Obsidian Canvas Creator logo

Obsidian Canvas Creator

CommunityPopular
axtonliu
obsidian-canvas-creator

Create Obsidian Canvas files from text content, supporting both MindMap and freeform layouts. Use this skill when users want to visualize content as an interactive canvas, create mind maps, or organize information spatially in Obsidian format.

Overview

Publisheraxtonliu
Repositoryaxton-obsidian-visual-skills
Skill nameobsidian-canvas-creator
Stars
3.6K
Forks
321
Bundled files
4
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.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Obsidian Canvas Creator 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.
  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/axtonliu/axton-obsidian-visual-skills.git /tmp/axton-obsidian-visual-skills
mkdir -p .claude/skills
cp -r /tmp/axton-obsidian-visual-skills/obsidian-canvas-creator .claude/skills/obsidian-canvas-creator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Obsidian Canvas Creator 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 Obsidian Canvas Creator 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 Obsidian Canvas Creator 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.

Obsidian Canvas Creator

Transform text content into structured Obsidian Canvas files with support for MindMap and freeform layouts.

When to Use This Skill

  • User requests to create a canvas, mind map, or visual diagram from text
  • User wants to organize information spatially
  • User mentions "Obsidian Canvas" or similar visualization tools
  • Converting structured content (articles, notes, outlines) into visual format

Core Workflow

1. Analyze Content

Read and understand the input content:

  • Identify main topics and hierarchical relationships
  • Extract key points, facts, and supporting details
  • Note any existing structure (headings, lists, sections)

2. Determine Layout Type

Ask user to choose or infer from context:

MindMap Layout:

  • Radial structure from center
  • Parent-child relationships
  • Clear hierarchy
  • Good for: brainstorming, topic exploration, hierarchical content

Freeform Layout:

  • Custom positioning
  • Flexible relationships
  • Multiple connection types
  • Good for: complex networks, non-hierarchical content, custom arrangements

3. Plan Structure

For MindMap:

  • Identify central concept (root node)
  • Map primary branches (main topics)
  • Organize secondary branches (subtopics)
  • Position leaf nodes (details)

For Freeform:

  • Group related concepts
  • Identify connection patterns
  • Plan spatial zones
  • Consider visual flow

4. Generate Canvas

Create JSON following the Canvas specification:

Node Creation:

  • Assign unique 8-12 character hex IDs
  • Set appropriate dimensions based on content length
  • Apply consistent color schemes
  • Ensure no coordinate overlaps

Edge Creation:

  • Connect parent-child relationships
  • Use appropriate arrow styles
  • Add labels for complex relationships
  • Choose line styles (straight for hierarchy, curved for cross-references)

Grouping (Optional):

  • Create visual containers for related nodes
  • Use subtle background colors
  • Add descriptive labels

5. Apply Layout Algorithm

MindMap Layout Calculations:

Refer to references/layout-algorithms.md for detailed algorithms. Key principles:

  • Center root at (0, 0)
  • Distribute primary nodes radially
  • Space secondary nodes based on sibling count
  • Maintain minimum spacing: 320px horizontal, 200px vertical

Freeform Layout Principles:

  • Start with logical groupings
  • Position groups with clear separation
  • Connect across groups with curved edges
  • Balance visual weight across canvas

6. Validate and Output

Before outputting:

Validation Checklist:

  • All nodes have unique IDs
  • No coordinate overlaps (check distance > node dimensions + spacing)
  • All edges reference valid node IDs
  • Groups (if any) have labels
  • Colors use consistent format (hex or preset numbers)
  • JSON is properly escaped (Chinese quotes: 『』 for double, 「」 for single)

Output Format:

  • Complete, valid JSON Canvas file
  • No additional explanation text
  • Directly importable into Obsidian

Node Sizing Guidelines

Text Length-Based Sizing:

  • Short text (<30 chars): 220 × 100 px
  • Medium text (30-60 chars): 260 × 120 px
  • Long text (60-100 chars): 320 × 140 px
  • Very long text (>100 chars): 320 × 180 px

Color Schemes

Preset Colors (Recommended):

  • "1" - Red (warnings, important)
  • "2" - Orange (action items)
  • "3" - Yellow (questions, notes)
  • "4" - Green (positive, completed)
  • "5" - Cyan (information, details)
  • "6" - Purple (concepts, abstract)

Custom Hex Colors: Use for brand consistency or specific themes. Always use uppercase format: "#4A90E2"

Critical Rules

  1. Quote Handling:

    • Chinese double quotes → 『』
    • Chinese single quotes → 「」
    • English double quotes → \"
  2. ID Generation:

    • 8-12 character random hex strings
    • Must be unique across all nodes and edges
  3. Z-Index Order:

    • Output groups first (bottom layer)
    • Then subgroups
    • Finally text/link nodes (top layer)
  4. Spacing Requirements:

    • Minimum horizontal: 320px between node centers
    • Minimum vertical: 200px between node centers
    • Account for node dimensions when calculating
  5. JSON Structure:

    • Top level contains only nodes and edges arrays
    • No extra wrapping objects
    • No comments in output
  6. No Emoji:

    • Do not use any Emoji symbols in node text
    • Use color coding or text labels for visual distinction instead

Examples

Simple MindMap Request

User: "Create a mind map about solar system planets"

Process:

  1. Identify center: "Solar System"
  2. Primary branches: Inner Planets, Outer Planets, Dwarf Planets
  3. Secondary nodes: Individual planets with key facts
  4. Apply radial layout
  5. Generate JSON with proper spacing

Freeform Content Request

User: "Turn this article into a canvas" + [article text]

Process:

  1. Extract article structure (intro, body sections, conclusion)
  2. Identify key concepts and relationships
  3. Group related sections spatially
  4. Connect with labeled edges
  5. Apply freeform layout with clear zones

Reference Documents

  • Canvas Specification: references/canvas-spec.md - Complete JSON Canvas format specification
  • Layout Algorithms: references/layout-algorithms.md - Detailed positioning algorithms for both layout types

Load these references when:

  • Need specification details for edge cases
  • Implementing complex layout calculations
  • Troubleshooting validation errors

Tips for Quality Canvases

  1. Keep text concise: Each node should be scannable (<2 lines preferred)
  2. Use hierarchy: Group by importance and relationship
  3. Balance the canvas: Distribute nodes to avoid clustering
  4. Strategic colors: Use colors to encode meaning, not just decoration
  5. Meaningful connections: Only add edges that clarify relationships
  6. Test in Obsidian: Verify the output opens correctly

Common Pitfalls to Avoid

  • Overlapping nodes (always check distances)
  • Inconsistent quote escaping (breaks JSON parsing)
  • Missing group labels (causes sidebar navigation issues)
  • Too much text in nodes (use file nodes for long content)
  • Duplicate IDs (each must be unique)
  • Unconnected nodes (unless intentional islands)

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Obsidian Canvas Creator AI skill do?

Create Obsidian Canvas files from text content, supporting both MindMap and freeform layouts. Use this skill when users want to visualize content as an interactive canvas, create mind maps, or organize information spatially in Obsidian format.

Why use Obsidian Canvas Creator on TypingMind?

Because you install it once and use it with any model. Obsidian Canvas Creator 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 Obsidian Canvas Creator in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/axtonliu/axton-obsidian-visual-skills/tree/main/obsidian-canvas-creator. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Obsidian Canvas Creator?

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 Obsidian Canvas Creator?

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

Is the Obsidian Canvas Creator AI skill free?

Yes. It is published on GitHub by axtonliu 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 👇