canvas-ops

Control the agent-hand canvas editor via JSON commands for nodes and edges.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/weykon/agent-hand --skill canvas-ops
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: canvas-ops
Source: https://github.com/weykon/agent-hand/tree/main/skills/canvas-ops
Command: npx skills add https://github.com/weykon/agent-hand --skill canvas-ops

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill allows for the programmatic manipulation and querying of the agent-hand canvas workflow editor, enabling automated creation and management of visual workflows.

Core Features & Use Cases

  • Node and Edge Management: Add, update, and remove nodes and edges to build or modify canvas diagrams.
  • Canvas State Querying: Retrieve information about nodes, edges, and the overall canvas state.
  • Workflow Automation: Integrate canvas operations into automated agent workflows for dynamic diagram generation.
  • Use Case: An agent can automatically generate a visual representation of a complex process by adding nodes for each step and edges to show dependencies, all triggered by an external event.

Quick Start

Use the canvas-ops skill to add a new node with the ID 'start' and label 'Begin' to the canvas.

Frequently Asked Questions about canvas-ops

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate creating and modifying visual workflow diagrams in agent-hand?

To automate workflow diagrams, use a JSON-based command interface to programmatically add, update, or remove nodes and edges within the agent-hand canvas. This enables dynamic diagram generation without manual editing.

What is the mechanism for programmatic canvas control in the agent-hand environment?

The mechanism for programmatic canvas control is a JSON-based command interface. It allows agents to execute operations like adding nodes, querying canvas state, and triggering automatic layouts within the agent-hand workflow editor.

Can I query the current canvas state and retrieve information about existing nodes and edges?

Yes, you can query the current canvas state to retrieve information about existing nodes and edges. The canvas operations support querying the overall state of the workflow diagram to inspect current elements and their configurations.

How do I add a new node with a specific ID and label to the canvas?

To add a new node with a specific ID and label to the canvas, issue an add operation through the JSON-based command interface. You specify the desired node ID, such as 'start', and label, such as 'Begin', in the command payload.

Does the canvas workflow editor support automatic layouts for generated diagrams?

Yes, the canvas workflow editor supports triggering automatic layouts. After programmatically adding or updating nodes and edges, you can trigger an automatic layout to visually organize the workflow diagram.

Can I dynamically generate a visual representation of a complex process triggered by an external event?

Yes, you can dynamically generate a visual representation of a complex process triggered by an external event. An agent can automatically add nodes for each process step and edges to show dependencies, creating the full visual workflow.