Agent skill
canvas-template
Browse and instantiate 12 canvas template archetypes: presentation, flowchart, mind-map, gallery, dashboard, storyboard, knowledge-graph, mood-board, timeline, comparison, kanban, project-brief. Each template generates a ready-to-use canvas with proper layout, zones, and placeholder content. Triggers on: canvas template, canvas template list, browse templates, canvas from template, use template, show archetypes.
Install this agent skill to your Project
npx add-skill https://github.com/AgriciDaniel/claude-canvas/tree/main/skills/canvas-template
SKILL.md
canvas-template: Template Browser & Instantiation
Operations
List Templates (/canvas template list)
Run the template script to list available archetypes:
python3 scripts/canvas_template.py --list
Present the results as a formatted table:
| Archetype | Layout | Description |
|---|---|---|
| presentation | linear-vertical | Slide deck for Advanced Canvas (1200x675 slides) |
| flowchart | linear-vertical → auto dagre | Process flow with connected step nodes |
| mind-map | grid → auto radial | Radial expansion from central topic |
| gallery | grid | Image placeholder grid with title zone |
| dashboard | grid | Metric cards + status zones |
| storyboard | linear-horizontal | Scene cards for video planning |
| knowledge-graph | grid → auto force | Entity nodes for relationship mapping |
| mood-board | grid | Asymmetric image grid for creative direction |
| timeline | linear-horizontal | Horizontal event sequence |
| comparison | grid | Side-by-side columns for option analysis |
| kanban | grid | Todo/Doing/Done column board |
| project-brief | linear-vertical | Stacked zones for project kickoff |
Instantiate Template (/canvas template use [name])
- Validate the template name against the 12 archetypes.
- Ask for required parameters:
- title (all templates): What's the canvas title?
- Template-specific params (slide_count, step_count, image_count, etc.)
- Determine output path (canvas directory detection from orchestrator).
- Run instantiation:
python3 scripts/canvas_template.py [template] [output_path] --param title="[title]" --param [key]=[value]
- Validate the output:
python3 scripts/canvas_validate.py [output_path]
- MANDATORY: Content Quality Gate — Read the orchestrator's Quality Standards section. Before reporting:
- Replace ALL placeholder text in every node with real content relevant to the title
- Verify no "Describe this", "YYYY-MM-DD", "Value: 0", or "Content goes here" strings remain
- Run
python3 scripts/canvas_validate.pyand confirm 0 errors, 0 overlap warnings - If the template has
post_layout(mind-map→radial, knowledge-graph→force, flowchart→dagre), confirm the layout was applied
- Report: "Created [name] canvas at [path] with [N] nodes, [E] edges, [G] groups."
Template Parameters
Each template has defaults that can be overridden:
| Template | Key Parameters | Defaults |
|---|---|---|
| presentation | slide_count | 6 |
| flowchart | step_count | 5 |
| mind-map | branch_count | 5 |
| gallery | image_count, columns | 9, 3 |
| dashboard | metric_count | 4 |
| storyboard | scene_count | 6 |
| knowledge-graph | entity_count | 8 |
| mood-board | image_count | 8 |
| timeline | event_count | 6 |
| comparison | criteria_count | 4 |
| kanban | cards_per_column | 3 |
| project-brief | objective_count | 3 |
All templates accept color_title, color_body, color_accent to override the color scheme (values: "1"-"6").
Post-Instantiation
After creating a template canvas, suggest next steps based on the archetype:
- presentation: "Add content to each slide. Use
/canvas add bananafor hero images." - gallery/mood-board: "Replace placeholder slots with
/canvas add imageor/canvas add banana." - flowchart: "Edit step text. Run
/canvas layout dagreto re-flow after changes." - mind-map: "Edit branches. Run
/canvas layout radialfor proper expansion." - knowledge-graph: "Add entities and edges. Run
/canvas layout forceto visualize relationships." - kanban: "Add task cards with
/canvas add text. Move between columns manually in Obsidian."
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
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.
canvas
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.
canvas-export
Export Obsidian Canvas files to PNG, SVG, or PDF formats. Uses the Advanced Canvas plugin's built-in export when Obsidian is running, or falls back to Playwright browser-based screenshot capture. Supports single canvas export, presentation slide-per-page PDF export, and batch export. Triggers on: canvas export, export canvas, canvas to png, canvas to pdf, canvas to svg, save canvas as image, screenshot canvas, export presentation.
canvas-generate
AI-orchestrated full canvas generation. Given a description, detects the best archetype, generates content and visuals, instantiates a template, applies layout, and produces a complete canvas. The flagship command. Dispatches canvas-media and canvas-composer agents for parallel asset generation. Triggers on: canvas generate, generate canvas, create a visual board, build me a canvas, make a canvas about, canvas from description, auto-generate canvas, full canvas generation.
canvas-populate
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.
canvas-present
Build presentation-mode canvases for the Advanced Canvas plugin. Creates slide-deck canvases with 1200x675 group nodes connected by edges for arrow-key navigation. Supports title slides, content slides with images, full-text slides, and optional script annotation columns for video planning. Triggers on: canvas present, create presentation, build slide deck, canvas slides, make a presentation, presentation canvas, present from notes, slide deck canvas, canvas presentation.
Didn't find tool you were looking for?