drawio-skill — What is it?

The Agents365-ai/drawio-skill project is a Python-based tool that converts natural language descriptions into professional draw.io diagrams, offering a range of features for codebase visualization and diagram generation with AI assistance.

⭐ 5,638 Stars 🍴 452 Forks Python Author: Agents365-ai
Source: Description per README View on GitHub →

Why it matters

This project is gaining attention due to its ability to bridge the gap between natural language and technical diagrams, particularly useful for developers and technical writers who need to create diagrams from code or descriptions without manual drawing. Its integration with various AI/LLM tools and extensive shape library adds unique value.

Source: Synthesis of README and project traits

Core Features

Natural Language to Diagram Conversion

Converts natural language descriptions into draw.io diagrams, supporting 6 diagram types and offering a vision self-check for up to 5 rounds of refinement.

Source: README Highlights
Codebase Visualization

Automatically generates structure diagrams from existing codebases in Python, JS-TS, Go, and Rust, with features like auto-lay-out, transitive reduction, and nested module containers.

Source: README Visualize a Codebase
Shape Search

Searches a library of 10,000+ official draw.io shapes to ensure accurate icon representation for services like AWS, Azure, GCP, and Cisco.

Source: README Shape Search
AI/LLM Brand Logos

Incorporates AI and LLM brand logos into diagrams for LLM-app architecture diagrams, with a collection of 321 logos.

Source: README Highlights
Self-check and Auto-fix

Automatically checks and fixes diagram issues like overlaps, clipped labels, and stacked edges, up to 2 rounds of auto-fixing.

Source: README Highlights

Architecture

The architecture of the project suggests a modular design with separate components for language parsing, diagram generation, codebase extraction, and layout algorithms. It leverages Graphviz for auto-lay-out and includes various extractors for different programming languages. The project is designed to be multi-agent compatible and zero-config, with a focus on ease of integration and use.

Source: Code tree + README

Project Knowledge Graph

Knowledge graph: project (center) + core features (inner hexagons) + key dependencies (outer chips) Graphviz mxgraph aiicons.py Natural Language to Diagram ConversionNatural Language to… Codebase VisualizationCodebase Visualizat… Shape Search AI/LLM Brand Logos Self-check and Auto-fixSelf-check and Auto… drawio-skill Project Core feature Key dependency

Center: project; inner ring: core feature modules; outer ring: key dependencies. Auto-generated from core_features and tech_stack.key_deps.

Tech Stack

LanguagePythonFrameworkNot enough information
Graphvizmxgraphaiicons.py
Not enough information
Source: Code tree + README

Quick Start

1. Install the draw.io desktop CLI. 2. Install the skill using `npx skills add Agents365-ai/365-skills -g` or through the Claude Code plugin marketplace. 3. Describe what you want in natural language and the skill will generate the diagram.
Source: README Installation/Quick Start

Use Cases

This project is suitable for developers, technical writers, and anyone who needs to create diagrams from code or descriptions. It is useful for visualizing codebase structures, documenting architecture, and creating diagrams for presentations or documentation.

Source: README

Strengths & Limitations

Strengths

  • Strength 1: Streamlines diagram creation from natural language.
  • Strength 2: Offers advanced features like codebase visualization and AI/LLM logo integration.
  • Strength 3: Supports multiple diagram types and has a vast shape library.

Limitations

  • Limitation 1: The project's documentation could be more comprehensive.
  • Limitation 2: The lack of specific performance metrics or benchmarks makes it hard to assess efficiency.
Source: Synthesis of README, code structure and dependencies

Latest Release

v1.14.0 (2026-06-02): Added data-store brand logos to the AI/LLM brand logos feature.

Source: GitHub Releases

Verdict

The Agents365-ai/drawio-skill project is a valuable tool for automating diagram creation, particularly for those who need to generate diagrams from code or descriptions. Its integration with AI/LLM tools and extensive shape library make it a standout choice for developers and technical writers looking to enhance their documentation and visualization processes.

Frequently Asked Questions

What is drawio-skill?

The Agents365-ai/drawio-skill project is a Python-based tool that converts natural language descriptions into professional draw.io diagrams, offering a range of features for codebase visualization and diagram generation…

What are the main features of drawio-skill?

drawio-skill's core features include: Natural Language to Diagram Conversion, Codebase Visualization, Shape Search, AI/LLM Brand Logos, Self-check and Auto-fix.

Why is drawio-skill trending?

This project is gaining attention due to its ability to bridge the gap between natural language and technical diagrams, particularly useful for developers and technical writers who need to create diagrams from code or…

What is drawio-skill used for?

This project is suitable for developers, technical writers, and anyone who needs to create diagrams from code or descriptions.

Transparency Notice
This page is auto-generated by AI (a large language model) from the following public materials: GitHub README, code tree, dependency files and release notes. Analyzed at: 2026-06-12 18:33. Quality score: 85/100.

Data sources: README, GitHub API, dependency files