Stats
Actions
Tags
From trayce
Use when the user wants to draw, sketch, or send visual content to this conversation via the trayce canvas. Also use when asked to push, send, or place images on a canvas. Triggers on mentions of drawing, sketching, canvas, visual, trayce, or pushing images.
How this skill is triggered — by the user, by Claude, or both
Slash command
/trayce:trayceThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Browser canvas connected to this Claude Code session via MCP Channels. Users draw sketches and submit them with optional prompt text. You can push images back to their canvas.
Browser canvas connected to this Claude Code session via MCP Channels. Users draw sketches and submit them with optional prompt text. You can push images back to their canvas.
Submissions arrive as channel notifications. Read the PNG with the Read tool — it's a file path, not inline data. The path comes from the notification (it will be under the OS temp dir on whichever platform the server is running).
<channel source="trayce" image_path="{path from notification}">
User's prompt text
</channel>
Use mcp__trayce__push_image. Always prefer file_path — it avoids context window limits.
push_image(file_path: "<absolute path to image>", label: "Architecture")
| Param | Usage |
|---|---|
file_path | Absolute path to PNG/JPEG on disk. Always use this. |
image_base64 | Only for tiny inline data (<50KB). Avoid. |
label | Layer name in the canvas UI. Optional. |
Images arrive as hidden, movable/resizable transform layers.
Workflow: Save image to disk first (e.g., download with curl, generate with a tool), then push via file_path.
Use the cross-platform TypeScript scripts — they work on Linux, macOS, and Windows.
| Action | Command |
|---|---|
| Start | bun run ${CLAUDE_PLUGIN_ROOT}/../scripts/start.ts |
| Stop | bun run ${CLAUDE_PLUGIN_ROOT}/../scripts/stop.ts |
start.ts prints the server status as JSON ({"status":"existing"|"new","url":"...","pid":...}); if a server is already running, it reports the existing one without relaunching.
npx claudepluginhub sds-mode/trayce --plugin trayceManages Obsidian canvas files as visual reference boards: creates canvases, adds images/text/PDFs/wiki pages with auto-positioning into zones, lists contents, and integrates with image capture.
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.
Generates images, icons, diagrams, patterns, storyboards; edits and restores photos using Nano Banana MCP server with Gemini models. Auto-activates on image requests.