drawio-skill
Generate draw.io diagrams from natural language — 11 presets (UML, SysML/MBSE, BPMN, network, C4…), 36 tools: codebase/CI/infra-to-diagram, image→editable diagram, mind maps, build-up animation, exec-view compression, click-through runbooks, PR diff bot. Vision self-check, 10,000+ shapes. Exports PN
The drawio-skill agent skill transforms natural language descriptions into professional draw.io diagrams with 11 diagram type presets including UML, BPMN, C4, network topology, and SysML. It offers 36 specialized tools that convert existing codebases (Python, JavaScript, Go, Rust), infrastructure-as-code (Terraform, Kubernetes, Docker Compose), and SQL schemas into auto-laid-out diagrams with official vendor icons. The skill integrates vision-based self-checking, accesses over 10,000 draw.io shapes, and exports to PNG, SVG, PDF formats, working with Claude Code, Cursor, Copilot, and other Agent Skills-compatible platforms.
Key Features
Use Cases
- 01Document microservices architectures by describing components and connections in plain English, automatically generating tier-based layouts
- 02Reverse-engineer Python project structures into visual class hierarchies and module dependency graphs from existing codebases
- 03Create live infrastructure diagrams from deployed Terraform state, Kubernetes clusters, or running Docker containers with real resource icons
- 04Generate multi-page C4 architecture documentation with click-through navigation from system context to component details
- 05Build ML/deep learning model diagrams with annotated tensor shapes and color-coded layer types for technical documentation
- 06Track infrastructure drift by comparing diagram snapshots across time with automated color-coded change detection
Related Skills
View moresuperpowers
An agentic skills framework & software development methodology that works.
skills
Skills for Real Engineers. Straight from my .agents directory.
skills
Public repository for Agent Skills
ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
drawio-skill — FAQ
What is drawio-skill and what does it do?+
The drawio-skill is an agent skill that converts natural language descriptions and existing code/infrastructure into professional draw.io diagrams. It supports 11 diagram types, can extract architecture from Python/JS/Go/Rust codebases, Terraform/Kubernetes/Docker configs, and SQL schemas, and automatically exports to PNG/SVG/PDF formats.
How do I install drawio-skill?+
First install the draw.io desktop CLI (brew install --cask drawio on macOS, or download from releases for Windows/Linux). Then install the skill using 'npx skills add Agents365-ai/365-skills -g' for general agents, or '/plugin marketplace add Agents365-ai/365-skills' then '/plugin install drawio' for Claude Code.
Which AI clients and agents work with drawio-skill?+
The skill works with Claude Code, Cursor, GitHub Copilot, OpenClaw, Codex, Autohand Code, Hermes, and any agent compatible with the Agent Skills format.
Do I need API keys or special prerequisites?+
You need draw.io desktop version 30 or later installed and accessible via CLI. For auto-layout features, you need Graphviz installed (brew install graphviz or apt install graphviz). No API keys are required.
Is drawio-skill free to use?+
Yes, drawio-skill is open source under the MIT license and free to use. All dependencies (draw.io desktop and Graphviz) are also free.
Can drawio-skill visualize my existing codebase or infrastructure?+
Yes, it includes 13 extractors that analyze Python/JS/Go/Rust code for import graphs and class hierarchies, parse Terraform/Kubernetes/docker-compose for resource diagrams with official cloud icons, convert SQL DDL to ER diagrams, and can even snapshot live infrastructure from terraform show, docker inspect, or kubectl get output.
How do I install drawio-skill?+
Open the source repository on GitHub and follow its README. drawio-skill is a skill — MCP Agents Market links you directly to the official repo.
Is drawio-skill free?+
drawio-skill is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.