excalidraw-flowchart

0
0
Source

Create Excalidraw flowcharts from descriptions. Use when user asks to "create a flowchart", "draw a diagram", "visualize a process", "make a flow diagram", "architecture diagram", or discusses workflow/process visualization. Supports DSL, DOT/Graphviz, and JSON formats.

Install

mkdir -p .claude/skills/excalidraw-flowchart && curl -L -o skill.zip "https://mcp.directory/api/skills/download/8454" && unzip -o skill.zip -d .claude/skills/excalidraw-flowchart && rm skill.zip

Installs to .claude/skills/excalidraw-flowchart

About this skill

Excalidraw Flowchart Skill

Create professional flowcharts and diagrams as Excalidraw files that can be opened in Excalidraw.

When to Use This Skill

  • User asks to create a flowchart or diagram
  • User wants to visualize a process or workflow
  • User needs an architecture diagram
  • User mentions "excalidraw" or "flow diagram"
  • User wants to document decision trees

Prerequisites

The @swiftlysingh/excalidraw-cli tool must be installed:

npm install -g @swiftlysingh/excalidraw-cli

Or use via npx (no installation needed):

npx @swiftlysingh/excalidraw-cli create --inline "DSL" -o output.excalidraw

How to Create a Flowchart

Step 1: Analyze the Request

Identify from the user's description:

  • What are the main steps/nodes?
  • What are the decision points?
  • What is the flow direction?
  • Are there any loops or branches?

Step 2: Write the DSL

Use this DSL syntax to describe the flowchart:

SyntaxElementUse For
[Label]RectangleProcess steps, actions
{Label?}DiamondDecisions, conditionals
(Label)EllipseStart/End points
[[Label]]DatabaseData storage
![path]ImageInline images
![path](WxH)Sized ImageImages with explicit dimensions
->ArrowConnections
-> "text" ->Labeled ArrowConnections with labels
-->Dashed ArrowOptional/alternative paths

DSL Directives

DirectiveDescriptionExample
@directionSet flow direction@direction LR
@spacingSet node spacing@spacing 60
@imagePosition image@image logo.png at 100,50
@decorateAttach decoration to node@decorate icon.png top-right
@stickerAdd sticker from library@sticker checkmark at 200,100
@librarySet sticker library path@library ./assets/stickers
@scatterScatter images on canvas@scatter star.png count:5

Step 3: Generate the File

Run the CLI to create the .excalidraw file:

npx @swiftlysingh/excalidraw-cli create --inline "YOUR_DSL_HERE" -o flowchart.excalidraw

Or for multi-line DSL, use a heredoc:

npx @swiftlysingh/excalidraw-cli create --inline "$(cat <<'EOF'
(Start) -> [Step 1] -> {Decision?}
{Decision?} -> "yes" -> [Step 2] -> (End)
{Decision?} -> "no" -> [Step 3] -> [Step 1]
EOF
)" -o flowchart.excalidraw

Step 4: Inform the User

Tell the user:

  1. The file was created at the specified path
  2. They can open it in Excalidraw (https://excalidraw.com) via File > Open
  3. They can edit it further in Excalidraw if needed

DSL Examples

Simple Linear Flow

(Start) -> [Initialize] -> [Process Data] -> [Save Results] -> (End)

Decision Tree

(Start) -> [Receive Request] -> {Authenticated?}
{Authenticated?} -> "yes" -> [Process Request] -> (Success)
{Authenticated?} -> "no" -> [Return 401] -> (End)

Loop/Retry Pattern

(Start) -> [Attempt Operation] -> {Success?}
{Success?} -> "yes" -> [Continue] -> (End)
{Success?} -> "no" -> {Retry Count < 3?}
{Retry Count < 3?} -> "yes" -> [Increment Counter] -> [Attempt Operation]
{Retry Count < 3?} -> "no" -> [Log Failure] -> (Error)

Multi-Branch Flow

(User Input) -> {Input Type?}
{Input Type?} -> "text" -> [Parse Text] -> [Process]
{Input Type?} -> "file" -> [Read File] -> [Process]
{Input Type?} -> "url" -> [Fetch URL] -> [Process]
[Process] -> [Output Result] -> (Done)

With Database

[API Request] -> {Cache Hit?}
{Cache Hit?} -> "yes" -> [[Read Cache]] -> [Return Data]
{Cache Hit?} -> "no" -> [[Query Database]] -> [[Update Cache]] -> [Return Data]

CLI Options

  • -o, --output <file> - Output file path (default: flowchart.excalidraw)
  • -f, --format <type> - Input format: dsl, json, dot (default: auto-detected)
  • -d, --direction <TB|BT|LR|RL> - Flow direction (default: TB = top to bottom)
  • -s, --spacing <number> - Node spacing in pixels (default: 50)
  • --inline <dsl> - Inline DSL/DOT string
  • --stdin - Read input from stdin
  • --verbose - Verbose output

Example with options:

npx @swiftlysingh/excalidraw-cli create --inline "[A] -> [B] -> [C]" --direction LR --spacing 80 -o horizontal-flow.excalidraw

DOT/Graphviz Format (New in v1.1.0)

The CLI now supports DOT/Graphviz format for creating diagrams. This is useful when working with existing DOT files or when you prefer the DOT syntax.

DOT Syntax

digraph {
    rankdir=LR

    start [shape=ellipse label="Start"]
    process [shape=box label="Process Data"]
    decision [shape=diamond label="Valid?"]
    end [shape=ellipse label="End"]

    start -> process
    process -> decision
    decision -> end [label="yes"]
    decision -> process [label="no" style=dashed]
}

Supported DOT Features

FeatureDOT SyntaxMaps To
Rectangleshape=box or shape=rect[Label]
Diamondshape=diamond{Label}
Ellipseshape=ellipse or shape=circle(Label)
Databaseshape=cylinder[[Label]]
Directionrankdir=TB|BT|LR|RL@direction
Edge labels[label="text"]-> "text" ->
Dashed edges[style=dashed]-->
Colors[fillcolor="..." color="..."]Node styling

Using DOT Files

# From file (auto-detected by .dot or .gv extension)
npx @swiftlysingh/excalidraw-cli create diagram.dot -o output.excalidraw

# Inline DOT
npx @swiftlysingh/excalidraw-cli create --format dot --inline "digraph { A -> B -> C }" -o output.excalidraw

Images and Decorations (New in v1.1.0)

Image Nodes

Include images as flow elements:

(Start) -> ![logo.png](100x50) -> [Process] -> (End)

Positioned Images

Place images at specific positions:

@image background.png at 0,0
@image logo.png near (Start) top-right

(Start) -> [Process] -> (End)

Node Decorations

Attach small icons/badges to nodes:

[Deploy to Production]
@decorate checkmark.png top-right

[Review Required]
@decorate warning.png top-left

Decoration anchors: top, bottom, left, right, top-left, top-right, bottom-left, bottom-right

Sticker Library

Use a library of reusable stickers:

@library ./assets/stickers
@sticker success at 100,100
@sticker warning near (Error) top-right

Scatter Images

Distribute images randomly across the canvas:

@scatter confetti.png count:10
@scatter star.png count:5 width:20 height:20

Common Patterns

API Request Flow

[Client Request] -> [API Gateway] -> {Auth Valid?}
{Auth Valid?} -> "yes" -> [Route to Service] -> [[Database]] -> [Response]
{Auth Valid?} -> "no" -> [401 Unauthorized]

CI/CD Pipeline

(Push) -> [Build] -> [Test] -> {Tests Pass?}
{Tests Pass?} -> "yes" -> [Deploy Staging] -> {Manual Approval?}
{Manual Approval?} -> "yes" -> [Deploy Production] -> (Done)
{Manual Approval?} -> "no" -> (Cancelled)
{Tests Pass?} -> "no" -> [Notify Team] -> (Failed)

User Registration

(Start) -> [Enter Details] -> {Email Valid?}
{Email Valid?} -> "no" -> [Show Error] -> [Enter Details]
{Email Valid?} -> "yes" -> {Password Strong?}
{Password Strong?} -> "no" -> [Show Password Requirements] -> [Enter Details]
{Password Strong?} -> "yes" -> [[Save to Database]] -> [Send Verification Email] -> (Success)

Tips

  1. Keep labels concise - Use short, action-oriented text
  2. End decisions with ? - Makes it clear it's a conditional
  3. Use consistent naming - Helps with node deduplication
  4. Start with (Start) - Makes the entry point clear
  5. Test complex flows - Break into smaller parts if needed

You might also like

flutter-development

aj-geddes

Build beautiful cross-platform mobile apps with Flutter and Dart. Covers widgets, state management with Provider/BLoC, navigation, API integration, and material design.

1,1421,171

drawio-diagrams-enhanced

jgtolentino

Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.

969933

ui-ux-pro-max

nextlevelbuilder

"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient."

683829

godot

bfollington

This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.

691549

nano-banana-pro

garg-aayush

Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.

797540

pdf-to-markdown

aliceisjustplaying

Convert entire PDF documents to clean, structured Markdown for full context loading. Use this skill when the user wants to extract ALL text from a PDF into context (not grep/search), when discussing or analyzing PDF content in full, when the user mentions "load the whole PDF", "bring the PDF into context", "read the entire PDF", or when partial extraction/grepping would miss important context. This is the preferred method for PDF text extraction over page-by-page or grep approaches.

697374

Stay ahead of the MCP ecosystem

Get weekly updates on new skills and servers.