Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a sys...
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a sys...
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
A skill for generating Excalidraw-format diagrams from natural language descriptions. This skill helps create visual representations of processes, systems, relationships, and ideas without manual drawing.
Use this skill when users request: "Create a diagram showing..." "Make a flowchart for..." "Visualize the process of..." "Draw the system architecture of..." "Generate a mind map about..." "Create an Excalidraw file for..." "Show the relationship between..." "Diagram the workflow of..." Supported diagram types: ๐ Flowcharts: Sequential processes, workflows, decision trees ๐ Relationship Diagrams: Entity relationships, system components, dependencies ๐ง Mind Maps: Concept hierarchies, brainstorming results, topic organization ๐๏ธ Architecture Diagrams: System design, module interactions, data flow ๐ Data Flow Diagrams (DFD): Data flow visualization, data transformation processes ๐ Business Flow (Swimlane): Cross-functional workflows, actor-based process flows ๐ฆ Class Diagrams: Object-oriented design, class structures and relationships ๐ Sequence Diagrams: Object interactions over time, message flows ๐๏ธ ER Diagrams: Database entity relationships, data models
Clear description of what should be visualized Identification of key entities, steps, or concepts Understanding of relationships or flow between elements
Analyze the user's description to determine: Diagram type (flowchart, relationship, mind map, architecture) Key elements (entities, steps, concepts) Relationships (flow, connections, hierarchy) Complexity (number of elements)
User IntentDiagram TypeExample KeywordsProcess flow, steps, proceduresFlowchart"workflow", "process", "steps", "procedure"Connections, dependencies, associationsRelationship Diagram"relationship", "connections", "dependencies", "structure"Concept hierarchy, brainstormingMind Map"mind map", "concepts", "ideas", "breakdown"System design, componentsArchitecture Diagram"architecture", "system", "components", "modules"Data flow, transformation processesData Flow Diagram (DFD)"data flow", "data processing", "data transformation"Cross-functional processes, actor responsibilitiesBusiness Flow (Swimlane)"business process", "swimlane", "actors", "responsibilities"Object-oriented design, class structuresClass Diagram"class", "inheritance", "OOP", "object model"Interaction sequences, message flowsSequence Diagram"sequence", "interaction", "messages", "timeline"Database design, entity relationshipsER Diagram"database", "entity", "relationship", "data model"
For Flowcharts: List of sequential steps Decision points (if any) Start and end points For Relationship Diagrams: Entities/nodes (name + optional description) Relationships between entities (from โ to, with label) For Mind Maps: Central topic Main branches (3-6 recommended) Sub-topics for each branch (optional) For Data Flow Diagrams (DFD): Data sources and destinations (external entities) Processes (data transformations) Data stores (databases, files) Data flows (arrows showing data movement from left-to-right or from top-left to bottom-right) Important: Do not represent process order, only data flow For Business Flow (Swimlane): Actors/roles (departments, systems, people) - displayed as header columns Process lanes (vertical lanes under each actor) Process boxes (activities within each lane) Flow arrows (connecting process boxes, including cross-lane handoffs) For Class Diagrams: Classes with names Attributes with visibility (+, -, #) Methods with visibility and parameters Relationships: inheritance (solid line + white triangle), implementation (dashed line + white triangle), association (solid line), dependency (dashed line), aggregation (solid line + white diamond), composition (solid line + filled diamond) Multiplicity notations (1, 0..1, 1..*, *) For Sequence Diagrams: Objects/actors (arranged horizontally at top) Lifelines (vertical lines from each object) Messages (horizontal arrows between lifelines) Synchronous messages (solid arrow), asynchronous messages (dashed arrow) Return values (dashed arrows) Activation boxes (rectangles on lifelines during execution) Time flows from top to bottom For ER Diagrams: Entities (rectangles with entity names) Attributes (listed inside entities) Primary keys (underlined or marked with PK) Foreign keys (marked with FK) Relationships (lines connecting entities) Cardinality: 1:1 (one-to-one), 1:N (one-to-many), N:M (many-to-many) Junction/associative entities for many-to-many relationships (dashed rectangles)
Create the .excalidraw file with appropriate elements: Available element types: rectangle: Boxes for entities, steps, concepts ellipse: Alternative shapes for emphasis diamond: Decision points arrow: Directional connections text: Labels and annotations Key properties to set: Position: x, y coordinates Size: width, height Style: strokeColor, backgroundColor, fillStyle Font: fontFamily: 5 (Excalifont - required for all text elements) Text: Embedded text for labels Connections: points array for arrows Important: All text elements must use fontFamily: 5 (Excalifont) for consistent visual appearance.
Structure the complete Excalidraw file: { "type": "excalidraw", "version": 2, "source": "https://excalidraw.com", "elements": [ // Array of diagram elements ], "appState": { "viewBackgroundColor": "#ffffff", "gridSize": 20 }, "files": {} }
Save as <descriptive-name>.excalidraw Inform user how to open: Visit https://excalidraw.com Click "Open" or drag-and-drop the file Or use Excalidraw VS Code extension
Diagram TypeRecommended CountMaximumFlowchart steps3-1015Relationship entities3-812Mind map branches4-68Mind map sub-topics per branch2-46
Start positions: Center important elements, use consistent spacing Spacing: Horizontal gap: 200-300px between elements Vertical gap: 100-150px between rows Colors: Use consistent color scheme Primary elements: Light blue (#a5d8ff) Secondary elements: Light green (#b2f2bb) Important/Central: Yellow (#ffd43b) Alerts/Warnings: Light red (#ffc9c9) Text sizing: 16-24px for readability Font: Always use fontFamily: 5 (Excalifont) for all text elements Arrow style: Use straight arrows for simple flows, curved for complex relationships
If user request has too many elements: Suggest breaking into multiple diagrams Focus on main elements first Offer to create detailed sub-diagrams Example response: "Your request includes 15 components. For clarity, I recommend: 1. High-level architecture diagram (6 main components) 2. Detailed diagram for each subsystem Would you like me to start with the high-level view?"
User: "Create a flowchart for user registration" Agent generates: Extract steps: "Enter email" โ "Verify email" โ "Set password" โ "Complete" Create flowchart with 4 rectangles + 3 arrows Save as user-registration-flow.excalidraw
User: "Diagram the relationship between User, Post, and Comment entities" Agent generates: Entities: User, Post, Comment Relationships: User โ Post ("creates"), User โ Comment ("writes"), Post โ Comment ("contains") Save as user-content-relationships.excalidraw
User: "Mind map about machine learning concepts" Agent generates: Center: "Machine Learning" Branches: Supervised Learning, Unsupervised Learning, Reinforcement Learning, Deep Learning Sub-topics under each branch Save as machine-learning-mindmap.excalidraw
IssueSolutionElements overlapIncrease spacing between coordinatesText doesn't fit in boxesIncrease box width or reduce font sizeToo many elementsBreak into multiple diagramsUnclear layoutUse grid layout (rows/columns) or radial layout (mind maps)Colors inconsistentDefine color palette upfront based on element types
const columns = Math.ceil(Math.sqrt(entityCount)); const x = startX + (index % columns) * horizontalGap; const y = startY + Math.floor(index / columns) * verticalGap;
const angle = (2 * Math.PI * index) / branchCount; const x = centerX + radius * Math.cos(angle); const y = centerY + radius * Math.sin(angle);
Use timestamp + random string for unique IDs: const id = Date.now().toString(36) + Math.random().toString(36).substr(2);
Always provide: โ Complete .excalidraw JSON file ๐ Summary of what was created ๐ Element count ๐ก Instructions for opening/editing Example summary: Created: user-workflow.excalidraw Type: Flowchart Elements: 7 rectangles, 6 arrows, 1 title text Total: 14 elements To view: 1. Visit https://excalidraw.com 2. Drag and drop user-workflow.excalidraw 3. Or use File โ Open in Excalidraw VS Code extension
Before delivering the diagram: All elements have unique IDs Coordinates prevent overlapping Text is readable (font size 16+) All text elements use fontFamily: 5 (Excalifont) Arrows connect logically Colors follow consistent scheme File is valid JSON Element count is reasonable (<20 for clarity)
For specialized diagrams (e.g., AWS/GCP/Azure architecture diagrams), you can use pre-made icon libraries from Excalidraw. This provides professional, standardized icons instead of basic shapes.
If user asks for AWS/cloud architecture diagrams or mentions wanting to use specific icons: Check if library exists: Look for libraries/<library-name>/reference.md If library exists: Proceed to use icons (see AI Assistant Workflow below) If library does NOT exist: Respond with setup instructions: To use [AWS/GCP/Azure/etc.] architecture icons, please follow these steps: 1. Visit https://libraries.excalidraw.com/ 2. Search for "[AWS Architecture Icons/etc.]" and download the .excalidrawlib file 3. Create directory: skills/excalidraw-diagram-generator/libraries/[icon-set-name]/ 4. Place the downloaded file in that directory 5. Run the splitter script: python skills/excalidraw-diagram-generator/scripts/split-excalidraw-library.py skills/excalidraw-diagram-generator/libraries/[icon-set-name]/ This will split the library into individual icon files for efficient use. After setup is complete, I can create your diagram using the actual AWS/cloud icons. Alternatively, I can create the diagram now using simple shapes (rectangles, ellipses) which you can later replace with icons manually in Excalidraw.
Step 1: Create Library Directory mkdir -p skills/excalidraw-diagram-generator/libraries/aws-architecture-icons Step 2: Download Library Visit: https://libraries.excalidraw.com/ Search for your desired icon set (e.g., "AWS Architecture Icons") Click download to get the .excalidrawlib file Example categories (availability varies; confirm on the site): Cloud service icons UI/Material icons Flowchart symbols Step 3: Place Library File Rename the downloaded file to match the directory name (e.g., aws-architecture-icons.excalidrawlib) Move it to the directory created in Step 1 Step 4: Run Splitter Script python skills/excalidraw-diagram-generator/scripts/split-excalidraw-library.py skills/excalidraw-diagram-generator/libraries/aws-architecture-icons/ Step 5: Verify Setup After running the script, verify the following structure exists: skills/excalidraw-diagram-generator/libraries/aws-architecture-icons/ aws-architecture-icons.excalidrawlib (original) reference.md (generated - icon lookup table) icons/ (generated - individual icon files) API-Gateway.json CloudFront.json EC2.json Lambda.json RDS.json S3.json ...
Request: "Create an AWS architecture diagram with Internet Gateway, VPC, ELB, EC2, and RDS" Recommended Workflow (using Python scripts): Request: "Create an AWS architecture diagram with Internet Gateway, VPC, ELB, EC2, and RDS" Recommended Workflow (using Python scripts): # Step 1: Create base diagram file with title # Create my-aws-diagram.excalidraw with basic structure (title, etc.) # Step 2: Check icon availability # Read: libraries/aws-architecture-icons/reference.md # Confirm icons exist: Internet-gateway, VPC, ELB, EC2, RDS # Step 3: Add icons with Python script python scripts/add-icon-to-diagram.py my-aws-diagram.excalidraw "Internet-gateway" 150 100 --label "Internet Gateway" python scripts/add-icon-to-diagram.py my-aws-diagram.excalidraw VPC 200 200 python scripts/add-icon-to-diagram.py my-aws-diagram.excalidraw ELB 350 250 --label "Load Balancer" python scripts/add-icon-to-diagram.py my-aws-diagram.excalidraw EC2 500 300 --label "Web Server" python scripts/add-icon-to-diagram.py my-aws-diagram.excalidraw RDS 650 350 --label "Database" # Step 4: Add connecting arrows python scripts/add-arrow.py my-aws-diagram.excalidraw 200 150 250 200 # Internet โ VPC python scripts/add-arrow.py my-aws-diagram.excalidraw 265 230 350 250 # VPC โ ELB python scripts/add-arrow.py my-aws-diagram.excalidraw 415 280 500 300 # ELB โ EC2 python scripts/add-arrow.py my-aws-diagram.excalidraw 565 330 650 350 --label "SQL" --style dashed # Result: Complete diagram with professional AWS icons, labels, and connections Benefits: No manual coordinate calculation No token consumption for icon data Deterministic, reliable results Easy to iterate and adjust positions Alternative Workflow (manual, if scripts unavailable): Check: libraries/aws-architecture-icons/reference.md exists โ Yes Read reference.md โ Find entries for Internet-gateway, VPC, ELB, EC2, RDS Load: icons/Internet-gateway.json (298 lines) icons/VPC.json (550 lines) icons/ELB.json (363 lines) icons/EC2.json (231 lines) icons/RDS.json (similar size) Total: ~2000+ lines of JSON to process Extract elements from each JSON Calculate bounding boxes and offsets for each icon Transform all coordinates (x, y) for positioning Generate unique IDs for all elements Add arrows showing data flow Add text labels Generate final .excalidraw file Challenges with manual approach: High token consumption (~2000-5000 lines) Complex coordinate math Risk of ID conflicts
This workflow works with any valid .excalidrawlib file you provide. Examples of library categories you may find on https://libraries.excalidraw.com/: Cloud service icons Kubernetes / infrastructure icons UI / Material icons Flowchart / diagram symbols Network diagram icons Availability and naming can change; verify exact library names on the site before use.
If no icon libraries are set up: Create diagrams using basic shapes (rectangles, ellipses, arrows) Use color coding and text labels to distinguish components Inform user they can add icons later or set up libraries for future diagrams The diagram will still be functional and clear, just less visually polished
See bundled references for: references/excalidraw-schema.md - Complete Excalidraw JSON schema references/element-types.md - Detailed element type specifications templates/flowchart-template.json - Basic flowchart starter templates/relationship-template.json - Relationship diagram starter templates/mindmap-template.json - Mind map starter scripts/split-excalidraw-library.py - Tool to split .excalidrawlib files scripts/README.md - Documentation for library tools scripts/.gitignore - Prevents local Python artifacts from being committed
Complex curves are simplified to straight/basic curved lines Hand-drawn roughness is set to default (1) No embedded images support in auto-generation Maximum recommended elements: 20 per diagram No automatic collision detection (use spacing guidelines)
Potential improvements: Auto-layout optimization algorithms Import from Mermaid/PlantUML syntax Template library expansion Interactive editing after generation
Writing, remixing, publishing, visual generation, and marketing content production.
Largest current source with strong distribution and engagement signals.