How do I keep tool schemas current?

Always run RUBE_SEARCH_TOOLS before executing; do not hardcode tool slugs or arguments; schemas are returned with input fields.

What if the connection isn't ACTIVE?

Use RUBE_MANAGE_CONNECTIONS with toolkit tomba, follow the auth flow, and re-check ACTIVE before running workflows.

Is memory required in tool executions?

Yes. Include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if it is an empty object {}.

tomba-automation

Scanned

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

Files (1)

SKILL.md

2.8 KB

Tomba Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/tomba

Prerequisites

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

Step 2: Check Connection

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

Overview

This skill automates Tomba operations using Composio's Tomba toolkit through Rube MCP. It emphasizes always querying current tool schemas before workflows and requires an active Rube MCP connection plus an active Tomba connection. Use it to orchestrate tool discovery, connection checks, and multi-tool execution in a single, repeatable flow.

How This Skill Works

You first call RUBE_SEARCH_TOOLS to fetch available Tomba tools and their input schemas, then verify the Tomba connection with RUBE_MANAGE_CONNECTIONS. When ready, execute tools with RUBE_MULTI_EXECUTE_TOOL using the discovered tool_slug and schema-aligned arguments, always including memory. Throughout the session you should reuse session_id and monitor ACTIVE status before runs, and handle pagination as needed.

When to Use It

You need to automate a Tomba task flow within an Rube MCP workflow.
You must fetch the latest tool schemas before executing to avoid hardcoded slugs.
You want to run a sequence of Tomba tools in a single session with proper memory handling.
You need to verify the Tomba connection is ACTIVE before tool execution.
You are handling large tool responses and need to process pagination tokens during discovery.

Quick Start

Step 1: Add https://rube.app/mcp as an MCP server in your client configuration.
Step 2: Verify RUBE_SEARCH_TOOLS responds and connect to the tomba toolkit with RUBE_MANAGE_CONNECTIONS.
Step 3: Discover tools with RUBE_SEARCH_TOOLS, check the connection status, and execute a tool with RUBE_MULTI_EXECUTE_TOOL using a discovered slug and schema-based arguments; remember to include memory and a session_id.

Best Practices

Always call RUBE_SEARCH_TOOLS before any execution.
Check that RUBE_MANAGE_CONNECTIONS shows ACTIVE before running tools.
Use exact field names and types from the search results; do not guess.
Include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({}).
Reuse session IDs within a workflow and handle pagination for complete results.

Example Use Cases

Automate a lead enrichment flow by discovering Tomba tools, then executing a sequence of enrichment steps in one session.
Validate tool schemas before deployment to ensure compatibility with the current Tomba integration.
Run multiple Tomba tasks across a campaign while reusing a single session_id for consistency.
Iteratively fetch current tool slugs and arguments to adapt to schema changes without breaking automation.
Process paginated discovery results to execute all relevant Tomba tools in a batch.

Frequently Asked Questions

Add this skill to your agents