How do I ensure up-to-date tool schemas?

Always call RUBE_SEARCH_TOOLS before selecting a tool; tool slugs and input schemas come from the latest search results.

How do I verify the Carbone connection?

Use RUBE_MANAGE_CONNECTIONS with toolkit "carbone" and check that the status is ACTIVE before executing tools.

Do I need to pass memory in execute calls?

Yes. Always include a memory object in RUBE_MULTI_EXECUTE_TOOL, even if it is empty ({}).

carbone-automation

Scanned

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

Files (1)

SKILL.md

2.9 KB

Carbone Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/carbone

Prerequisites

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

Step 2: Check Connection

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

Overview

Automate Carbone operations through Composio's Carbone toolkit using Rube MCP. It guides discovery, connection management, and tool execution based on live tool schemas. Always search for current tool schemas before running any workflow to prevent failures.

How This Skill Works

Use RUBE_SEARCH_TOOLS to discover available Carbone tools and their input schemas. Then verify the Carbone connection with RUBE_MANAGE_CONNECTIONS and ensure status is ACTIVE. Finally execute the chosen tool with RUBE_MULTI_EXECUTE_TOOL, passing memory and the discovered arguments.

When to Use It

Automate a Carbone operation that requires up-to-date tool schemas by discovering tools first.
Integrate Carbone tasks into a larger Composio workflow and reuse a session_id for continuity.
Perform a safe, connection-verified run by checking that RUBE_MANAGE_CONNECTIONS shows ACTIVE before execution.
Execute multiple Carbone tools in sequence within a single workflow and manage tool slugs dynamically.
Handle schema changes and pagination by re-discovering tools before each run instead of hardcoding slugs.

Quick Start

Step 1: Add https://rube.app/mcp as an MCP server in your client configuration.
Step 2: Verify RUBE_SEARCH_TOOLS responds to confirm tool discovery and schemas.
Step 3: Call RUBE_MANAGE_CONNECTIONS with toolkits: ["carbone"] and run RUBE_MULTI_EXECUTE_TOOL using the discovered tool slug and memory.

Best Practices

Always call RUBE_SEARCH_TOOLS before selecting and running tools.
Check that RUBE_MANAGE_CONNECTIONS reports ACTIVE status before executing tools.
Use exact field names and types from the search results; avoid hardcoding.
Include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({}).
Reuse session IDs within a workflow and fetch fresh results as needed; manage pagination.

Example Use Cases

Daily Carbone report generation by discovering the appropriate tool slug and executing with a shared session.
Batch rendering of several Carbone visuals in a single workflow, reusing the same session_id.
A health-check workflow that confirms MCP connection availability and tool schemas before execution.
Carbone data export that uses a discovered tool slug from RUBE_SEARCH_TOOLS and runs with required args.
Schema-change resilient automation that re-discovers tools before each run to fetch updated slugs.

Frequently Asked Questions

Add this skill to your agents