How do I ensure I'm using current tool schemas?

Always call RUBE_SEARCH_TOOLS before selecting a tool slug; it returns slugs and input schemas.

What if the connection isn't ACTIVE?

Use RUBE_MANAGE_CONNECTIONS to check status and complete authentication via the provided link, then verify ACTIVE before executing tools.

Do I need to include memory in multi-tool calls?

Yes, memory must be included in RUBE_MULTI_EXECUTE_TOOL calls, even if empty.

cal-automation

Scanned

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

Files (1)

SKILL.md

2.8 KB

Cal Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/cal

Prerequisites

Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
Active Cal connection via RUBE_MANAGE_CONNECTIONS with toolkit cal
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 cal
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: "Cal 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 Cal task"}]
session: {id: "existing_session_id"}

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["cal"]
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 Cal-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `cal`
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/cal-automation/SKILL.mdView on GitHub

Overview

Automate Cal operations through Composio's Cal toolkit via Rube MCP. This skill emphasizes discovering current tool schemas before execution and maintaining an active Cal connection to run structured workflows.

How This Skill Works

First ensure Rube MCP is connected and RUBE_SEARCH_TOOLS is available. Then discover tools with RUBE_SEARCH_TOOLS for Cal use cases, verify the connection is ACTIVE with RUBE_MANAGE_CONNECTIONS, and finally execute the chosen tool via RUBE_MULTI_EXECUTE_TOOL using the discovered slug, proper arguments, memory payload, and the current session_id.

When to Use It

When you need to automate recurring Cal tasks and want to use the latest tool schemas
When tool schemas change frequently and you must fetch current tool slugs before running
When integrating Cal operations into a larger Composio workflow
When you need to verify the Cal connection is ACTIVE before executing workflows
When performing multi-step Cal workflows that require reusing a session ID

Quick Start

Step 1: Add the Rube MCP server as an MCP source in your client config and verify RUBE_SEARCH_TOOLS responds
Step 2: Call RUBE_MANAGE_CONNECTIONS with toolkit cal and ensure the connection status is ACTIVE
Step 3: Use RUBE_SEARCH_TOOLS to discover Cal tools, then run RUBE_MULTI_EXECUTE_TOOL with the chosen tool slug, proper arguments, memory, and the session_id

Best Practices

Always call RUBE_SEARCH_TOOLS first to fetch current schemas and tool slugs
Check that RUBE_MANAGE_CONNECTIONS shows ACTIVE before executing tools
Use exact field names and types from the search results; avoid hardcoding slugs
Include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty
Reuse session IDs within a workflow; generate new ones only for new workflows and watch for pagination tokens

Example Use Cases

Discover a Create Event tool slug from the Cal use case and execute it to add a calendar event with required fields
Run a batch update tool to change statuses of multiple events across calendars
Fetch a daily summary of upcoming events by executing a summary tool discovered via RUBE_SEARCH_TOOLS
Validate Cal connectivity by checking ACTIVE status before running a multi-step workflow
Chain several Cal tasks in one workflow by reusing the same session_id and sequentially calling discovered tools

Frequently Asked Questions

Add this skill to your agents