How do I start automating Conveyor tasks with this skill?

Add the MCP server (https://rube.app/mcp), verify RUBE_SEARCH_TOOLS responds, connect to the conveyor toolkit with RUBE_MANAGE_CONNECTIONS, then discover tools and execute them with RUBE_MULTI_EXECUTE_TOOL using the discovered slug and schema.

What if tool schemas change?

Always call RUBE_SEARCH_TOOLS to fetch current slugs and schemas; avoid hardcoding slugs or arguments and update your workflow accordingly.

Is memory required for executions?

Yes. Always include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({}), to support stateful workflows.

conveyor-automation

Scanned

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

Files (1)

SKILL.md

2.9 KB

Conveyor Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/conveyor

Prerequisites

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

Step 2: Check Connection

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

Overview

Automate Conveyor operations using Composio's Rube MCP toolkit. This skill guides tool discovery, establishes a Conveyor connection, and executes schema-compliant tool calls to streamline workflows.

How This Skill Works

Prereqs include a live RUBE_SEARCH_TOOLS feed and an active Conveyor connection via RUBE_MANAGE_CONNECTIONS using the conveyor toolkit. Always start by fetching current tool schemas with RUBE_SEARCH_TOOLS, then connect, and finally execute tools with RUBE_MULTI_EXECUTE_TOOL using the discovered tool slug and exact schema fields. You can also inspect full schemas with RUBE_GET_TOOL_SCHEMAS.

When to Use It

When you need up-to-date Conveyor tool schemas before automating a task
When establishing a new Conveyor integration and validating ACTIVE connections
When running a single Conveyor operation using a discovered tool slug
When performing multiple Conveyor tasks in a single workflow via RUBE_MULTI_EXECUTE_TOOL
When debugging or auditing tool discovery and handling pagination

Quick Start

Step 1: Get Rube MCP set up by adding https://rube.app/mcp as an MCP server in your client and verify RUBE_SEARCH_TOOLS responds.
Step 2: Establish the Conveyor connection with RUBE_MANAGE_CONNECTIONS using toolkits: ["conveyor"] and ensure the status is ACTIVE.
Step 3: Discover tools with RUBE_SEARCH_TOOLS, pick a tool_slug from results, then run RUBE_MULTI_EXECUTE_TOOL with that slug, the provided arguments, memory: {}, and the session_id from the discovery.

Best Practices

Always call RUBE_SEARCH_TOOLS before executing any workflow to get current tool slugs and schemas
Verify RUBE_MANAGE_CONNECTIONS reports ACTIVE before running tools
Use the exact field names and types from the search results rather than guessing
Include memory in every RUBE_MULTI_EXECUTE_TOOL call, even if empty
Reuse session IDs within a workflow and fetch subsequent pages if responses are paginated

Example Use Cases

Automate a belt sorter operation by discovering the available Conveyor tool, then executing it with arguments from the search result
Set up a recurring Conveyor task by establishing a persistent Rube MCP connection and reusing a session
Debug a schema change by re-running RUBE_SEARCH_TOOLS to fetch updated tool_slugs before execution
Execute multiple Conveyor tasks in sequence using RUBE_MULTI_EXECUTE_TOOL with a single session
Bulk Conveyor ops via RUBE_REMOTE_WORKBENCH and run_composio_tool to process a batch

Frequently Asked Questions

Add this skill to your agents