canvas
Canvas organizes visual references in Obsidian by letting you add images, PDFs, and wiki pages to canvas files with automatic positioning inside zones. It integrates with the /banana image capture skill and supports multiple operations like creating new canvases, managing zones, and listing existing canvases.
Canvas lets you add images, PDFs, and notes to Obsidian canvas files with automatic positioning.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-05-28
Canvas lets you add images, PDFs, and notes to Obsidian canvas files with automatic positioning. Canvas organizes visual references in Obsidian by letting you add images, PDFs, and wiki pages to canvas files with automatic positioning inside zones. It integrates with the /banana image capture skill and supports multiple operations like creating new canvases, managing zones, and listing existing canvases.
Use it when
- Canvas organizes visual reference boards using zones and groups to structure your layout.
- Canvas supports adding images, PDFs, and wiki pages to your Obsidian canvas files.
Verify before relying
Read SKILL.md below before installing (2 files). Open directory: indexed for reading, not audited.
Install
AgriciDaniel/claude-obsidian/canvas · repository language: Python
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How to add images to Obsidian canvas?
Canvas lets you add images to Obsidian canvas files with automatic positioning inside zones. You can capture images using the /banana plugin and then add them directly to your canvas. Canvas handles placement automatically, organizing your visual references without manual coordinate entry.
Can Canvas create visual boards with zones and groups?
Canvas organizes visual reference boards using zones and groups to structure your layout. You can create new canvases with auto layout, define zones to group related content, and organize images, PDFs, and wiki pages within those zones for a clean visual reference system.
What file types does Canvas support adding?
Canvas supports adding images, PDFs, and wiki pages to your Obsidian canvas files. It integrates with the /banana image capture skill, so you can seamlessly add captured images alongside other content types for comprehensive visual knowledge capture.
How does Canvas integrate with banana for images?
Canvas manages canvas files and integrates captured images from the banana plugin. After capturing images with /banana, Canvas can add them to your canvas with automatic positioning, streamlining your workflow for visual reference collection.
Can I list all visual boards in my wiki?
Canvas lets you view canvas status and list all visual boards in your wiki. This helps you manage multiple canvases and navigate between different visual reference layers you've created.
Does Canvas generate proper canvas JSON files?
Canvas generates canvas JSON with proper IDs and coordinate system for your Obsidian canvases. This ensures your visual boards are correctly formatted and compatible with Obsidian's canvas file structure.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
canvas: Visual Reference Layer
The three knowledge capture layers:
- /save → text synthesis (wiki/questions/, wiki/concepts/)
- /autoresearch → structured knowledge (wiki/sources/, wiki/concepts/)
- /canvas → visual references (wiki/canvases/)
A canvas is a JSON file Obsidian renders as an infinite visual board. This skill reads and writes canvas JSON directly. Read references/canvas-spec.md for the full format reference before making any edits. This spec aligns with the JSON Canvas open standard.
Substrate preference (v1.7+): This skill is a self-contained fallback. Prefer kepano/obsidian-skills as the authoritative substrate — its json-canvas skill is the canonical
(truncated - see the full file via the links below)
File tree — 2 files
skills/canvas/SKILL.md
skills/canvas/references/canvas-spec.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Add images, PDFs, and notes to an Obsidian canvas with automatic positioning”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
obsidian-bases enables you to transform vault notes into queryable, interactive views using Obsidian's native database layer. Define filters, computed properties, and multiple view types (table, cards, list) in .base files stored as YAML, then embed them directly in your notes. Perfect for dashboards, entity trackers, and content organization.
wiki-cli establishes the Obsidian CLI (v1.12+) as the primary transport layer for vault operations in claude-obsidian v1.7+, handling reads, writes, searches, and mutations without requiring MCP servers or REST API plugins. When the CLI is unavailable, the skill automatically falls back to direct filesystem access. Detection and fallback logic ensure reliable vault access across desktop and headless environments.
Build and modify .canvas files following the JSON Canvas Spec 1.0, adding text, file, link, and group nodes with precise positioning and connections. Manage edges between nodes, apply colors, and validate your canvas structure to ensure all references resolve correctly.
This skill enables you to build and modify .canvas files following the JSON Canvas Spec 1.0, working with nodes, edges, groups, and visual layouts. Handle text, file, link, and group node types while managing connections, colors, and positioning across an infinite canvas.
wiki transforms Obsidian into a compounding knowledge system by scaffolding vault structure from your description, organizing sources and entities, and maintaining a hot cache of recent context. Unlike RAG systems, the wiki persists as a structured artifact where cross-references and contradictions surface automatically. Route ingest, query, and maintenance tasks to specialized sub-skills while the skill handles vault setup, indexing, and knowledge layer management.
Turn any text content into structured Obsidian Canvas visualizations using mind map or freeform layouts. The skill analyzes your input, determines the best layout approach, and generates a ready-to-import JSON canvas with proper spacing, color coding, and hierarchical organization.
More skills research-render (MIT)