What prerequisites are needed?

Rube MCP must be connected with RUBE_SEARCH_TOOLS; a Sendspark connection via RUBE_MANAGE_CONNECTIONS for toolkit 'sendspark' is required; always search tools first to get current schemas.

Why should I always search tools first?

Tool schemas change over time; discovering tools ensures you use valid slugs and arguments.

How do I execute a tool and what is the memory parameter?

Use RUBE_MULTI_EXECUTE_TOOL with the discovered tool_slug, supply arguments per the input schema, include memory: {} even if empty, and pass the session_id.

sendspark-automation

Scanned

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

Files (1)

SKILL.md

2.9 KB

Sendspark Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/sendspark

Prerequisites

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

Step 2: Check Connection

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

Overview

Automates Sendspark tasks using Composio's Rube MCP toolkit. It discovers current tool schemas first to ensure compatibility, then connects to Sendspark and executes the chosen tool slug. This approach reduces manual setup and adapts to schema changes for scalable campaigns.

How This Skill Works

Start by discovering available Sendspark tools with RUBE_SEARCH_TOOLS to obtain current input schemas. Then verify or establish a Sendspark connection with RUBE_MANAGE_CONNECTIONS and ensure the status is ACTIVE. Finally, execute a tool via RUBE_MULTI_EXECUTE_TOOL using the discovered tool_slug and memory payload, reusing a session when appropriate.

When to Use It

When you need to automate batch Sendspark tasks at scale
When integrating Sendspark with a CRM or marketing workflow
When tool schemas change and you must re-discover available tools first
When performing bulk operations with RUBE_REMOTE_WORKBENCH or run_composio_tool
When you want to reuse a session across a multi-step Sendspark workflow

Quick Start

Step 1: Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed.
Step 2: Verify RUBE_SEARCH_TOOLS returns Sendspark tool schemas for your use case.
Step 3: Manage the Sendspark connection and execute a tool with RUBE_MULTI_EXECUTE_TOOL using the discovered slug and memory payload, reusing a session_id if available.

Best Practices

Always call RUBE_SEARCH_TOOLS before executing any workflow to get current schemas
Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE before running tools
Use exact field names and types from the tool schemas
Include memory in every RUBE_MULTI_EXECUTE_TOOL call, even if empty
Reuse session IDs within a workflow and regenerate for new workflows, avoid hard-coding slugs

Example Use Cases

Auto-send a personalized Sendspark video when a new lead enters a CRM using a discovered tool slug and session
Run a webinar follow-up sequence by executing a Sendspark tool with lead-specific arguments
Perform bulk sends by listing tools and using RUBE_REMOTE_WORKBENCH to run multiple tool slugs
Refresh tool schemas after Sendspark API updates and re-discover tools before running
Reuse a single session across a multi-step Sendspark workflow to improve reliability

Frequently Asked Questions

Add this skill to your agents