Drawio Diagram logo

Drawio Diagram

Community
automateyournetwork
drawio-diagram

Generate draw.io network diagrams — native .drawio files with CLI export (PNG/SVG/PDF), plus browser-based Mermaid/XML/CSV via MCP server. Use when creating network topology diagrams, generating architecture visuals, exporting diagrams to PNG or PDF, or building draw.io files from discovery data.

Overview

Publisherautomateyournetwork
Repositorynetclaw
Skill namedrawio-diagram
Stars
680
Forks
189
Bundled files
Instructions only
LicenseApache-2.0
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 automateyournetwork on GitHub. Read the source before you install it.

Installation

Install the Drawio Diagram 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/automateyournetwork/netclaw/tree/main/workspace/skills/drawio-diagram
  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/automateyournetwork/netclaw.git /tmp/netclaw
mkdir -p .claude/skills
cp -r /tmp/netclaw/workspace/skills/drawio-diagram .claude/skills/drawio-diagram
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Drawio Diagram 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 Drawio Diagram 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 Drawio Diagram 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.

Draw.io Network Diagrams

Generate network diagrams using two approaches:

  1. Native File Mode — Generate .drawio XML files on disk with optional PNG/SVG/PDF export via the draw.io desktop CLI (official jgraph skill-cli)
  2. Browser Mode — Open diagrams in the Draw.io browser editor via the @drawio/mcp MCP server (Mermaid, XML, or CSV input)

Installer note: native registration and the documented MCP_CALL invocation share the installed component launcher. Check readiness.json before first use; failed discovery is not device state. Existing write approvals still apply.

Mode 1: Native File Generation (Official Skill-CLI)

Generate native .drawio files directly. Optionally export to PNG, SVG, or PDF with the diagram XML embedded (so the exported file remains editable in draw.io).

How to Create a Diagram

  1. Generate draw.io XML in mxGraphModel format for the requested diagram
  2. Write the XML to a .drawio file in the current working directory using the Write tool
  3. If the user requested an export format (png, svg, pdf), export using the draw.io CLI with --embed-diagram, then delete the source .drawio file
  4. Open the result — the exported file if exported, or the .drawio file otherwise

Choosing the Output Format

Check the user's request for a format preference:

  • /drawio create a flowchart → flowchart.drawio
  • /drawio png flowchart for login → login-flow.drawio.png
  • /drawio svg: ER diagram → er-diagram.drawio.svg
  • /drawio pdf architecture overview → architecture-overview.drawio.pdf

If no format is mentioned, write the .drawio file and open it. The user can ask to export later.

Supported Export Formats

FormatEmbed XMLNotes
pngYes (-e)Viewable everywhere, editable in draw.io
svgYes (-e)Scalable, editable in draw.io
pdfYes (-e)Printable, editable in draw.io
jpgNoLossy, no embedded XML support

PNG, SVG, and PDF all support --embed-diagram — the exported file contains the full diagram XML, so opening it in draw.io recovers the editable diagram.

draw.io CLI

The draw.io desktop app includes a command-line interface for exporting.

Locating the CLI

Try drawio first (works if on PATH), then fall back to the platform-specific path:

  • macOS: /Applications/draw.io.app/Contents/MacOS/draw.io
  • Linux: drawio (typically on PATH via snap/apt/flatpak)
  • Windows: "C:\Program Files\draw.io\draw.io.exe"

Use which drawio (or where drawio on Windows) to check if it's on PATH before falling back.

Export Command
bash
drawio -x -f <format> -e -b 10 -o <output> <input.drawio>

Key flags:

  • -x / --export: export mode
  • -f / --format: output format (png, svg, pdf, jpg)
  • -e / --embed-diagram: embed diagram XML in the output (PNG, SVG, PDF only)
  • -o / --output: output file path
  • -b / --border: border width around diagram (default: 0)
  • -t / --transparent: transparent background (PNG only)
  • -s / --scale: scale the diagram size
  • --width / --height: fit into specified dimensions (preserves aspect ratio)
  • -a / --all-pages: export all pages (PDF only)
  • -p / --page-index: select a specific page (1-based)
Opening the Result
  • macOS: open <file>
  • Linux: xdg-open <file>
  • Windows: start <file>

File Naming

  • Use a descriptive filename based on the diagram content (e.g., login-flow, database-schema)
  • Use lowercase with hyphens for multi-word names
  • For export, use double extensions: name.drawio.png, name.drawio.svg, name.drawio.pdf — this signals the file contains embedded diagram XML
  • After a successful export, delete the intermediate .drawio file — the exported file contains the full diagram

Mode 2: Browser Editor via MCP Server

Open diagrams directly in the Draw.io browser editor using the @drawio/mcp MCP server. Supports three input formats.

Mermaid Diagrams (best for quick topology graphs)

bash
python3 $MCP_CALL "npx -y @drawio/mcp" open_drawio_mermaid '{"content":"graph TD\n  A --> B"}'

XML Diagrams (best for detailed, styled diagrams with precise positioning)

bash
python3 $MCP_CALL "npx -y @drawio/mcp" open_drawio_xml '{"content":"<mxGraphModel>...</mxGraphModel>"}'

CSV Diagrams (best for device inventories)

bash
python3 $MCP_CALL "npx -y @drawio/mcp" open_drawio_csv '{"content":"## label: %name%\nname,refs\nA,B\nB,C"}'

All three tools accept optional "lightbox": true for read-only view and "dark": "auto"|"true"|"false" for dark mode.

The tool returns a Draw.io URL. Share it directly — the diagram opens in the browser editor where it can be edited, exported, or saved.


XML Format Reference

A .drawio file is native mxGraphModel XML. Always generate XML directly — Mermaid and CSV formats require server-side conversion and cannot be saved as native files.

Basic Structure

Every diagram must have this structure:

xml
<mxGraphModel>
  <root>
    <mxCell id="0"/>
    <mxCell id="1" parent="0"/>
    <!-- Diagram cells go here with parent="1" -->
  </root>
</mxGraphModel>
  • Cell id="0" is the root layer
  • Cell id="1" is the default parent layer
  • All diagram elements use parent="1" unless using multiple layers

Common Styles

Rounded rectangle:

xml
<mxCell id="2" value="Label" style="rounded=1;whiteSpace=wrap;" vertex="1" parent="1">
  <mxGeometry x="100" y="100" width="120" height="60" as="geometry"/>
</mxCell>

Diamond (decision):

xml
<mxCell id="3" value="Condition?" style="rhombus;whiteSpace=wrap;" vertex="1" parent="1">
  <mxGeometry x="100" y="200" width="120" height="80" as="geometry"/>
</mxCell>

Arrow (edge):

xml
<mxCell id="4" value="" style="edgeStyle=orthogonalEdgeStyle;" edge="1" source="2" target="3" parent="1">
  <mxGeometry relative="1" as="geometry"/>
</mxCell>

Labeled arrow:

xml
<mxCell id="5" value="Yes" style="edgeStyle=orthogonalEdgeStyle;" edge="1" source="3" target="6" parent="1">
  <mxGeometry relative="1" as="geometry"/>
</mxCell>

Useful Style Properties

PropertyValuesUse for
rounded=10 or 1Rounded corners
whiteSpace=wrapwrapText wrapping
fillColor=#dae8fcHex colorBackground color
strokeColor=#6c8ebfHex colorBorder color
fontColor=#333333Hex colorText color
shape=cylinder3shape nameDatabase cylinders
shape=mxgraph.flowchart.documentshape nameDocument shapes
ellipsestyle keywordCircles/ovals
rhombusstyle keywordDiamonds
edgeStyle=orthogonalEdgeStylestyle keywordRight-angle connectors
edgeStyle=elbowEdgeStylestyle keywordElbow connectors
dashed=10 or 1Dashed lines
swimlanestyle keywordSwimlane containers

Diagram Types for Network Engineering

1. Physical Topology Diagram

Shows devices, physical links, interface names, IP addresses, and link speeds.

bash
python3 $MCP_CALL "npx -y @drawio/mcp" open_drawio_mermaid '{"content":"graph TD\n  R1[\"R1\\nCore Router\\n10.255.255.1\"]\n  R2[\"R2\\nCore Router\\n10.255.255.2\"]\n  SW1[\"SW1\\nDist Switch\\n10.255.255.3\"]\n  R1 -->|\"Gi0/0 -- Gi0/0\\n10.1.1.0/30\"| R2\n  R1 -->|\"Gi0/1 -- Gi0/1\\n10.1.2.0/30\"| SW1\n  R2 -->|\"Gi0/1 -- Gi0/1\\n10.1.3.0/30\"| SW1"}'

2. Logical Topology Diagram

Shows routing protocol relationships, areas, AS numbers, VRFs.

bash
python3 $MCP_CALL "npx -y @drawio/mcp" open_drawio_mermaid '{"content":"graph TD\n  subgraph \"OSPF Area 0\"\n    R1[\"R1 ABR\"]\n    R2[\"R2 ABR\"]\n  end\n  subgraph \"OSPF Area 1\"\n    R3[\"R3\"]\n  end\n  R1 --- R2\n  R1 --- R3"}'

3. Security Zones Diagram

Shows firewalls, DMZs, trust boundaries, ACL enforcement points.

bash
python3 $MCP_CALL "npx -y @drawio/mcp" open_drawio_mermaid '{"content":"graph LR\n  subgraph \"Untrusted\"\n    INET((Internet))\n  end\n  subgraph \"DMZ\"\n    WEB[\"Web Server\"]\n  end\n  subgraph \"Trusted\"\n    CORE[\"Core Switch\"]\n  end\n  INET --> FW[\"Firewall\"]\n  FW --> WEB\n  FW --> CORE"}'

CRITICAL: XML Well-Formedness

  • NEVER use double hyphens (--) inside XML comments. -- is illegal inside <!-- --> per the XML spec and causes parse errors. Use single hyphens or rephrase.
  • Escape special characters in attribute values: &amp;, &lt;, &gt;, &quot;
  • Always use unique id values for each mxCell

When to Use Each Mode

ScenarioModeWhy
Generate .drawio file for version controlNative FileProduces actual file on disk
Export PNG/SVG/PDF for documentationNative FileCLI export with embedded XML
Quick topology preview from discovery dataBrowserInstant visual in browser
CSV-based inventory diagramBrowserCSV format only available via MCP
Mermaid syntax diagramBrowserMermaid conversion only via MCP
Offline/air-gapped environmentNative FileNo network needed
Sharing a link to the diagramBrowserReturns shareable URL

Integration with Other Skills

  • Use pyats-topology to discover the network, then generate diagrams from the data
  • Use netbox-reconcile to color-code links by reconciliation status (documented/undocumented/missing)
  • Use markmap-viz for hierarchical views alongside Draw.io for topology views
  • Use aci-fabric-audit data to generate ACI fabric topology diagrams
  • Use gait-session-tracking to record diagram generation with source data references

Frequently asked questions

What does the Drawio Diagram AI skill do?

Generate draw.io network diagrams — native .drawio files with CLI export (PNG/SVG/PDF), plus browser-based Mermaid/XML/CSV via MCP server. Use when creating network topology diagrams, generating architecture visuals, exporting diagrams to PNG or PDF, or building draw.io files from discovery data.

Why use Drawio Diagram on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/automateyournetwork/netclaw/tree/main/workspace/skills/drawio-diagram. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Drawio Diagram?

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 Drawio Diagram?

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

Is the Drawio Diagram AI skill free?

Yes. It is published on GitHub by automateyournetwork under the Apache-2.0 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 👇