How do I ensure current tool schemas?

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

What should I check before executing a tool?

Verify the Datarobot connection is ACTIVE via RUBE_MANAGE_CONNECTIONS and ensure the execution payload includes memory.

Is memory required in the execute call?

Yes; always include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty.

datarobot-automation

Scanned

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

Files (1)

SKILL.md

2.9 KB

Datarobot Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/datarobot

Prerequisites

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

Step 2: Check Connection

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

Overview

This skill automates Datarobot operations through Composio's Datarobot toolkit using Rube MCP. It emphasizes discovering up-to-date tool schemas before execution, verifying an active connection, and following a repeatable workflow from discovery to execution.

How This Skill Works

First, discover available Datarobot tools with RUBE_SEARCH_TOOLS to obtain current tool slugs and required input schemas. Then verify an ACTIVE connection with RUBE_MANAGE_CONNECTIONS and the datarobot toolkit, and finally execute the chosen tool via RUBE_MULTI_EXECUTE_TOOL, including a memory payload. Always follow the documented step pattern (discover → check → execute) to handle schema changes and session management.

When to Use It

When you need to perform a Datarobot task but tool schemas may change, so always search first.
When you must confirm an ACTIVE Datarobot connection before executing workflows.
When starting a full Datarobot workflow: discovery, connection check, and tool execution.
When you want to reuse a session ID across multiple steps in a workflow.
When tool results are paginated and you need to fetch all tool options.

Quick Start

Step 1: Ensure Rube MCP is connected and RUBE_SEARCH_TOOLS responds.
Step 2: Call RUBE_MANAGE_CONNECTIONS with toolkit datarobot and authenticate if needed; confirm ACTIVE.
Step 3: Use RUBE_SEARCH_TOOLS to discover tools, then execute a chosen tool with RUBE_MULTI_EXECUTE_TOOL, including memory.

Best Practices

Always call RUBE_SEARCH_TOOLS first to fetch current schemas.
Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE before executing tools.
Use the exact field names and types from search results; avoid hardcoding.
Include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty.
Reuse session IDs within a workflow and handle pagination if present.

Example Use Cases

Discover Datarobot tool options, select a deployment tool slug, and run it with the required arguments to deploy a model.
Establish an ACTIVE Datarobot connection, then perform a prediction workflow using a discovered tool slug.
List all Datarobot tools using a use_case query, pick a suitable tool slug, and execute with proper schema-compliant arguments.
Chain steps in a single session: discover tools, verify connection, then execute multiple tools sequentially.
If tool slugs change due to schema updates, re-run RUBE_SEARCH_TOOLS to obtain new slugs and re-execute accordingly.

Frequently Asked Questions

Add this skill to your agents