What is curated-automation?

Curated-automation automates Curated tasks via the Rube MCP, coordinating discovery, connection management, and tool execution using the curated toolkit.

Do I need an active connection to Curated?

Yes. Ensure RUBE_MANAGE_CONNECTIONS shows ACTIVE for the curated toolkit before executing any tools.

Should I always call RUBE_SEARCH_TOOLS first?

Yes. RUBE_SEARCH_TOOLS fetches current tool schemas and slugs, preventing hardcoded, outdated calls.

curated-automation

Scanned

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

Files (1)

SKILL.md

2.9 KB

Curated Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/curated

Prerequisites

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

Step 2: Check Connection

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

Overview

Automate Curated operations through Composio's Curated toolkit using Rube MCP. This skill streamlines discovery, connection checks, and execution of curated tools while ensuring you use current schemas. Always search tools first to fetch up-to-date tool slugs and input schemas.

How This Skill Works

The workflow starts by discovering available curated tools with RUBE_SEARCH_TOOLS, then verifies the Curated connection via RUBE_MANAGE_CONNECTIONS, and finally executes the chosen tool with RUBE_MULTI_EXECUTE_TOOL. You must include memory in every execute call and ensure the session_id is reused appropriately across the workflow.

When to Use It

When automating a Curated operation and tool schemas may change, always call RUBE_SEARCH_TOOLS first.
When setting up a new Curated workflow, verify that the RUBE_MANAGE_CONNECTIONS status is ACTIVE before execution.
When selecting tools, rely on discovered slugs and exact field names from search results to ensure schema compliance.
When reusing a workflow, reuse session IDs within the same run to maintain context.
When handling multiple results, account for pagination and fetch until complete.

Quick Start

Step 1: Add https://rube.app/mcp as an MCP server in your client configuration.
Step 2: Run RUBE_SEARCH_TOOLS to verify availability and fetch current tool slugs and input schemas.
Step 3: Call RUBE_MANAGE_CONNECTIONS with toolkits: ["curated"] and then use RUBE_MULTI_EXECUTE_TOOL with a discovered tool_slug, proper arguments, memory: {}, and a session_id.

Best Practices

Always call RUBE_SEARCH_TOOLS before executing any curated tool to get current tool slugs and input schemas.
Check RUBE_MANAGE_CONNECTIONS reports ACTIVE status for the curated toolkit before running tools.
Use the exact field names and types from the search results; avoid hardcoding arguments.
Include a memory object in every RUBE_MULTI_EXECUTE_TOOL call, even if empty ({}).
Reuse session IDs within a single workflow and generate new ones only for separate workflows; watch for pagination tokens.

Example Use Cases

Automate a weekly curated data pull by discovering tools, confirming the Active curated connection, then executing the appropriate tool with the latest schema.
Orchestrate a multi-step curated task by discovering the necessary tool slugs, validating the connection, and issuing RUBE_MULTI_EXECUTE_TOOL with the discovered arguments.
Perform bulk curated operations via RUBE_REMOTE_WORKBENCH using run_composio_tool() for batch processing.
Adapt to schema changes by re-fetching tool schemas with RUBE_SEARCH_TOOLS before each execution to avoid broken calls.
Maintain session continuity across a sequence of curated steps while handling possible pagination in tool discovery results.

Frequently Asked Questions

Add this skill to your agents