Automated summary
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)
Use when you need to quickly create or iterate on visual diagrams with AI assistance, such as system architectures or flowcharts.
Avoid for complex, pixel-perfect designs or when offline access to diagrams is critical.
Security analysis
SafeThe 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
How this analysis is madeExamples
Draw a flowchart for a user login process including error handling.Create an architecture diagram of a microservices system with API gateway, services, and database.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
- Open canvas:
open_canvas({ name: "My Diagram" }) - Wait for user:
listen({ drawingId: "..." }) - User draws in the Excalidraw window
- User clicks Collaborate for feedback
- Review:
get_canvas_state({ drawingId: "..." }) - Add elements:
save_canvas({ drawingId: "...", elements: [...] }) - Repeat until user clicks Finish
- 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
- Always call listen after opening or saving a canvas to wait for user input
- Use compact element format for large diagrams to stay within token limits
- Respond visually - add annotations and elements when collaborating
- 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.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/canvas-visual-collaboration-mm8o525q/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/canvas-visual-collaboration-mm8o525q' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/canvas-visual-collaboration-mm8o525q/download' --output '.skill-downloads/canvas-visual-collaboration-mm8o525q/SKILL.md.part' && mv '.skill-downloads/canvas-visual-collaboration-mm8o525q/SKILL.md.part' '.skill-downloads/canvas-visual-collaboration-mm8o525q/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/canvas-visual-collaboration-mm8o525q/SKILL.md' && test -s '.skill-downloads/canvas-visual-collaboration-mm8o525q/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/canvas' && cp -R '.skill-downloads/canvas-visual-collaboration-mm8o525q' '.claude/skills/canvas'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/canvas-visual-collaboration-mm8o525q'openskills read 'canvas-visual-collaboration-mm8o525q'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/canvas-visual-collaboration-mm8o525q/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Supabase Docs Authoring
Documentation
Write, edit, and review Supabase documentation content including guides, tutorials, reference docs, and partials. Follow style guides and MDX/TOML validation rules.
Create Architecture Decision Record
Documentation
Create a new Architecture Decision Record with sequential numbering, register it in the AgentDB graph, and link related ADRs.
Plan update with deep research
Documentation
Updates a plan document by launching parallel subagents to analyze a topic across all compiler passes, then consolidates findings into the plan doc.