagrams to visually explain systems, processes, architectures, and abstract concepts.

Overview

PublisherCopilotKit
RepositoryOpenGenerativeUI
Skill nameSVG Diagram Generation
Stars
1.6K
Forks
202
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the SVG Diagram Generation 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/CopilotKit/OpenGenerativeUI.git /tmp/OpenGenerativeUI
mkdir -p .claude/skills
cp -r /tmp/OpenGenerativeUI/apps/agent/skills/svg-diagrams .claude/skills/copilotkit-svg-diagram-generation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable SVG Diagram Generation 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 SVG Diagram Generation 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 SVG Diagram Generation 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.

SVG Diagram Generation Skill

You can generate rich, inline SVG diagrams to visually explain concepts. Use this skill whenever a visual would help the user understand a system, process, architecture, or mechanism better than text alone.


Delivery

Diagrams ship through the generateSandboxedUi tool: the SVG markup goes in the html parameter, where it streams to the user element by element. SVG presentation attributes (fill, stroke, font-size) carry all styling here — if a diagram needs CSS animation classes, declare them in the css parameter, never in a <style> block inside html. Static diagrams need no jsFunctions or jsExpressions.


When to Use

  • Explaining how something works (load paths, circuits, pipelines, algorithms)
  • Showing architecture or structure (system diagrams, component layouts)
  • Illustrating processes or flows (flowcharts, data flow, decision trees)
  • Building intuition for abstract concepts (attention mechanisms, gradient descent, recursion)

SVG Setup

Always use this template:

svg
<svg width="100%" viewBox="0 0 680 H" xmlns="http://www.w3.org/2000/svg">
  <defs>
    <marker id="arrow" viewBox="0 0 10 10" refX="8" refY="5"
            markerWidth="6" markerHeight="6" orient="auto-start-reverse">
      <path d="M2 1L8 5L2 9" fill="none" stroke="context-stroke"
            stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round"/>
    </marker>
  </defs>
  <!-- Content here -->
</svg>
  • Width is always 680px via viewBox. Set width="100%" so it scales responsively.
  • H (height) = bottom-most element's y + height + 40px padding. Don't guess — compute it.
  • Safe content area: x=40 to x=640, y=40 to y=(H-40).
  • No wrapping divs, no <html>, <head>, <body>, or DOCTYPE.
  • Background is transparent — the host provides the background.

Core Design Rules

Typography

  • Two sizes only: 14px for titles/labels, 12px for subtitles/descriptions.
  • Two weights only: 400 (regular), 500 (medium/bold). Never use 600 or 700.
  • Font: Use font-family="system-ui, -apple-system, sans-serif" or inherit from host.
  • Always set text-anchor="middle" and dominant-baseline="central" for centered text in boxes.
  • Sentence case always. Never Title Case or ALL CAPS.

Text Width Estimation

At 14px, each character ~ 8px wide. At 12px, each character ~ 7px wide.

  • "Load Balancer" (13 chars) at 14px ~ 104px -> needs rect ~ 140px wide (with padding).
  • Always compute: rect_width = max(title_chars x 8, subtitle_chars x 7) + 48px padding.

Colors (Light/Dark Mode Safe)

Use these semantic color sets that work in both modes:

Teal:    fill="#E1F5EE" stroke="#0F6E56" text="#085041"  (dark: fill="#085041" stroke="#5DCAA5" text="#9FE1CB")
Purple:  fill="#EEEDFE" stroke="#534AB7" text="#3C3489"  (dark: fill="#3C3489" stroke="#AFA9EC" text="#CECBF6")
Coral:   fill="#FAECE7" stroke="#993C1D" text="#712B13"  (dark: fill="#712B13" stroke="#F0997B" text="#F5C4B3")
Amber:   fill="#FAEEDA" stroke="#854F0B" text="#633806"  (dark: fill="#633806" stroke="#EF9F27" text="#FAC775")
Blue:    fill="#E6F1FB" stroke="#185FA5" text="#0C447C"  (dark: fill="#0C447C" stroke="#85B7EB" text="#B5D4F4")
Gray:    fill="#F1EFE8" stroke="#5F5E5A" text="#444441"  (dark: fill="#444441" stroke="#B4B2A9" text="#D3D1C7")
Red:     fill="#FCEBEB" stroke="#A32D2D" text="#791F1F"  (dark: fill="#791F1F" stroke="#F09595" text="#F7C1C1")
Green:   fill="#EAF3DE" stroke="#3B6D11" text="#27500A"  (dark: fill="#27500A" stroke="#97C459" text="#C0DD97")
Pink:    fill="#FBEAF0" stroke="#993556" text="#72243E"  (dark: fill="#72243E" stroke="#ED93B1" text="#F4C0D1")

Color meaning, not sequence: Don't rainbow-cycle. Use 2-3 colors per diagram. Map colors to categories or physical properties (warm = heat/energy, cool = calm/cold, gray = structural/neutral).

If you're rendering inside a system that supports CSS variables, prefer:

  • var(--color-text-primary) for primary text
  • var(--color-text-secondary) for muted text
  • var(--color-border-tertiary) for light borders

Shapes & Layout

  • Stroke width: 0.5px for borders, 1.5px for arrows/connectors.
  • Corner radius: rx="4" for subtle rounding, rx="8" for emphasized. rx="20" for large containers.
  • Spacing: 60px minimum between boxes, 24px padding inside boxes, 12px text-to-edge clearance.
  • Single-line box: 44px tall. Two-line box: 56px tall.
  • Max 4-5 nodes per row at 680px width. If more, split into multiple diagrams.
  • All connectors need fill="none" — SVG defaults fill to black, which turns paths into black blobs.

Component Patterns

Single-Line Node

svg
<g>
  <rect x="100" y="20" width="180" height="44" rx="8"
        fill="#EEEDFE" stroke="#534AB7" stroke-width="0.5"/>
  <text x="190" y="42" text-anchor="middle" dominant-baseline="central"
        font-size="14" font-weight="500" fill="#3C3489">Node title</text>
</g>

Two-Line Node

svg
<g>
  <rect x="100" y="20" width="200" height="56" rx="8"
        fill="#E6F1FB" stroke="#185FA5" stroke-width="0.5"/>
  <text x="200" y="38" text-anchor="middle" dominant-baseline="central"
        font-size="14" font-weight="500" fill="#0C447C">Title</text>
  <text x="200" y="56" text-anchor="middle" dominant-baseline="central"
        font-size="12" fill="#185FA5">Short subtitle</text>
</g>

Arrow Connector

svg
<line x1="200" y1="76" x2="200" y2="120"
      stroke="#534AB7" stroke-width="1.5" marker-end="url(#arrow)"/>

Dashed Flow Indicator

svg
<line x1="200" y1="76" x2="200" y2="120"
      stroke="#534AB7" stroke-width="1.5" stroke-dasharray="4 3"/>

Leader Line with Label (for annotations)

svg
<line x1="440" y1="100" x2="500" y2="130"
      stroke="currentColor" stroke-width="0.5" stroke-dasharray="4 4" opacity="0.5"/>
<circle cx="440" cy="100" r="2" fill="currentColor" opacity="0.5"/>
<text x="506" y="134" font-size="12" fill="currentColor" opacity="0.7">Annotation text</text>

Large Container (for structural diagrams)

svg
<rect x="80" y="40" width="520" height="300" rx="20"
      fill="#E1F5EE" stroke="#0F6E56" stroke-width="0.5"/>
<text x="340" y="68" text-anchor="middle"
      font-size="14" font-weight="500" fill="#085041">Container name</text>

Diagram Types & When to Use Each

1. Flowchart

When: Sequential processes, decision trees, pipelines. Layout: Top-to-bottom or left-to-right. Single direction only. Rules:

  • Arrows must never cross unrelated boxes. Route around with L-bends if needed.
  • Keep all same-type boxes the same height.
  • Max 4-5 nodes per diagram. Break complex flows into multiple diagrams.

2. Structural Diagram

When: Containment matters — things inside other things (architecture, org charts, system components). Layout: Nested rectangles. Outer = container, inner = regions. Rules:

  • Max 2-3 nesting levels.
  • 20px minimum padding inside every container.
  • Use different color ramps for parent vs child to show hierarchy.

3. Illustrative Diagram

When: Building intuition. "How does X actually work?" Layout: Freeform — follows the subject's natural geometry. Rules:

  • Shapes can be freeform (paths, ellipses, polygons), not just rects.
  • Color encodes intensity, not category (warm = active, cool = dormant).
  • Overlap shapes for depth, but never let strokes cross text.
  • Labels go in margins with leader lines pointing to the relevant part.

Critical Checks Before Finalizing

  1. ViewBox height: Find your lowest element (max y + height). Set H = that + 40px.
  2. No content past x=640 or below y=(H-40).
  3. Text fits in boxes: (char_count x 8) + 48 < rect_width for 14px text.
  4. No arrows through boxes: Trace every line's path — if it crosses a rect, reroute.
  5. All <path> connectors have fill="none".
  6. All text has appropriate fill color — never rely on inheritance (SVG defaults to black).
  7. Colors work in dark mode: If using hardcoded colors, provide both light and dark variants. If using CSS variables, you're fine.

Multi-Diagram Approach

For complex topics, use multiple smaller SVGs instead of one dense one:

  • Each SVG should have 3-5 nodes max.
  • Write explanatory text between diagrams.
  • First diagram = overview, subsequent = zoom into subsections.
  • Never promise diagrams you don't deliver.

Example: Simple 3-Step Flow

svg
<svg width="100%" viewBox="0 0 680 260" xmlns="http://www.w3.org/2000/svg">
  <defs>
    <marker id="arrow" viewBox="0 0 10 10" refX="8" refY="5"
            markerWidth="6" markerHeight="6" orient="auto-start-reverse">
      <path d="M2 1L8 5L2 9" fill="none" stroke="context-stroke"
            stroke-width="1.5" stroke-linecap="round" stroke-linejoin="round"/>
    </marker>
  </defs>

  <!-- Step 1 -->
  <rect x="230" y="20" width="220" height="56" rx="8"
        fill="#E1F5EE" stroke="#0F6E56" stroke-width="0.5"/>
  <text x="340" y="38" text-anchor="middle" dominant-baseline="central"
        font-size="14" font-weight="500" fill="#085041">User request</text>
  <text x="340" y="56" text-anchor="middle" dominant-baseline="central"
        font-size="12" fill="#0F6E56">HTTP POST /api/data</text>

  <!-- Arrow 1->2 -->
  <line x1="340" y1="76" x2="340" y2="100" stroke="#534AB7"
        stroke-width="1.5" marker-end="url(#arrow)"/>

  <!-- Step 2 -->
  <rect x="230" y="106" width="220" height="56" rx="8"
        fill="#EEEDFE" stroke="#534AB7" stroke-width="0.5"/>
  <text x="340" y="124" text-anchor="middle" dominant-baseline="central"
        font-size="14" font-weight="500" fill="#3C3489">Server processing</text>
  <text x="340" y="142" text-anchor="middle" dominant-baseline="central"
        font-size="12" fill="#534AB7">Validate and transform</text>

  <!-- Arrow 2->3 -->
  <line x1="340" y1="162" x2="340" y2="186" stroke="#854F0B"
        stroke-width="1.5" marker-end="url(#arrow)"/>

  <!-- Step 3 -->
  <rect x="230" y="192" width="220" height="56" rx="8"
        fill="#FAEEDA" stroke="#854F0B" stroke-width="0.5"/>
  <text x="340" y="210" text-anchor="middle" dominant-baseline="central"
        font-size="14" font-weight="500" fill="#633806">Database write</text>
  <text x="340" y="228" text-anchor="middle" dominant-baseline="central"
        font-size="12" fill="#854F0B">INSERT into table</text>
</svg>

Tips for Great Diagrams

  • Less is more: A clean 4-node diagram teaches better than a cramped 12-node one.
  • Color = meaning: Warm colors for active/hot/important, cool for passive/cold/secondary, gray for structural.
  • Streaming effect: Since SVGs render top-to-bottom as tokens arrive, structure your elements top-down for a natural build-up animation.
  • Annotations on the side: Put explanatory labels in the right margin (x > 560) with leader lines pointing to the relevant element.
  • Consistent heights: All boxes of the same type should be the same height.
  • Whitespace is your friend: Don't fill every pixel. Breathing room makes diagrams readable.

Frequently asked questions

What does the SVG Diagram Generation AI skill do?

Generating rich inline SVG diagrams to visually explain systems, processes, architectures, and abstract concepts.

Why use SVG Diagram Generation on TypingMind?

Because you install it once and use it with any model. SVG Diagram Generation 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 SVG Diagram Generation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/CopilotKit/OpenGenerativeUI/tree/main/apps/agent/skills/svg-diagrams. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use SVG Diagram Generation?

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 SVG Diagram Generation?

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

Is the SVG Diagram Generation AI skill free?

Yes. It is published on GitHub by CopilotKit 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 👇