Obsidian Canvas Builder

What it does

When your agent uses it

• Creating a mood board, flowchart or storyboard as an Obsidian canvas
• Building a presentation from notes inside Obsidian Canvas
• Re-laying out a cluttered canvas with a different algorithm
• Exporting a canvas to PNG, SVG or PDF

Example prompts

• “Create a canvas from the timeline template for our product launch.”
• “Lay out my research canvas with a radial layout.”
• “Build a presentation canvas from my meeting notes.”
• “Add the latest AI-generated images to the mood board canvas.”

Requirements

• Obsidian, or a project folder to hold the .canvas files

Workflow steps

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

1. 1If wiki/canvases/ exists in the current directory or a parent: use it (claude-obsidian vault mode).
2. 2Otherwise: use .canvases/ in the current working directory (standalone mode).
3. 3Create the directory if it doesn't exist.

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

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

• Network

  No URLs in SKILL.md.

  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 Builder loads about 2.5k tokens when it runs, and up to ~13k if it reads all its reference files. Until then it costs about 188 tokens; SKILL.md has 910 words of instructions outside code blocks.

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

~188

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

~2.5k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~13k

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). 910 words, ~2,486 tokens.

name

canvas

description

AI-orchestrated visual production for Obsidian Canvas. Create presentations, flowcharts, mood boards, knowledge graphs, galleries, storyboards, timelines, dashboards, and more with intelligent layout and AI-generated content. Claude acts as Creative Director — dispatching sub-agents for image generation, SVG diagrams, GIF creation, and spatial layout. Supports 12 template archetypes, 6 layout algorithms, and Advanced Canvas presentation mode. Triggers on: /canvas, create canvas, build canvas, make a presentation, visual board, mood board, flowchart canvas, storyboard, canvas from template, lay out canvas, export canvas, canvas layout, canvas generate, add to canvas, put this on the canvas, open canvas, canvas present, canvas template.

main.canvas              14 nodes (8 images, 3 text, 2 file, 1 group)
design-ideas.canvas      42 nodes (30 images, 4 text, 8 groups)

def next_position(canvas_nodes, target_zone_label, new_w, new_h):
    # Find zone group node
    zone = next((n for n in canvas_nodes
                 if n.get('type') == 'group'
                 and n.get('label') == target_zone_label), None)

    if zone is None:
        # No zone: place below all content
        max_y = max((n['y'] + n.get('height', 0) for n in canvas_nodes), default=-140)
        return snap_grid(-400, max_y + 60)

    zx, zy = zone['x'], zone['y']
    zw, zh = zone['width'], zone['height']

    # Nodes inside this zone (exclude groups)
    inside = [n for n in canvas_nodes
              if n.get('type') != 'group'
              and zx <= n['x'] < zx + zw
              and zy <= n['y'] < zy + zh]

    if not inside:
        return snap_grid(zx + 20, zy + 20)

    # Find the bottom-most row: nodes whose bottom edge is closest to the zone bottom
    max_bottom = max(n['y'] + n.get('height', 0) for n in inside)
    # Nodes on the last row: those whose top y is within one row-height of the bottom
    last_row = [n for n in inside if n['y'] + n.get('height', 0) >= max_bottom - 20]
    if not last_row:
        last_row = inside  # fallback

    rightmost_x = max(n['x'] + n.get('width', 0) for n in last_row)
    next_x = rightmost_x + 40

    if next_x + new_w > zx + zw:
        # Overflow: new row below the current last row
        return snap_grid(zx + 20, max_bottom + 20)

    # Same row: align to top of the LAST row (not all nodes)
    current_row_y = min(n['y'] for n in last_row)
    return snap_grid(next_x, current_row_y)

def snap_grid(x, y, grid=20):
    return (round(x / grid) * grid, round(y / grid) * grid)

{
  "nodes": [],
  "edges": []
}

© 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

SKILL.md and 7 other files (references) in skills/canvas of AgriciDaniel/claude-canvas.

• SKILL.md
• references/canvas-spec.md
• references/layout-algorithms.md
• references/media-guide.md
• references/mermaid-patterns.md
• references/performance-guide.md
• references/presentation-spec.md
• references/template-catalog.md

Open the folder on GitHubat commit 05b808c