Canvas Create logo

Canvas Create

Community
AgriciDaniel
canvas-create

Create new Obsidian Canvas files — blank with a starter structure, or from one of 12 template archetypes (presentation, flowchart, mind-map, gallery, dashboard, storyboard, knowledge-graph, mood-board, timeline, comparison, kanban, project-brief). Handles directory creation, slug generation, and starter zone setup. Triggers on: canvas create, create canvas, new canvas, canvas new, start canvas.

Overview

PublisherAgriciDaniel
Repositoryclaude-canvas
Skill namecanvas-create
Stars
301
Forks
27
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by AgriciDaniel on GitHub. Read the source before you install it.

Installation

Install the Canvas Create AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/AgriciDaniel/claude-canvas/tree/main/skills/canvas-create
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/AgriciDaniel/claude-canvas.git /tmp/claude-canvas
mkdir -p .claude/skills
cp -r /tmp/claude-canvas/skills/canvas-create .claude/skills/canvas-create
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Canvas Create in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Canvas Create on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Canvas Create is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

canvas-create: Create New Canvases


Operations

Blank Canvas (/canvas create [name])

  1. Slugify the name: lowercase, spaces to hyphens, strip special chars.
  2. Determine canvas directory (see canvas orchestrator for context detection).
  3. Create [canvas_dir]/[slug].canvas with starter structure:
json
{
  "nodes": [
    {
      "id": "zone-default",
      "type": "group",
      "label": "General",
      "x": -400, "y": -140, "width": 800, "height": 400, "color": "4"
    },
    {
      "id": "title",
      "type": "text",
      "text": "# [Name]\n\nDrop images, PDFs, and notes here.",
      "x": -400, "y": -300, "width": 400, "height": 120, "color": "6"
    }
  ],
  "edges": []
}

Note: Groups MUST come before content nodes in the array (z-index ordering — groups render behind content).

  1. Report: "Created [canvas_dir]/[slug].canvas. Open it in Obsidian to view."

Templated Canvas (/canvas create [name] from [template])

  1. Validate template name against the 12 archetypes.
  2. If no template name given or unclear, show available templates:
presentation   — Slide deck (1200x675, Advanced Canvas)
flowchart      — Process flow (Sugiyama/dagre layout)
mind-map       — Radial center-out expansion
gallery        — Grid of image nodes
dashboard      — Metric cards + charts + zones
storyboard     — Linear scene cards + script annotations
knowledge-graph — Force-directed entity map
mood-board     — Asymmetric image grid
timeline       — Horizontal event sequence
comparison     — Side-by-side columns
kanban         — Column zones (Todo/Doing/Done)
project-brief  — Hero zone + objectives + deliverables
  1. Ask the user for template-specific parameters (title, number of items, color scheme).
  2. Delegate to canvas-template skill for instantiation.
  3. MANDATORY: Replace ALL placeholder text in every node with real, relevant content based on the title and topic. This is not optional:
    • Read the generated canvas JSON
    • For each text node, replace generic text ("Describe this step", "YYYY-MM-DD", "Value: 0") with real content relevant to the canvas title
    • Use the Edit tool to update each node's text field
    • This is the difference between a skeleton and a finished canvas
  4. Run python3 scripts/canvas_validate.py <path> to verify validity.
  5. Report the created canvas with node/zone counts.

Slug Generation

python
import re
def slugify(name):
    slug = name.lower().strip()
    slug = re.sub(r'[^a-z0-9\s-]', '', slug)
    slug = re.sub(r'[\s]+', '-', slug)
    slug = re.sub(r'-+', '-', slug)
    return slug.strip('-')

Directory Rules

  • Vault mode (wiki/canvases/ exists): create there, media to _attachments/images/canvas/
  • Standalone mode: create in .canvases/, media to .canvases/assets/
  • Create the directory if it doesn't exist.
  • Never overwrite an existing canvas without asking the user.

Frequently asked questions

What does the Canvas Create AI skill do?

Create new Obsidian Canvas files — blank with a starter structure, or from one of 12 template archetypes (presentation, flowchart, mind-map, gallery, dashboard, storyboard, knowledge-graph, mood-board, timeline, comparison, kanban, project-brief). Handles directory creation, slug generation, and starter zone setup. Triggers on: canvas create, create canvas, new canvas, canvas new, start canvas.

Why use Canvas Create on TypingMind?

Because you install it once and use it with any model. Canvas Create is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Canvas Create in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/AgriciDaniel/claude-canvas/tree/main/skills/canvas-create. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Canvas Create?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Canvas Create?

As many as you like. As long as a model supports skills, you can use Canvas Create with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Canvas Create AI skill free?

Yes. It is published on GitHub by AgriciDaniel under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇