SkillFoxx

Type a name, a task or a service

drawio-ai-kit

Skills and a CLI that teach an agent to draw valid draw.io diagrams for AWS, Azure, GCP, Databricks and BPMN with structure checks

Skill

Medium risk

We rate an entry medium when the tool runs code, makes network calls or reads project files. Check what exactly it does before installing.

Why this level

  • Installs a global CLI and runs shell commands
  • Writes diagram files into the project
All reasons and checks

sparklabx/drawio-ai-kitAuthor:sparklabx

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/drawio-ai-kit

Detects the agents on your machine, checks the risk and pins the version.

Other ways to install

Run in a terminal in the project folder

npx skills add sparklabx/drawio-ai-kit --skill drawio-aws -a claude-code -y

The skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.

Without third-party tools, from commit 6a19ef5
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/sparklabx/drawio-ai-kit.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skills/drawio-aws/
git -C "$tmp" checkout 6a19ef512fa91aca37abd685b2e06a06d0333eeb
mkdir -p .claude/skills
cp -R "$tmp/skills/drawio-aws" .claude/skills/drawio-aws

Commands for macOS and Linux, on Windows run them in Git Bash.

Run in a terminal in the project folder

npx skills add sparklabx/drawio-ai-kit --skill drawio-aws -a cursor -y

The skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.

Without third-party tools, from commit 6a19ef5
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/sparklabx/drawio-ai-kit.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skills/drawio-aws/
git -C "$tmp" checkout 6a19ef512fa91aca37abd685b2e06a06d0333eeb
mkdir -p .agents/skills
cp -R "$tmp/skills/drawio-aws" .agents/skills/drawio-aws

Commands for macOS and Linux, on Windows run them in Git Bash.

Run in a terminal in the project folder

npx skills add sparklabx/drawio-ai-kit --skill drawio-aws -a github-copilot -y

The skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.

Without third-party tools, from commit 6a19ef5
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/sparklabx/drawio-ai-kit.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skills/drawio-aws/
git -C "$tmp" checkout 6a19ef512fa91aca37abd685b2e06a06d0333eeb
mkdir -p .github/skills
cp -R "$tmp/skills/drawio-aws" .github/skills/drawio-aws

Commands for macOS and Linux, on Windows run them in Git Bash.

Run in a terminal in the project folder

npx skills add sparklabx/drawio-ai-kit --skill drawio-aws -a codex -y

The skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.

Without third-party tools, from commit 6a19ef5
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/sparklabx/drawio-ai-kit.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skills/drawio-aws/
git -C "$tmp" checkout 6a19ef512fa91aca37abd685b2e06a06d0333eeb
mkdir -p .agents/skills
cp -R "$tmp/skills/drawio-aws" .agents/skills/drawio-aws

Commands for macOS and Linux, on Windows run them in Git Bash.

Run in a terminal in the project folder

npx skills add sparklabx/drawio-ai-kit --skill drawio-aws -a gemini-cli -y

The skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.

Without third-party tools, from commit 6a19ef5
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/sparklabx/drawio-ai-kit.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skills/drawio-aws/
git -C "$tmp" checkout 6a19ef512fa91aca37abd685b2e06a06d0333eeb
mkdir -p .agents/skills
cp -R "$tmp/skills/drawio-aws" .agents/skills/drawio-aws

Commands for macOS and Linux, on Windows run them in Git Bash.

Run in a terminal in the project folder

tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/sparklabx/drawio-ai-kit.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skills/drawio-aws/
git -C "$tmp" checkout 6a19ef512fa91aca37abd685b2e06a06d0333eeb
mkdir -p .devin/skills
cp -R "$tmp/skills/drawio-aws" .devin/skills/drawio-aws

Commands for macOS and Linux, on Windows run them in Git Bash.

Formerly Windsurf.

Run in a terminal in the project folder

npx skills add sparklabx/drawio-ai-kit --skill drawio-aws -a cline -y

The skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.

Without third-party tools, from commit 6a19ef5
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/sparklabx/drawio-ai-kit.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skills/drawio-aws/
git -C "$tmp" checkout 6a19ef512fa91aca37abd685b2e06a06d0333eeb
mkdir -p .cline/skills
cp -R "$tmp/skills/drawio-aws" .cline/skills/drawio-aws

Commands for macOS and Linux, on Windows run them in Git Bash.

Run in a terminal in the project folder

npx skills add sparklabx/drawio-ai-kit --skill drawio-aws -a roo -y

The skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.

Without third-party tools, from commit 6a19ef5
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/sparklabx/drawio-ai-kit.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skills/drawio-aws/
git -C "$tmp" checkout 6a19ef512fa91aca37abd685b2e06a06d0333eeb
mkdir -p .roo/skills
cp -R "$tmp/skills/drawio-aws" .roo/skills/drawio-aws

Commands for macOS and Linux, on Windows run them in Git Bash.

A fork of Roo Code, same .roo folders.

Run in a terminal in the project folder

npx skills add sparklabx/drawio-ai-kit --skill drawio-aws -a opencode -y

The skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.

Without third-party tools, from commit 6a19ef5
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/sparklabx/drawio-ai-kit.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skills/drawio-aws/
git -C "$tmp" checkout 6a19ef512fa91aca37abd685b2e06a06d0333eeb
mkdir -p .agents/skills
cp -R "$tmp/skills/drawio-aws" .agents/skills/drawio-aws

Commands for macOS and Linux, on Windows run them in Git Bash.

Run in a terminal in the project folder

tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/sparklabx/drawio-ai-kit.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skills/drawio-aws/
git -C "$tmp" checkout 6a19ef512fa91aca37abd685b2e06a06d0333eeb
mkdir -p .agents/skills
cp -R "$tmp/skills/drawio-aws" .agents/skills/drawio-aws

Commands for macOS and Linux, on Windows run them in Git Bash.

Run in a terminal in the project folder

tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/sparklabx/drawio-ai-kit.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skills/drawio-aws/
git -C "$tmp" checkout 6a19ef512fa91aca37abd685b2e06a06d0333eeb
mkdir -p .agents/skills
cp -R "$tmp/skills/drawio-aws" .agents/skills/drawio-aws

Commands for macOS and Linux, on Windows run them in Git Bash.

You will need: Node.js

Checked against the repository on Sep 25, 2026, commit 6a19ef5.

Text for your agent

Install the CLI and all skills: npm i -g github:sparklabx/drawio-ai-kit && npx skills add sparklabx/drawio-ai-kit. Restart the agent and ask for a diagram.

Other ways from the author
npm i -g github:sparklabx/drawio-ai-kit && npx skills add sparklabx/drawio-ai-kit

The CLI on PATH plus all 5 domain skills. Restart the agent after installing.

This is third-party code. Review the repository files before installing.

What it does

A set of domain skills plus the drawio-ai CLI helps an agent build draw.io diagrams without invented icons or broken layout. It is backed by a catalog of real mxgraph stencils with their taxonomy and colors, a set of layout rules and a static XML validator that checks stencil references and geometry before saving. An optional visual self-check renders through the draw.io desktop app. Five domains are covered: AWS, Azure, GCP, Databricks and BPMN, with .drawio as the default output.

Who it is for. For developers, devops engineers and technical writers who need clean cloud architecture diagrams.

Good fit when

  • You need an AWS, Azure, GCP or Databricks architecture diagram in draw.io
  • You need a BPMN diagram with correct shapes
  • The agent draws empty shapes or wrong icons and you need validation

Not a fit when

  • You need a format other than draw.io, PNG or SVG
  • The diagram is outside the supported domains and stencils

Example request

Draw an AWS diagram for a three-tier web app

Limitations

It needs Node.js 18+, and the CLI installs from GitHub since it is not on the npm registry yet. The visual self-check needs the draw.io desktop app, and Graphviz helps with large graphs. Optional logo-icon fetching comes from public CDNs and is opt-in. There are no install hooks and no telemetry.

How to disable. Remove the CLI: npm uninstall -g drawio-ai-kit. Remove domain skills with npx skills remove drawio-aws and so on.

Security check

  • Installs a global CLI and runs shell commands
  • Writes diagram files into the project

README in short

The README describes a kit for generating draw.io diagrams through an agent. The core has three parts: a declarative catalog of mxgraph stencils with colors, a set of layout rules and a static XML validator. Everything is exposed through the dependency-free drawio-ai CLI. Five domain skills for AWS, Azure, GCP, Databricks and BPMN install via the skills CLI, which detects Claude Code, Codex and Gemini CLI. There are no install hooks and no telemetry. MIT licensed.

FAQ

Why do empty shapes not appear?

The catalog holds real stencil ids and the validator checks references and geometry before saving, so non-existent icons are rejected.

Is the draw.io desktop app required?

No. It is only for the render-based visual self-check; core generation and validation work without it.

Editors’ pick

An MCP server built into the Netdata agent: metrics, logs, alerts and live process, service and container data for an AI assistant

MCP serverMedium riskNo VPN needed80.7K
Editors’ pick

GitHub's official MCP server: code, issues, pull requests, Actions and security alerts straight from the agent

MCP serverHigh risk33.3K

Agent Skills for Google products

Agent Skills for Google products and technologies

Editors’ pick

Official Google skill collection for working with Google Cloud, BigQuery, GKE, ads and analytics from an agent

SkillHigh risk20.5K
Official

AWS's official MCP server suite: docs, IaC, containers, serverless, databases, cost and monitoring

MCP serverHigh risk9.7K
Foxx AIdrawio-ai-kit

I am Foxx AI and I have already vetted this tool. Ask about install, setup or anything else, and I will keep it simple.