Obsidian Canvas Populator

What it does

When your agent uses it

• Adding an image or PDF to an Obsidian Canvas you already have
• Dropping a text card or web link onto a canvas
• Grouping existing nodes into a labeled zone
• Connecting two canvas nodes with an edge

Example prompts

• “Add ./media/architecture.png to my project canvas inside the Design zone.”
• “Put a text card on the canvas that says Launch checklist due Friday.”
• “Connect the Research note node to the Summary node on my planning canvas.”

Requirements

• An existing Obsidian Canvas file
• Python 3 with Pillow, or ImageMagick, for image sizing

Workflow steps

9 steps, taken from the first numbered list in SKILL.md.

1. 1Read the target canvas JSON. Parse nodes and edges arrays.
2. 2Collect existing IDs to prevent collisions.
3. 3Generate a new ID: [type]-[slug]-[unix-timestamp].
4. 4Calculate position using the auto-positioning algorithm (see canvas orchestrator).
5. 5Spacing check: Verify the calculated position has at least 80px horizontal and 60px vertical gap from ALL existing content nodes. If not…
6. 6Append the new node to the nodes array (after any groups — z-index ordering).
7. 7Validate: Run python3 scripts/canvas_validate.py — check for overlaps and node count.
8. 8Write the updated canvas JSON.
9. 9Report: "Added [description] to [zone] zone at position ([x], [y])."

What it can do on your machine

Read from SKILL.md and the folder at commit 05b808c. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • python3
  • curl

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Obsidian Canvas Populator loads about 1.6k tokens when it runs. Until then it costs about 115 tokens; SKILL.md has 688 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~115

When it runs · the whole SKILL.md, loaded when a task matches

~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from AgriciDaniel/claude-canvas at commit 05b808c, republished under its MIT licence (© AgriciDaniel). 688 words, ~1,622 tokens.

name

canvas-populate

description

Add content to existing Obsidian Canvas files. Supports all node types: images (with auto aspect ratio detection), text cards, PDFs, wiki notes, web links, Mermaid diagrams, SVGs, GIFs, AI-generated images via banana. Also adds zones (groups), edges between nodes, and imports recent banana images. Triggers on: canvas add, add to canvas, put on canvas, canvas zone, canvas connect, canvas from banana, add image to canvas, add text to canvas.

user-invocable

false

python3 -c "from PIL import Image; img=Image.open('[path]'); print(img.width, img.height)"
# or fallback
identify -format '%w %h' [path]

{
  "id": "text-[slug]-[timestamp]",
  "type": "text",
  "text": "[content]",
  "x": 0, "y": 0,
  "width": 300, "height": 120
}

{
  "id": "link-[slug]-[timestamp]",
  "type": "link",
  "url": "[url]",
  "x": 0, "y": 0,
  "width": 400, "height": 120
}

{
  "id": "text-mermaid-[timestamp]",
  "type": "text",
  "text": "```mermaid\n[code]\n```",
  "x": 0, "y": 0,
  "width": 500, "height": 400,
  "color": "5"
}

{
  "id": "zone-[slug]-[timestamp]",
  "type": "group",
  "label": "[name]",
  "x": -400,
  "y": "[max_y]",
  "width": 1000,
  "height": 400,
  "color": "[color or '4']"
}

{
  "id": "e-[from-slug]-[to-slug]-[timestamp]",
  "fromNode": "[from-id]",
  "toNode": "[to-id]",
  "toEnd": "arrow"
}

© AgriciDaniel, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/canvas-populate of AgriciDaniel/claude-canvas.

Open the folder on GitHubat commit 05b808c