What is beautiful-drawio?

A skill for creating native draw.io diagrams with planned layouts for architecture diagrams, flowcharts, system maps, data flows, and other diagrams with many connected parts. Draw.io is a diagramming tool, and the skill focuses on placing items and connections clearly before creating the file.

Use it to create cleaner system architecture, deployment, security-boundary, block, and multi-lane flow diagrams in .drawio format.

It helps prevent overlapping boxes, tangled connection lines, and unnecessary crossings in dense diagrams.

beautiful-drawio — Skill for Claude Code by cyberelf/agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add cyberelf/agent_skills --skill beautiful-drawio

Clone the repo

git clone --depth 1 https://github.com/cyberelf/agent_skills

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/cyberelf/agent_skills/beautiful-drawio/github.svg)](https://agentmods.dev/skills/cyberelf/agent_skills/beautiful-drawio)

Your own site

<a href="https://agentmods.dev/skills/cyberelf/agent_skills/beautiful-drawio"><img src="https://agentmods.dev/badge/skills/cyberelf/agent_skills/beautiful-drawio/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/cyberelf/agent_skills/beautiful-drawio"><img src="https://agentmods.dev/badge/skills/cyberelf/agent_skills/beautiful-drawio.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,504 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00066	$0.02504
Opus 5.5	$0.00026	$0.01002
Sonnet 5.5	$0.00013	$0.00501
Haiku 4.5	$0.00007	$0.00250

Measured 2mo ago against content hash 1b99ad81eaed, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

beautiful-drawio scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/elk_layout_to_drawio.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/beautiful-drawio/SKILL.md · 254 lines

How it starts

The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Beautiful Draw.io

Create native .drawio diagrams with a layout-first workflow designed for dense block diagrams, architecture maps, and connection-heavy systems.

This skill exists because the baseline drawio workflow focuses on XML generation and export, while high-quality diagrams require an explicit layout pass before any mxGraph XML is written.

For complex diagrams, do not rely on natural-language layout instructions alone. The preferred path is now a typed JSON specification plus either an ELK-backed layout engine or a structured row/column packer, so the agent describes structure, hierarchy, and sibling order rather than hand-authoring absolute coordinates.

When To Use

The user asks for .drawio output but wants the visual quality closer to a Mermaid/ELK layout.
The diagram has many edges, cross-domain links, or layered blocks.
The user explicitly complains about overlapping edges, node collisions, or too many crossings.
The diagram is a system architecture, block diagram, deployment map, data flow, security boundary diagram, or multi-lane flowchart.

Core Difference From The Default Drawio Skill

Default drawio: write mxGraph XML directly, then adjust routing ad hoc.
beautiful-drawio: design topology first, reduce crossings before placement, route edges by lane and hierarchy, then emit mxGraph XML.
Default drawio: treats layout as a side effect of coordinates.
beautiful-drawio: treats layout as a first-class design step.

Workflow

0. Use the typed JSON pipeline for dense diagrams

If the diagram has more than a handful of nodes or any nontrivial crossing pressure, use the structured pipeline:

The agent chooses a diagram type such as product-block, technical-architecture, data-flow, or deployment.
The agent supplies nodes, containers, parent-child hierarchy, and sibling order in JSON.
The agent does not supply absolute coordinates unless preserving a partially fixed legacy diagram.
Run ELK layout script.
Let the script generate optimized coordinates and draw.io XML.
Only do manual edits after the script output if a small visual adjustment is still needed.

Read the full file on GitHub · 254 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 254 lines · 66 tokens per session scan A 1b99ad81eaed

Subscribe to this mod's changes

beautiful-drawio is a skill published in the GitHub repository cyberelf/agent_skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 66 tokens to every session and 2,504 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Design and UX

beautiful-drawio next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
beautiful-drawiocyberelf/agent_skills	Skill	2	2mo ago	MIT	A	66	Claude Code
webgl-holographic-foilnexu-io/open-design	Skill	106k	today	Apache-2.0	A	41	Claude Code, Codex
html-ppt-hermes-cyber-terminalnexu-io/open-design	Skill	106k	today	Apache-2.0	A	53	Claude Code, Codex
html-ppt-taste-brutalistnexu-io/open-design	Skill	106k	today	Apache-2.0	A	78	Claude Code, Codex
visual-ralphYeachan-Heo/oh-my-codex	Skill	34k	today	MIT	A	52	Codex
glance-canonical-layoutsandroid/skills	Skill	10k	2d ago	Apache-2.0	A	56	Claude Code
accessibilitymicrosoft/hve-core	Skill	1.6k	today	MIT	A	47	Claude Code