excalidraw-diagram

Generate production-quality Excalidraw architecture diagrams from natural language. Visual structure maps to conceptual structure — fan-out for one-to-many, timelines for sequences, convergence for aggregation. Includes self-validation via Playwright render review.

Best use case

excalidraw-diagram is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Generate production-quality Excalidraw architecture diagrams from natural language. Visual structure maps to conceptual structure — fan-out for one-to-many, timelines for sequences, convergence for aggregation. Includes self-validation via Playwright render review.

Teams using excalidraw-diagram should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/excalidraw-diagram/SKILL.md --create-dirs "https://raw.githubusercontent.com/nvdigitalsolutions/mcp-ai-wpoos/main/includes/bundled-skills/excalidraw-diagram/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/excalidraw-diagram/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How excalidraw-diagram Compares

Feature / Agentexcalidraw-diagramStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Generate production-quality Excalidraw architecture diagrams from natural language. Visual structure maps to conceptual structure — fan-out for one-to-many, timelines for sequences, convergence for aggregation. Includes self-validation via Playwright render review.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Excalidraw Diagram Generator

Generate visual architecture diagrams, sequence diagrams, data-flow diagrams, and system maps from natural language descriptions using Excalidraw's JSON format.

## Install

```bash
npx skills add https://github.com/coleam00/excalidraw-diagram-skill --skill excalidraw-diagram
```

## When to Use

- Documenting architecture decisions for the repository
- Explaining system design to stakeholders or new team members
- Visualising data flow, API call sequences, or deployment topology
- Creating diagrams for RFCs, ADRs, and design documents
- Generating animated GIFs from Excalidraw exports for presentations

## Design Philosophy

**Diagrams that argue, not display.** Every shape and grouping mirrors the concept it represents:

| Concept | Visual pattern |
|---------|---------------|
| One-to-many (fan-out) | Single node → multiple branches |
| Sequential steps | Left-to-right timeline or top-to-bottom flow |
| Aggregation (many-to-one) | Convergence funnel |
| Subsystems / bounded contexts | Grouped rectangles with labelled borders |
| External dependencies | Dashed borders or cloud shapes |
| Data stores | Cylinder shapes |

Never default to a uniform grid of identical cards. Let the shape of the diagram communicate the shape of the system.

## Output Format

Generate Excalidraw JSON that can be opened directly in https://excalidraw.com or the Excalidraw VS Code extension.

```json
{
  "type": "excalidraw",
  "version": 2,
  "source": "https://excalidraw.com",
  "elements": [
    {
      "id": "el1",
      "type": "rectangle",
      "x": 100, "y": 100,
      "width": 160, "height": 60,
      "label": { "text": "API Gateway" },
      "strokeColor": "#1e1e2e",
      "backgroundColor": "#cba6f7",
      "fillStyle": "solid"
    }
  ],
  "appState": { "viewBackgroundColor": "#ffffff" }
}
```

Save the JSON to a `.excalidraw` file:

```bash
cat > architecture.excalidraw << 'EOF'
{ ...generated JSON... }
EOF
```

## Self-Validation Loop

After generating the JSON, validate the rendered output:

```bash
# Render to PNG using Playwright
npx playwright screenshot --url "https://excalidraw.com/#json=..." output.png

# Or use the excalidraw-utils CLI
npx excalidraw-utils export architecture.excalidraw --output output.png
```

Review the rendered image for:

- Overlapping labels or elements
- Arrows pointing to wrong nodes
- Unbalanced whitespace (cluster elements or spread them)
- Missing labels on key flows

Fix any layout issues before presenting the diagram.

## Example Prompts

```
Create an Excalidraw diagram showing how a request flows through
our API gateway, auth middleware, and downstream microservices.

Generate an architecture diagram for a multi-tenant SaaS with
separate database schemas per tenant and a shared analytics layer.

Draw a sequence diagram for our OAuth2 PKCE flow including
the browser, authorisation server, and resource server.

Create a data-flow diagram showing how webhook events move from
Stripe through our queue, processor, and into the database.
```

## Brand Customisation

Store your colour palette in `references/color-palette.md`:

```markdown
# Colour Palette
- Primary:   #7c3aed (purple)
- Secondary: #2563eb (blue)
- Success:   #16a34a (green)
- Warning:   #d97706 (amber)
- Error:     #dc2626 (red)
- Surface:   #f8fafc (light grey)
- Text:      #1e293b (dark)
```

Reference this file in every diagram generation prompt to keep visuals consistent across the project.

## Tips

- Annotate key flows with real API paths or JSON payloads inline, not placeholder text
- For large systems, generate one diagram per bounded context and a high-level overview
- Use Excalidraw's "hand-drawn" style for exploratory/draft diagrams; clean style for documentation
- Export to SVG for embedding in Markdown; PNG for presentations
- Version-control `.excalidraw` files in the repository alongside the code they describe

Related Skills

webapp-testing

5
from nvdigitalsolutions/mcp-ai-wpoos

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

web-artifacts-builder

5
from nvdigitalsolutions/mcp-ai-wpoos

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

valyu

5
from nvdigitalsolutions/mcp-ai-wpoos

Search the live web and 36+ specialised data sources including SEC filings, PubMed, ChEMBL, clinical trials, FRED economic indicators, and patent databases. Use when current, authoritative, or paywalled data is required.

ui-ux-pro-max

5
from nvdigitalsolutions/mcp-ai-wpoos

AI-powered design intelligence with 67 UI styles, 161 color palettes, 57 font pairings, 99 UX guidelines, and 25 chart types across 15+ tech stacks. Generates complete design systems for any product type with industry-specific reasoning rules.

theme-factory

5
from nvdigitalsolutions/mcp-ai-wpoos

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.

slack-gif-creator

5
from nvdigitalsolutions/mcp-ai-wpoos

Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."

skill-creator

5
from nvdigitalsolutions/mcp-ai-wpoos

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

shannon

5
from nvdigitalsolutions/mcp-ai-wpoos

Autonomous AI security pen testing. Executes real exploits against web applications to find SQL injection, XSS, SSRF, authentication flaws, and IDOR vulnerabilities. Reports only confirmed, reproducible findings — no false positives.

remotion

5
from nvdigitalsolutions/mcp-ai-wpoos

Create programmatic videos using React and Remotion. Translate natural language descriptions into working Remotion components for product demos, release announcements, explainer videos, and animated content.

planetscale

5
from nvdigitalsolutions/mcp-ai-wpoos

Design schemas and write queries for PlanetScale serverless MySQL using branch-based workflows. Ensures index coverage, avoids foreign key anti-patterns, and treats every schema change as a reviewable, reversible deploy request.

mcp-builder

5
from nvdigitalsolutions/mcp-ai-wpoos

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

karpathy-coding-principles

5
from nvdigitalsolutions/mcp-ai-wpoos

Apply Karpathy-inspired coding behavior guidelines — think before coding, prefer simplicity, make surgical changes, and execute toward verifiable goals. Reduces wrong assumptions, overengineering, and unintended side-effects.