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

toneden-automation skill

safe

/toneden-automation

This skill automates Toneden tasks via Composio MCP, constantly discovering tool schemas first to ensure up-to-date execution.

npx playbooks add skill composiohq/awesome-claude-skills --skill toneden-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: toneden-automation
description: "Automate Toneden tasks via Rube MCP (Composio). Always search tools first for current schemas."
requires:
  mcp: [rube]
---

# Toneden Automation via Rube MCP

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

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

## Prerequisites

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

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["toneden"]
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 Toneden-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `toneden` |
| 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 Toneden tasks through the Rube MCP (Composio) integration, providing a repeatable pattern to discover, connect, and run Toneden toolkit tools. It enforces safety checks like tool discovery and connection validation to avoid schema and auth errors. Use it to run single or multi-step Toneden workflows programmatically from an agent environment.

How this skill works

The skill first calls RUBE_SEARCH_TOOLS to retrieve current tool slugs, input schemas, and recommended execution plans. It then verifies an active Toneden connection via RUBE_MANAGE_CONNECTIONS and executes operations using RUBE_MULTI_EXECUTE_TOOL (including memory and session handling). For bulk or advanced tasks, it leverages RUBE_REMOTE_WORKBENCH or RUBE_GET_TOOL_SCHEMAS when full schemas are required.

When to use it

Automate Toneden campaign, audience, or track operations from an agent
Run multi-step Toneden workflows that require tool discovery and orchestration
Integrate Toneden actions into larger automation pipelines that need schema-safe calls
Perform bulk operations or remote workbench runs for high-volume Toneden tasks

Best practices

Always call RUBE_SEARCH_TOOLS first — tool slugs and schemas change frequently
Confirm Toneden connection status with RUBE_MANAGE_CONNECTIONS and ensure it is ACTIVE
Pass the exact fields and types from returned schemas; don’t hardcode arguments
Always include a memory parameter (can be empty {}) when calling RUBE_MULTI_EXECUTE_TOOL
Reuse session_id within a workflow; generate new session IDs for new workflows
Handle pagination in responses and follow pagination tokens until completion

Example use cases

Discover available Toneden actions and execute a campaign update with the returned schema-compliant args
Connect and authenticate a Toneden toolkit, then run a multi-step audience import workflow
Perform bulk uploads or batch edits using RUBE_REMOTE_WORKBENCH run_composio_tool() calls
Fetch full tool schemas with RUBE_GET_TOOL_SCHEMAS before building UI or validation logic for a Toneden integration

FAQ

What is the first API call I should make?

Always run RUBE_SEARCH_TOOLS to discover current tool slugs, input schemas, and recommended plans before any other calls.

What if the Toneden connection is not ACTIVE?

Call RUBE_MANAGE_CONNECTIONS to get the connection status and follow the returned auth link to complete setup; confirm ACTIVE before executing tools.