home / skills / composiohq / awesome-claude-skills / convolo-ai-automation

convolo-ai-automation skill

safe

/convolo-ai-automation

This skill automates Convolo AI tasks via Rube MCP by discovering current tool schemas, validating connections, and executing tools efficiently.

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

# Convolo AI Automation via Rube MCP

Automate Convolo AI operations through Composio's Convolo AI toolkit via Rube MCP.

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

## Prerequisites

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

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["convolo_ai"]
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 Convolo AI-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `convolo_ai` |
| 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 Convolo AI operations through Composio’s Convolo AI toolkit via Rube MCP. It provides a clear pattern for discovering tools, validating connections, and executing multi-step workflows while enforcing schema compliance and session handling. Use it to reliably run Convolo tasks programmatically and at scale.

How this skill works

The skill always starts by calling RUBE_SEARCH_TOOLS to fetch up-to-date tool slugs, input schemas, and recommended plans. It then validates the Convolo AI connection via RUBE_MANAGE_CONNECTIONS and only proceeds when the connection is ACTIVE. Execution happens through RUBE_MULTI_EXECUTE_TOOL (or RUBE_REMOTE_WORKBENCH for bulk runs) using the exact fields returned by the search and including a memory object and session ID.

When to use it

Automating recurring Convolo AI workflows or pipelines
Orchestrating multi-step tasks that require up-to-date tool schemas
Running bulk operations or remote workbench jobs for Convolo AI
Building integrations where robust connection checks and schema compliance are required
Implementing session-based workflows that must persist state or reuse sessions

Best practices

Always call RUBE_SEARCH_TOOLS first; tool schemas and slugs change frequently
Verify toolkit connection with RUBE_MANAGE_CONNECTIONS and ensure status is ACTIVE before execution
Use exact field names and types returned by the search; do not hardcode arguments
Include a memory parameter (can be an empty object) in RUBE_MULTI_EXECUTE_TOOL calls
Reuse session IDs for related workflow steps; generate new sessions for distinct workflows
Check for pagination tokens and fetch all pages when search results are paginated

Example use cases

Trigger a Convolo model evaluation by discovering the appropriate execution tool and passing schema-compliant inputs
Batch-process content transformations using RUBE_REMOTE_WORKBENCH with run_composio_tool() for parallel runs
Automate dataset uploads and model fine-tuning sequences with validated connection checks and session reuse
Integrate Convolo AI operations into a CI/CD pipeline that dynamically discovers tool schemas before each run
Create an interactive agent that discovers available Convolo capabilities and executes tasks on behalf of users

FAQ

Do I need API keys to use Rube MCP?

No API keys are required; add https://rube.app/mcp as an MCP server in your client configuration and use the provided Rube MCP actions.

What if RUBE_SEARCH_TOOLS returns a different schema than I expect?

Treat the returned schema as authoritative: update your arguments to match exact field names and types, and do not execute with hardcoded payloads.