Code to diagram

Skill zebbern/claude-code-guide/skills/code-to-diagram

Claude Code Guide - Setup, Commands, workflows, agents, skills & tips-n-tricks go from beginner to power user!

Install

npx -y skills add zebbern/claude-code-guide --skill code-to-diagram

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its author says it does

Copied from the file, not written here

Analyze codebases and automatically generate architecture diagrams, flowcharts, and org charts. Uses AST parsing to map import dependencies for Python, JS/TS, Go, and Java, outputting Mermaid or SVG files. Triggered when users ask to visualize code architecture, understand dependencies, draw a flowchart, or create a module diagram from source code.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

3.8 KB, as published. Nobody here has run it

Code to Diagram

Extract import and dependency relationships from a codebase via AST parsing, and automatically generate three types of diagrams:

Architecture Diagram — Module/directory-level dependency relationships
Flowchart — File-level import call chains
Org Chart — Directory/file hierarchy structure

Supported languages: Python, JavaScript, TypeScript, Go, Java

Output formats: Mermaid text (.mmd) or SVG images (requires mmdc installed on the system)

Usage

Basic: Analyze an Entire Project

python3 scripts/analyze_codebase.py /path/to/project

Outputs three Mermaid diagrams to stdout and writes .mmd files to the current directory.

Specify Diagram Type

# Architecture diagram only
python3 scripts/analyze_codebase.py /path/to/project --type architecture

# Flowchart only
python3 scripts/analyze_codebase.py /path/to/project --type flowchart

# Org chart only
python3 scripts/analyze_codebase.py /path/to/project --type org

Specify Output Directory and Format

# Output to a specific directory
python3 scripts/analyze_codebase.py /path/to/project --output /tmp/diagrams

# Output as SVG (requires mmdc)
python3 scripts/analyze_codebase.py /path/to/project --format svg

# Output both Mermaid and SVG
python3 scripts/analyze_codebase.py /path/to/project --format both

Output JSON Analysis Results

python3 scripts/analyze_codebase.py /path/to/project --json

Parameters

Parameter	Description
`directory`	Code directory to analyze (required)
`--type, -t`	Diagram type: `architecture`, `flowchart`, `org`, `all` (default: `all`)
`--output, -o`	Output directory (default: current directory)
`--format, -f`	Output format: `mermaid`, `svg`, `both` (default: `mermaid`)
`--max-files`	Maximum number of files to scan (default: 500)
`--max-depth`	Maximum depth for org chart (default: 4)
`--json`	Output analysis results in JSON format

How It Works

Scan phase: Recursively traverse the directory, skipping node_modules, .git, __pycache__, etc.
Parse phase:
- Python files: uses the ast module to parse import and from ... import statements
- JS/TS files: uses regex to match import, require, and export from
- Go files: uses regex to match import statements
- Java files: uses regex to match import statements
Resolve internal dependencies: Maps import paths to actual files within the project
Generate diagrams: Converts dependency relationships into Mermaid diagram syntax
Render (optional): Calls mmdc (Mermaid CLI) to render .mmd files as SVG

Use Cases

Quickly understand the module structure of an unfamiliar project
Visualize dependencies during code review
Create architecture diagrams for technical documentation
Detect circular dependencies or excessive coupling
Analyze project structure before refactoring

Dependencies

Python 3.7+ (standard library only, no extra packages needed)
SVG output requires @mermaid-js/mermaid-cli (optional)

Notes

Only analyzes static import relationships; dynamic imports are not tracked
For large projects, use --max-files to limit the scan scope
Mermaid diagrams with too many nodes may be hard to render; use --type to generate diagrams separately