What problem does it solve? Working with open tldraw Desktop documents programmatically requires knowing the app's local server, per-launch auth token, and document ownership rules. This Skill provides the endpoints, helper commands, and recipes needed to read, edit, connect, and script live tldraw canvases without manual GUI work. ## Core Features & Use Cases - Canvas inspection and editing: List open documents, read shapes and bindings, capture screenshots, and run JavaScript against a live editor via /api/search and /api/doc/:id/exec. - Diagram generation and linting: Build flowcharts and mindmaps from Mermaid source, create bound arrow connections, and run lint checks before reporting completion. - Durable board scripts: Write script/main.js and config.js through the script workspace for clickable UI, animations, custom shapes, and shared-board-safe behavior. - Use Case: Ask the agent to arrange and connect the boxes on your open project-plan canvas; it discovers the document, creates bound arrows between shapes, lints the result, and saves the file. ## Quick Start Ask the agent to list the shapes on your currently open tldraw canvas and connect two of them with a labeled arrow.