Do I need API keys to use this skill?

No API keys are required. You just need to add https://rube.app/mcp as an MCP server in your client configuration.

What if tool slugs or schemas change?

Always call RUBE_SEARCH_TOOLS to fetch current slugs and schemas; do not hardcode tool slugs or arguments.

How do I know execution succeeded?

Verify the Splitwise connection status is ACTIVE via RUBE_MANAGE_CONNECTIONS before executing tools and ensure the RUBE_MULTI_EXECUTE_TOOL call completes without errors.

splitwise-automation

Scanned

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

Files (1)

SKILL.md

2.9 KB

Splitwise Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/splitwise

Prerequisites

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

Step 2: Check Connection

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

Overview

Automate Splitwise operations through Composio's Splitwise toolkit via Rube MCP. This skill emphasizes always discovering current tool schemas before execution to adapt to changes and keep workflows reliable.

How This Skill Works

The workflow starts by calling RUBE_SEARCH_TOOLS to fetch available Splitwise tools and their input schemas. It then checks the Splitwise connection with RUBE_MANAGE_CONNECTIONS and, once ACTIVE, executes a discovered tool using RUBE_MULTI_EXECUTE_TOOL with the required arguments and a memory payload (memory: {}).

When to Use It

When you want to automate recurring Splitwise tasks without hardcoding tool slugs or schemas.
When you must verify that the Splitwise connection is ACTIVE before running workflows.
When tool schemas may change and you need to fetch fresh input fields via RUBE_SEARCH_TOOLS.
When performing a sequence of steps (discover → connect → execute) within a single workflow.
When handling batch or bulk Splitwise operations that require multiple tool executions.

Quick Start

Step 1: Ensure Rube MCP is connected and that RUBE_SEARCH_TOOLS can respond for Splitwise.
Step 2: Run RUBE_SEARCH_TOOLS with a Splitwise use_case to discover available tools and their input schemas.
Step 3: Run RUBE_MULTI_EXECUTE_TOOL with a discovered tool_slug and a memory payload, ensuring memory: {} is included.

Best Practices

Always call RUBE_SEARCH_TOOLS before running or updating workflows to get current tool slugs and schemas.
Check the connection status with RUBE_MANAGE_CONNECTIONS to ensure it is ACTIVE before executing tools.
Use exact field names and types as reported by the tool schemas from the search results.
Always include memory: {} in RUBE_MULTI_EXECUTE_TOOL calls, even if empty.
Reuse session IDs within a workflow and avoid hardcoding tool slugs across runs.

Example Use Cases

Automate a recurring group expense and split it evenly among participants by discovering the appropriate Splitwise tool and executing it.
Add an expense after a group dinner by discovering the corresponding tool, ensuring an ACTIVE connection, and running the tool with proper arguments.
Bulk-upload multiple expenses from a CSV by mapping each row to the discovered tool schemas and executing them in sequence.
Onboard a new group by establishing a Splitwise connection and creating initial balances automatically.
Run a monthly reconciliation to summarize outstanding debts and update Splitwise accordingly.

Frequently Asked Questions

Add this skill to your agents