Canvas - Visual Collaboration

VerifiedSafe

Enables AI-powered visual collaboration using Excalidraw for creating diagrams, flowcharts, and system architectures. Use it to draw, annotate, and collaborate on visual designs, then capture screenshots or export results. Helpful whenever you need to sketch technical concepts or visualize ideas.

Sby Skills Guide Bot
DocumentationIntermediate
806/2/2026
Claude Code
#diagrams#flowcharts#excalidraw#visual-collaboration#architecture

Recommended for

Our review

Creates and manages visual diagrams using Excalidraw through AI assistance, enabling users to draw flowcharts, architecture sketches, and concept maps.

Strengths

  • Integrates seamlessly with AI chat for collaborative editing
  • Supports a wide range of diagram types
  • Allows programmatic addition and modification of elements
  • Provides real-time collaboration via listen and update tools

Limitations

  • Requires manual user interaction for initial drawing
  • Canvas state is stored locally, not cloud-synced
  • Limited to Excalidraw's feature set (no advanced UML or BPMN)
When to use it

Use when you need to quickly create or iterate on visual diagrams with AI assistance, such as system architectures or flowcharts.

When not to use it

Avoid for complex, pixel-perfect designs or when offline access to diagrams is critical.

Security analysis

Safe
Quality score90/100

The skill only uses collaborative canvas tools for creating diagrams; no shell commands, network requests, data exfiltration, or destructive actions. The tools are safe visual collaboration utilities.

No concerns found

Examples

Flowchart creation
Draw a flowchart for a user login process including error handling.
Architecture diagram
Create an architecture diagram of a microservices system with API gateway, services, and database.
Mind map
Open a canvas and sketch a mind map of our project requirements.

name: canvas description: Use when the user asks to draw diagrams, create flowcharts, sketch architecture, visualize concepts, make a canvas, open Excalidraw, or mentions visual collaboration. Provides AI-powered visual collaboration using Excalidraw. version: 1.0.0 allowed-tools: [mcp__plugin_collaborative-canvas_canvas__open_canvas, mcp__plugin_collaborative-canvas_canvas__close_canvas, mcp__plugin_collaborative-canvas_canvas__list_canvases, mcp__plugin_collaborative-canvas_canvas__save_canvas, mcp__plugin_collaborative-canvas_canvas__get_canvas_state, mcp__plugin_collaborative-canvas_canvas__update_canvas, mcp__plugin_collaborative-canvas_canvas__export_canvas, mcp__plugin_collaborative-canvas_canvas__delete_canvases, mcp__plugin_collaborative-canvas_canvas__listen, mcp__plugin_collaborative-canvas_canvas__add_to_canvas, mcp__plugin_collaborative-canvas_canvas__close_widget, mcp__plugin_collaborative-canvas_canvas__capture_screenshot]

Canvas - Visual Collaboration

Overview

Canvas provides AI-powered visual collaboration using Excalidraw. Create diagrams, flowcharts, system architectures, and visual documentation with Claude's assistance.

When to Use

  • Create diagrams or flowcharts
  • Sketch system architecture
  • Visualize concepts or ideas
  • Make technical drawings
  • Visual collaboration on designs

Workflow

  1. Open canvas: open_canvas({ name: "My Diagram" })
  2. Wait for user: listen({ drawingId: "..." })
  3. User draws in the Excalidraw window
  4. User clicks Collaborate for feedback
  5. Review: get_canvas_state({ drawingId: "..." })
  6. Add elements: save_canvas({ drawingId: "...", elements: [...] })
  7. Repeat until user clicks Finish
  8. Close: close_widget({ drawingId: "..." })

Key Tools

| Tool | Purpose | |------|---------| | open_canvas | Create or open a drawing | | listen | Wait for user collaboration | | save_canvas | Save elements to canvas | | get_canvas_state | View current drawing state | | add_to_canvas | Add elements programmatically | | close_widget | Close the Excalidraw window | | list_canvases | List all saved drawings | | capture_screenshot | Capture canvas as image |

Best Practices

  1. Always call listen after opening or saving a canvas to wait for user input
  2. Use compact element format for large diagrams to stay within token limits
  3. Respond visually - add annotations and elements when collaborating
  4. Close properly - call close_widget when finished to clean up

Element Format

When adding elements, use compact format:

{
  "elements": [
    { "type": "rectangle", "x": 100, "y": 100, "width": 200, "height": 100 },
    { "type": "text", "x": 150, "y": 130, "text": "Hello" },
    { "type": "arrow", "x": 300, "y": 150, "points": [[0, 0], [100, 50]] }
  ]
}

IDs are auto-generated if not provided.

Storage Location

Drawings are saved to ~/.local/share/collaborative-canvas/drawings/ with metadata.

Related skills