Do I need API keys to use kaggle-automation?

No — you add the MCP endpoint (https://rube.app/mcp) as described; no API keys are required.

Why must I call RUBE_SEARCH_TOOLS first?

Tool schemas can change; you must fetch current slugs and input schemas before execution to avoid errors.

How do I ensure the session remains valid across steps?

Reuse an existing session_id within a workflow and generate a new one only for separate workflows.

kaggle-automation

Scanned

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

Files (1)

SKILL.md

2.8 KB

Kaggle Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/kaggle

Prerequisites

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

Step 2: Check Connection

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

Overview

Automate Kaggle operations through Composio's Kaggle toolkit via Rube MCP. Always search for current tool schemas with RUBE_SEARCH_TOOLS before running workflows to avoid hardcoding tool slugs and brittle integrations.

How This Skill Works

Discover available Kaggle tools with RUBE_SEARCH_TOOLS to obtain slugs and input schemas. Verify the Kaggle connection with RUBE_MANAGE_CONNECTIONS and ensure it is ACTIVE. Execute the chosen tool using RUBE_MULTI_EXECUTE_TOOL, supplying exact arguments from the discovered schema and including a memory object (even if empty).

When to Use It

Starting a new Kaggle project and wanting end-to-end automation of tasks
When tool schemas may have changed and you need current slugs and inputs
Before running any workflow, to confirm the Kaggle connection is ACTIVE
Batching multiple Kaggle tool executions in a single session
Reusing a session ID across related Kaggle tasks to maintain context

Quick Start

Step 1: Run RUBE_SEARCH_TOOLS to discover Kaggle tools and schemas
Step 2: Run RUBE_MANAGE_CONNECTIONS for the 'kaggle' toolkit and ensure ACTIVE
Step 3: Use RUBE_MULTI_EXECUTE_TOOL with a discovered tool_slug and memory: {}

Best Practices

Always call RUBE_SEARCH_TOOLS first to fetch current tool slugs and input schemas
Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE before executing tools
Use exact field names and types from the search results; do not hardcode
Include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({})
Reuse session IDs within a workflow and fetch new IDs only for new workflows; handle pagination tokens if present

Example Use Cases

Discover Kaggle tool slugs for a submission workflow and plan execution
Connect to the Kaggle toolkit and confirm the ACTIVE status before running tasks
Execute a Kaggle tool using arguments sourced from RUBE_SEARCH_TOOLS results
Perform bulk operations via RUBE_REMOTE_WORKBENCH to run multiple tools in one batch
Fetch full tool schemas with RUBE_GET_TOOL_SCHEMAS to review required inputs

Frequently Asked Questions

Add this skill to your agents