json-canvas
Verifiedby kepano · Updated Apr 16, 2026
Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian.
See It In Action
Let me explore the project to find the relevant files.
I have the full picture. The canvas has 3 timeline nodes (header, detection, initial response) plus the Datadog link. The outage notes have 5 more timeline events, root cause analysis, mitigation steps, and follow-up actions that need to be added.
Canvas updated. Here's what was added from your outage notes:
Timeline (left column) — 5 new nodes completing the flow:
- Investigation (14:41) — connection pool exhaustion on payment-db-primary
- Root Cause Identified (14:48) — unthrottled
backfill_invoice_idxmigration - Mitigation (14:52) — killed migration, connections recovering
- Recovery (14:58) — latency normal, error rate <0.1%
- All-Clear (15:05) — Slack + PagerDuty resolved (green)
Detail cards (right column) — 3 new nodes linked laterally:
- Root Cause Analysis (red) — batch_size 50000 vs intended 500, row locks exhausting 50-connection pool, CI gap on migration configs
- Mitigation Steps (yellow) — pg_terminate_backend, pod restart, Datadog verification, scheduler pause
- Follow-up Actions (cyan) — 5 action items with checkboxes (CI validation, pool alerting, kill-switch, UTC/PST cron retro, runbook update)
All timeline nodes are connected top-to-bottom with arrows, and the detail cards branch off to the right from their corresponding timeline events. Ready for the postmortem.
Permissions
| Scope | Description |
|---|---|
| filesystem:read | |
| filesystem:write |
SKILL.md
JSON Canvas Skill
File Structure
A canvas file (.canvas) contains two top-level arrays following the JSON Canvas Spec 1.0:
{
"nodes": [],
"edges": []
}
nodes(optional): Array of node objectsedges(optional): Array of edge objects connecting nodes
Common Workflows
1. Create a New Canvas
- Create a
.canvasfile with the base structure{"nodes": [], "edges": []} - Generate unique 16-character hex IDs for each node (e.g.,
"6f0ad84f44ce9c17") - Add nodes with required fields:
id,type,x,y,width,height - Add edges referencing valid node IDs via
fromNodeandtoNode - Validate: Parse the JSON to confirm it is valid. Verify all
fromNode/toNodevalues exist in the nodes array
2. Add a Node to an Existing Canvas
- Read and parse the existing
.canvasfile - Generate a unique ID that does not collide with existing node or edge IDs
- Choose position (
x,y) that avoids overlapping existing nodes (leave 50-100px spacing) - Append the new node object to the
nodesarray - Optionally add edges connecting the new node to existing nodes
- Validate: Confirm all IDs are unique and all edge references resolve to existing nodes
3. Connect Two Nodes
- Identify the source and target node IDs
- Generate a unique edge ID
- Set
fromNodeandtoNodeto the source and target IDs - Optionally set
fromSide/toSide(top, right, bottom, left) for anchor points - Optionally set
labelfor descriptive text on the edge - Append the edge to the
edgesarray - Validate: Confirm both
fromNodeandtoNodereference existing node IDs
4. Edit an Existing Canvas
- Read and parse the
.canvasfile as JSON - Locate the target node or edge by
id - Modify the desired attributes (text, position, color, etc.)
- Write the updated JSON back to the file
- Validate: Re-check all ID uniqueness and edge reference integrity after editing
Nodes
Nodes are objects placed on the canvas. Array order determines z-index: first node = bottom layer, last node = top layer.
Generic Node Attributes
| Attribute | Required | Type | Description |
|---|---|---|---|
id | Yes | string | Unique 16-char hex identifier |
type | Yes | string | text, file, link, or group |
x | Yes | integer | X position in pixels |
y | Yes | integer | Y position in pixels |
width | Yes | integer | Width in pixels |
height | Yes | integer | Height in pixels |
color | No | canvasColor | Preset "1"-"6" or hex (e.g., "#FF0000") |
Text Nodes
| Attribute | Required | Type | Description |
|---|---|---|---|
text | Yes | string | Plain text with Markdown syntax |
{
"id": "6f0ad84f44ce9c17",
"type": "text",
"x": 0,
"y": 0,
"width": 400,
"height": 200,
"text": "# Hello World\n\nThis is **Markdown** content."
}
Newline pitfall: Use \n for line breaks in JSON strings. Do not use the literal \\n -- Obsidian renders that as the characters \ and n.
File Nodes
| Attribute | Required | Type | Description |
|---|---|---|---|
file | Yes | string | Path to file within the system |
subpath | No | string | Link to heading or block (starts with #) |
{
"id": "a1b2c3d4e5f67890",
"type": "file",
"x": 500,
"y": 0,
"width": 400,
"height": 300,
"file": "Attachments/diagram.png"
}
Link Nodes
| Attribute | Required | Type | Description |
|---|---|---|---|
url | Yes | string | External URL |
{
"id": "c3d4e5f678901234",
"type": "link",
"x": 1000,
"y": 0,
"width": 400,
"height": 200,
"url": "https://obsidian.md"
}
Group Nodes
Groups are visual containers for organizing other nodes. Position child nodes inside the group's bounds.
| Attribute | Required | Type | Description |
|---|---|---|---|
label | No | string | Text label for the group |
background | No | string | Path to background image |
backgroundStyle | No | string | cover, ratio, or repeat |
{
"id": "d4e5f6789012345a",
"type": "group",
"x": -50,
"y": -50,
"width": 1000,
"height": 600,
"label": "Project Overview",
"color": "4"
}
Edges
Edges connect nodes via fromNode and toNode IDs.
| Attribute | Required | Type | Default | Description |
|---|---|---|---|---|
id | Yes | string | - | Unique identifier |
fromNode | Yes | string | - | Source node ID |
fromSide | No | string | - | top, right, bottom, or left |
fromEnd | No | string | none | none or arrow |
toNode | Yes | string | - | Target node ID |
toSide | No | string | - | top, right, bottom, or left |
toEnd | No | string | arrow | none or arrow |
color | No | canvasColor | - | Line color |
label | No | string | - | Text label |
{
"id": "0123456789abcdef",
"fromNode": "6f0ad84f44ce9c17",
"fromSide": "right",
"toNode": "a1b2c3d4e5f67890",
"toSide": "left",
"toEnd": "arrow",
"label": "leads to"
}
Colors
The canvasColor type accepts either a hex string or a preset number:
| Preset | Color |
|---|---|
"1" | Red |
"2" | Orange |
"3" | Yellow |
"4" | Green |
"5" | Cyan |
"6" | Purple |
Preset color values are intentionally undefined -- applications use their own brand colors.
ID Generation
Generate 16-character lowercase hexadecimal strings (64-bit random value):
"6f0ad84f44ce9c17"
"a3b2c1d0e9f8a7b6"
Layout Guidelines
- Coordinates can be negative (canvas extends infinitely)
xincreases right,yincreases down; position is the top-left corner- Space nodes 50-100px apart; leave 20-50px padding inside groups
- Align to grid (multiples of 10 or 20) for cleaner layouts
| Node Type | Suggested Width | Suggested Height |
|---|---|---|
| Small text | 200-300 | 80-150 |
| Medium text | 300-450 | 150-300 |
| Large text | 400-600 | 300-500 |
| File preview | 300-500 | 200-400 |
| Link preview | 250-400 | 100-200 |
Validation Checklist
After creating or editing a canvas file, verify:
- All
idvalues are unique across both nodes and edges - Every
fromNodeandtoNodereferences an existing node ID - Required fields are present for each node type (
textfor text nodes,filefor file nodes,urlfor link nodes) typeis one of:text,file,link,groupfromSide/toSidevalues are one of:top,right,bottom,leftfromEnd/toEndvalues are one of:none,arrow- Color presets are
"1"through"6"or valid hex (e.g.,"#FF0000") - JSON is valid and parseable
If validation fails, check for duplicate IDs, dangling edge references, or malformed JSON strings (especially unescaped newlines in text content).
Complete Examples
See references/EXAMPLES.md for full canvas examples including mind maps, project boards, research canvases, and flowcharts.
References
FAQ
What does json-canvas do?
Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian.
When should I use json-canvas?
Use it when you need a repeatable workflow that produces code diff.
What does json-canvas output?
In the evaluated run it produced code diff.
How do I install or invoke json-canvas?
Ask the agent to use this skill when the task matches its documented workflow.
Which agents does json-canvas support?
Agent support is inferred from the source, but not explicitly declared.
What tools, channels, or permissions does json-canvas need?
It uses no extra tools; channels commonly include diff; permissions include filesystem:read, filesystem:write.
Is json-canvas safe to install?
Static analysis marked this skill as medium risk; review side effects and permissions before enabling it.
How is json-canvas different from an MCP or plugin?
A skill packages instructions and workflow conventions; tools, MCP servers, and plugins are dependencies the skill may call during execution.
Does json-canvas outperform not using a skill?
About json-canvas
When to use json-canvas
When you need to create a new .canvas file with nodes and edges. When you want to edit or connect items in an existing JSON Canvas document. When you need to validate canvas structure, IDs, and edge references.
When json-canvas is not the right choice
When you need graphical editing inside a visual canvas UI rather than direct file manipulation. When the task involves unrelated diagram formats instead of JSON Canvas files.
What it produces
Produces code diff.