Drawio

This is a serious diagram workflow for technical and academic contexts. It routes requests to offline-first YAML specs, supports six themes, and handles math typesetting with LaTeX and AsciiMath. The routing table is comprehensive: it knows when you need IEEE-style paper figures versus cloud architecture versus formula-heavy diagrams, and it pulls only the relevant reference docs for each path. Network topology gets semantic device types and auto-labeled links. Academic output defaults to the full offline bundle with SVG, adding PNG only when draw.io Desktop is available and the request screams thesis or manuscript. If you write diagrams for papers or need reproducible architecture docs with formula support, this handles the full pipeline from spec to export.

skills.sh installs: 8.7K
GitHub stars: 299
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add bahayonghang/drawio-skills --skill drawio --agent claude-code

Installs into .claude/skills of the current project.

Files

Draw.io Base Skill

Create, edit, validate, replicate, import, and export draw.io diagrams through a YAML-first offline workflow. It is the single maintained base for sibling overlays and owns the local CLI, schemas, references, themes, palettes, examples, style presets, and export helpers.

Scope

Use this base skill for general draw.io work: software/system architecture; network topologies and infrastructure maps; flowcharts, swimlanes, process maps, and org charts; UML class/sequence/state/ER; Mermaid and CSV conversion; structured redraw and non-academic replication; formula-bearing technical diagrams; .drawio import, sidecar export, and local validation.

For paper, thesis, IEEE, journal, manuscript, or publication-ready figure requests, route to the sibling drawio-academic-skills overlay; the base does not apply academic publication gates. Without the overlay, render the local YAML bundle but report that overlay policy was not applied.