drawio
Has your agent generate draw.io diagrams and export them to various formats. It's useful for visualizing data structures, systems, or workflows.
What it does
This tool creates visual diagrams, like flowcharts or org charts, from descriptions. It can save the diagram as a `.drawio` file and export it as an image (PNG, SVG, PDF).
When to use it
- ✓Create a flowchart for a process.
- ✓Draw an organizational chart for a company.
- ✓Visualize a system's architecture.
Example of what to ask your AI
“Create a simple flowchart showing the steps to make coffee, saving it as a PNG.”
Want more? Open the sections below.
How to use
The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.
Skill link
Ready-to-paste message
How it works
You describe the diagram you want, and the tool turns it into special code (XML) that the draw.io program understands. It then saves this code to a file and can convert it into an image.
Installation
Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.
In the terminal (Claude Code, Codex, Cursor), in your project folder:
npx skills add github/awesome-copilot --skill drawioOr download just the file:
curl -L https://raw.githubusercontent.com/github/awesome-copilot/main/skills/drawio/SKILL.md -o SKILL.mdTechnical content (original SKILL.md)
Original text by the author, straight from GitHub.
Draw.io Diagram Skill
Generate draw.io diagrams as native .drawio files and export them to PNG images that can be embedded in Word documents.
How to Create a Diagram
- Generate draw.io XML in
mxGraphModelformat for the requested diagram - Write the XML to a
.drawiofile using the create/edit file tool - Export to PNG using the bundled export script
Bundled Export Script
This skill includes drawio-to-png.mjs, a Node.js export script with two rendering backends:
- draw.io CLI (pixel-perfect, fastest) — used automatically if draw.io desktop is installed
- Official draw.io viewer in headless browser (pixel-perfect, needs Chromium/Edge) — fallback when CLI is unavailable
Usage
# Install dependencies (one-time, from the scripts folder)
cd skills/drawio/scripts && npm install
# Export a single diagram
node skills/drawio/scripts/drawio-to-png.mjs <input.drawio> [output.png]
# Export all .drawio files in a directory
node skills/drawio/scripts/drawio-to-png.mjs --dir <directory>
# Force a specific renderer
node skills/drawio/scripts/drawio-to-png.mjs --renderer=cli|viewer|auto <input.drawio>
Skill Folder Contents
| File | Purpose |
|---|---|
SKILL.md |
This instruction file |
scripts/drawio-to-png.mjs |
Node.js export script (CLI + browser fallback) |
scripts/package.json |
Dependencies (puppeteer-core) |
Supported Export Formats
| Format | Embed XML | Notes |
|---|---|---|
png |
Yes | Viewable everywhere, editable in draw.io |
svg |
Yes | Scalable, editable in draw.io |
pdf |
Yes | Printable, editable in draw.io |
Draw.io XML Style Conventions
Use these styles for consistent, professional diagrams:
<!-- Primary service (highlighted) -->
<mxCell style="rounded=1;whiteSpace=wrap;html=1;fillColor=#dae8fc;strokeColor=#6c8ebf;strokeWidth=2;arcSize=12;shadow=1;" />
<!-- External system -->
<mxCell style="rounded=1;whiteSpace=wrap;html=1;fillColor=#f5f5f5;strokeColor=#666666;" />
<!-- Success/processing stage -->
<mxCell style="rounded=1;whiteSpace=wrap;html=1;fillColor=#d5e8d4;strokeColor=#82b366;" />
<!-- Warning/quality gate -->
<mxCell style="rounded=1;whiteSpace=wrap;html=1;fillColor=#fff2cc;strokeColor=#d6b656;" />
<!-- Error/failure path -->
<mxCell style="rounded=1;whiteSpace=wrap;html=1;fillColor=#f8cecc;strokeColor=#b85450;" />
<!-- Data store (cylinder) -->
<mxCell style="shape=cylinder3;whiteSpace=wrap;html=1;fillColor=#fff2cc;strokeColor=#d6b656;" />
<!-- Arrow -->
<mxCell style="edgeStyle=orthogonalEdgeStyle;rounded=1;strokeColor=#6c8ebf;strokeWidth=2;" />
Locating the draw.io CLI
Try drawio first (works if on PATH), then fall back:
- Windows:
"C:\Program Files\draw.io\draw.io.exe" - macOS:
/Applications/draw.io.app/Contents/MacOS/draw.io - Linux:
drawio(via snap/apt/flatpak)
CLI Export Command
drawio -x -f png -e -b 10 -o <output.png> <input.drawio>
Flags: -x (export), -f (format), -e (embed diagram XML), -b (border), -o (output path).
FAQ
What is a .drawio file?
It's a file containing all your diagram's information, allowing you to edit it later in the draw.io program.
Can I edit the diagram after exporting to PNG?
Yes, if the PNG was created with embedded XML (which is the default), you can open it in draw.io to edit.
How does the AI know how to draw the diagram?
You need to describe the diagram to the AI, telling it what elements (boxes, arrows, text) to include and how they connect.
Details
Original description by the author
Generate draw.io diagrams as .drawio files and export to PNG/SVG/PDF with embedded XML
repo: github/awesome-copilot
Popularity
- GitHub stars
- 40k
- Ranking position
- #5127
- License
- MIT
- Updated
- 10/15/2026
Comments
- …
More skills from this repository
acquire-codebase-knowledge
Helps your agent understand and document an existing code project. It's useful for onboarding new people or getting an overview of the architecture.
github/awesome-copilot
acreadiness-assess
Enables your agent to assess a project's readiness for AI and generate a report. It's useful for understanding how well a project is prepared to use AI tools.
github/awesome-copilot
acreadiness-generate-instructions
Helps your agent create instructions for AI tools based on an assessment. It's useful for improving how AI interacts with code and closing identified gaps.
github/awesome-copilot
acreadiness-policy
Enables your agent to help define or apply policies for AI project assessment. It's useful for standardizing how projects are evaluated and ensuring compliance.
github/awesome-copilot
Similar skills
accessibility
Helps your agent create interfaces that everyone can use. Ensures websites and apps work well for people with disabilities, like those who are blind or have reduced mobility.
affaan-m/ECC
design-system
Helps your agent create a design system from existing code. It extracts visual information and checks for consistency, generating a report and an interactive preview.
affaan-m/ECC
liquid-glass-design
Helps your agent create iOS user interfaces with a 'Liquid Glass' effect. Allows adding dynamic and interactive visual effects in SwiftUI and UIKit.
affaan-m/ECC