Do I need API keys to use this skill?

No API keys are required — add the Rube MCP endpoint (e.g., https://rube.app/mcp) in your client configuration.

What if a tool's schema changes?

Always use RUBE_SEARCH_TOOLS to fetch current schemas; do not hardcode slugs or arguments.

Is the memory parameter required?

Yes. Include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty (memory: {}), to maintain state and context.

canvas-automation

Scanned

npx machina-cli add skill ComposioHQ/awesome-claude-skills/canvas-automation --openclaw

Files (1)

SKILL.md

2.8 KB

Canvas Automation via Rube MCP

Automate Canvas operations through Composio's Canvas toolkit via Rube MCP.

Toolkit docs: composio.dev/toolkits/canvas

Prerequisites

Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
Active Canvas connection via RUBE_MANAGE_CONNECTIONS with toolkit canvas
Always call RUBE_SEARCH_TOOLS first to get current tool schemas

Setup

Get Rube MCP: Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.

Verify Rube MCP is available by confirming RUBE_SEARCH_TOOLS responds
Call RUBE_MANAGE_CONNECTIONS with toolkit canvas
If connection is not ACTIVE, follow the returned auth link to complete setup
Confirm connection status shows ACTIVE before running any workflows

Tool Discovery

Always discover available tools before executing workflows:

RUBE_SEARCH_TOOLS
queries: [{use_case: "Canvas operations", known_fields: ""}]
session: {generate_id: true}

This returns available tool slugs, input schemas, recommended execution plans, and known pitfalls.

Core Workflow Pattern

Step 1: Discover Available Tools

RUBE_SEARCH_TOOLS
queries: [{use_case: "your specific Canvas task"}]
session: {id: "existing_session_id"}

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["canvas"]
session_id: "your_session_id"

Step 3: Execute Tools

RUBE_MULTI_EXECUTE_TOOL
tools: [{
  tool_slug: "TOOL_SLUG_FROM_SEARCH",
  arguments: {/* schema-compliant args from search results */}
}]
memory: {}
session_id: "your_session_id"

Known Pitfalls

Always search first: Tool schemas change. Never hardcode tool slugs or arguments without calling RUBE_SEARCH_TOOLS
Check connection: Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE status before executing tools
Schema compliance: Use exact field names and types from the search results
Memory parameter: Always include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({})
Session reuse: Reuse session IDs within a workflow. Generate new ones for new workflows
Pagination: Check responses for pagination tokens and continue fetching until complete

Quick Reference

Operation	Approach
Find tools	`RUBE_SEARCH_TOOLS` with Canvas-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `canvas`
Execute	`RUBE_MULTI_EXECUTE_TOOL` with discovered tool slugs
Bulk ops	`RUBE_REMOTE_WORKBENCH` with `run_composio_tool()`
Full schema	`RUBE_GET_TOOL_SCHEMAS` for tools with `schemaRef`

Powered by Composio

Source

git clone https://github.com/ComposioHQ/awesome-claude-skills/blob/master/composio-skills/canvas-automation/SKILL.mdView on GitHub

Overview

Automate Canvas operations using Composio's Canvas toolkit via Rube MCP. It emphasizes discovering current tool schemas before execution and ensuring an active connection. Follow the core workflow: discover tools, verify the connection, and then execute the chosen tool.

How This Skill Works

The process starts by calling RUBE_SEARCH_TOOLS to fetch tool slugs and input schemas for a Canvas use case. Next, RUBE_MANAGE_CONNECTIONS validates an ACTIVE connection for the canvas toolkit. Finally, RUBE_MULTI_EXECUTE_TOOL runs the selected tool with memory and the session context.

When to Use It

You need to automate a specific Canvas operation after confirming the available tools and schemas.
You want to verify that the Canvas connection is ACTIVE before executing any workflow.
You must execute a tool with arguments derived from current schemas rather than hardcoding values.
You are performing multiple tools within a single session and want to reuse the session ID.
Tool results are paginated and you need to fetch all pages before proceeding.

Quick Start

Step 1: RUBE_SEARCH_TOOLS queries: [{use_case: "Canvas operations"}] to get available tools and schemas.
Step 2: RUBE_MANAGE_CONNECTIONS toolkits: ["canvas"] and confirm session is ACTIVE.
Step 3: RUBE_MULTI_EXECUTE_TOOL with the discovered tool_slug and memory: {} to run the task.

Best Practices

Always call RUBE_SEARCH_TOOLS first to obtain current tool schemas; never hardcode tool slugs or arguments.
Verify that RUBE_MANAGE_CONNECTIONS shows ACTIVE status before executing tools.
Use exact field names and types from the tool schemas returned by search results.
Include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty (memory: {}).
Reuse session IDs within a workflow and handle pagination tokens until complete.

Example Use Cases

Automate creating a Canvas assignment by discovering the appropriate tool via RUBE_SEARCH_TOOLS and executing it with the required arguments.
Update course metadata in Canvas by fetching the correct tool schema and executing the tool with live schema-compliant inputs.
Perform bulk Canvas operations using RUBE_REMOTE_WORKBENCH's run_composio_tool() for multiple tasks in one flow.
Reconnect to the Canvas toolkit when a connection drops, validate ACTIVE status, and resume workflow execution.
Handle paginated tool results during discovery and iterate through pages to complete a multi-step Canvas task.

Frequently Asked Questions

Add this skill to your agents