home / skills / composiohq / awesome-claude-skills / cloudcart-automation

cloudcart-automation skill

safe

/cloudcart-automation

This skill automates Cloudcart tasks via Rube MCP, ensuring tool schemas are refreshed by searching tools first for up-to-date execution plans.

npx playbooks add skill composiohq/awesome-claude-skills --skill cloudcart-automation

Review the files below or copy the command above to add this skill to your agents.

Files (1)

SKILL.md

2.9 KB

---
name: cloudcart-automation
description: "Automate Cloudcart tasks via Rube MCP (Composio). Always search tools first for current schemas."
requires:
  mcp: [rube]
---

# Cloudcart Automation via Rube MCP

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

**Toolkit docs**: [composio.dev/toolkits/cloudcart](https://composio.dev/toolkits/cloudcart)

## Prerequisites

- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Cloudcart connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `cloudcart`
- 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.

1. Verify Rube MCP is available by confirming `RUBE_SEARCH_TOOLS` responds
2. Call `RUBE_MANAGE_CONNECTIONS` with toolkit `cloudcart`
3. If connection is not ACTIVE, follow the returned auth link to complete setup
4. Confirm connection status shows ACTIVE before running any workflows

## Tool Discovery

Always discover available tools before executing workflows:

```
RUBE_SEARCH_TOOLS
queries: [{use_case: "Cloudcart 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 Cloudcart task"}]
session: {id: "existing_session_id"}
```

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["cloudcart"]
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 Cloudcart-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `cloudcart` |
| 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](https://composio.dev)*

Overview

This skill automates Cloudcart tasks by orchestrating Composio’s Cloudcart toolkit through a Rube MCP connection. It guides tool discovery, connection checks, and multi-tool execution to run reliable Cloudcart workflows. The skill enforces runtime checks so you always use current tool schemas and an active Cloudcart connection.

How this skill works

First it queries Rube MCP with RUBE_SEARCH_TOOLS to discover available Cloudcart tool slugs and exact input schemas. It verifies or establishes a Cloudcart connection via RUBE_MANAGE_CONNECTIONS, then runs tools with RUBE_MULTI_EXECUTE_TOOL (including memory and session). It handles pagination, session reuse, and follows returned execution plans and schemaRefs for safe automation.

When to use it

Automating product, order, or catalog operations in Cloudcart
Running bulk Cloudcart updates or migrations via Composio tools
Integrating Cloudcart tasks into larger agent workflows
When tool schemas may change frequently and require discovery before use
Before any run that depends on a Cloudcart connection state

Best practices

Always call RUBE_SEARCH_TOOLS first; never hardcode tool slugs or arguments
Verify Cloudcart connection status with RUBE_MANAGE_CONNECTIONS and ensure it is ACTIVE
Supply memory (even an empty {}) in RUBE_MULTI_EXECUTE_TOOL calls
Reuse a session_id for a workflow and create a new one for distinct workflows
Respect exact field names and types from the returned schemaRef and handle pagination tokens

Example use cases

Discover and execute a Cloudcart 'create product' tool by first fetching its schema and required fields
Run a bulk price or inventory update via RUBE_MULTI_EXECUTE_TOOL using discovered tool slugs and memory
Automate order fulfillment steps by chaining multiple Cloudcart tools within the same session_id
Fetch full tool schemas with RUBE_GET_TOOL_SCHEMAS to validate inputs before a critical production operation
Use RUBE_REMOTE_WORKBENCH with run_composio_tool() for scripted bulk operations

FAQ

What must I call before executing a tool?

Always call RUBE_SEARCH_TOOLS to get current tool slugs and input schemas.

How do I know the Cloudcart connection is ready?

Use RUBE_MANAGE_CONNECTIONS for the cloudcart toolkit and confirm the returned status is ACTIVE before running tools.