Skill detail

project-diagrams

Specializes in architecture, C4, data-flow, and deployment diagrams.

MatchDirectReviewed for architecture diagram
Sourceflight505/claude-project-plannerExternal source
Reported installs18Popularity signal only

Inspect before use

Automated review checks relevance, not safety or endorsement. Read the source instructions before using this skill.

Saved source preview

SKILL.md

The saved excerpt is a snapshot from review. The external source remains the complete and most current version.

---
name: project-diagrams
description: "Create publication-quality architecture diagrams using Nano Banana Pro AI or Mermaid. Specialized in system architecture, C4 diagrams, data flow, sequence diagrams, and software design visualizations for project planning."
allowed-tools: [Read, Write, Edit, Bash]
---

# Project Diagrams and Architecture Visualizations

## Overview

Project diagrams transform complex software architectures and system designs into clear visual representations. **This skill offers two diagram generation approaches:**

| Approach | Best For | Output |
|----------|----------|--------|
| **Nano Banana Pro AI** | Publication-quality visuals, presentations, complex custom diagrams | PNG images |
| **Mermaid** | Version-controlled docs, GitHub markdown, editable diagrams | SVG/PNG from code |

## Choosing Your Approach

### Use Nano Banana Pro AI when:
- You need visually polished, publication-ready diagrams
- Creating custom visualizations that don't fit standard templates
- Diagrams for presentations, proposals, or client deliverables
- Complex architectural diagrams with custom styling

### Use Mermaid when:
- Diagrams need to be version-controlled in git (text diffs)
- Embedding directly in GitHub/GitLab markdown
- You need to edit and iterate quickly on diagram structure
- Standardized diagram types (flowcharts, sequence, C4, ERD, Gantt)
- Collaborative documentation where others may edit

---

## Option 1: Nano Banana Pro AI (Recommended for Visuals)

**This approach uses Nano Banana Pro AI for diagram generation with Gemini 3 Pro quality review.**

**How it works:**
- Describe your diagram in natural language
- Nano Banana Pro generates publication-quality images automatically
- **Gemini 3 Pro reviews quality** against document-type thresholds
- **Smart iteration**: Only regenerates if quality is below threshold
- Professional output in minutes
- No coding, templates, or manual drawing required

**Quality Thresholds by Document Type:**
| Document Type | Threshold | Description |
|---------------|-----------|-------------|
| specification | 8.5/10 | Technical specs, PRDs |
| architecture | 8.0/10 | Architecture documents |
| proposal | 8.0/10 | Business proposals |
| sprint | 7.5/10 | Sprint planning docs |
| presentation | 6.5/10 | Slides, talks |
| default | 7.5/10 | General purpose |

## When to Use This Skill

This skill should be used when:
- Creating system architecture diagrams (C4 model, microservices, etc.)
- Illustrating data flow and integration patterns
- Drawing sequence diagrams for API interactions
- Visualizing database schemas and data models
- Creating deployment architecture diagrams (AWS, GCP, Azure)
- Depicting component relationships and dependencies
- Generating network topologies and infrastructure layouts
- Illustrating CI/CD pipelines and deployment workflows

## Quick Start: Generate Any Diagram

```bash
# System architecture (highest quality: 8.5/10)
python .claude/skills/project-diagrams/scripts/generate_schematic.py "Microservices architecture with API gateway, auth service, user service, and PostgreSQL" -o diagrams/architecture.png --doc-type specification

# C4 Context diagram
python .claude/skills/project-diagrams/scripts/generate_schematic.py "C4 Context diagram showing e-commerce system with payment gateway, inventory, customers" -o diagrams/c4_context.png --doc-type architecture

# Sequence diagram
python .claude/skills/project-diagrams/scripts/generate_schematic.py "Sequence diagram: user authentication flow with client, API, auth service, database" -o diagrams/auth_sequence.png

# Data flow diagram
python .claude/skills/project-diagrams/scripts/generate_schematic.py "Data flow: user input -> API -> validation -> business logic -> database -> response" -o diagrams/data_flow.png

# AWS deployment
python .claude/skills/project-diagrams/scripts/generate_schematic.py "AWS deployment: Route53 -> CloudFront -> ALB -> ECS Fargate -> RDS Aurora" -o diagrams/aws_deployment.png
`
Read the full source on GitHub (opens external page)
Context

Related work