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

rev-ai-automation skill

safe

/rev-ai-automation

This skill automates Rev AI tasks via Rube MCP, ensuring tool schemas are current before execution to reduce errors.

npx playbooks add skill composiohq/awesome-claude-skills --skill rev-ai-automation

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

Files (1)

SKILL.md

2.8 KB

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

# Rev AI Automation via Rube MCP

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

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

## Prerequisites

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

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["rev_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 Rev AI-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `rev_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 Rev AI tasks through Composio’s Rev AI toolkit using the Rube MCP orchestration layer. It provides a repeatable pattern for discovering available tools, verifying connections, and executing operations while respecting live tool schemas. Follow the search-first approach to avoid schema drift and ensure reliable workflows.

How this skill works

The skill first calls RUBE_SEARCH_TOOLS to discover current tool slugs, input schemas, and recommended execution plans. It then verifies that a Rev AI connection is ACTIVE via RUBE_MANAGE_CONNECTIONS. Finally it runs one or more operations with RUBE_MULTI_EXECUTE_TOOL (or bulk via RUBE_REMOTE_WORKBENCH), always supplying memory and a session id and using schema-compliant arguments.

When to use it

Automating transcription, diarization, or caption tasks with Rev AI from an agent.
Integrating Rev AI features into larger Claude-driven workflows or pipelines.
Running bulk or repeated Rev AI operations where tool schemas may change.
Building reproducible agent tasks that require session and connection management.
Debugging or validating available Rev AI tool capabilities before execution.

Best practices

Always call RUBE_SEARCH_TOOLS first and use the returned schemas; never hardcode tool slugs or fields.
Verify Rev AI connection status with RUBE_MANAGE_CONNECTIONS and complete auth flows if not ACTIVE.
Include a memory object (even an empty {}) in RUBE_MULTI_EXECUTE_TOOL calls and reuse session IDs per workflow.
Respect field types and names exactly as returned by the search results to avoid schema validation errors.
Handle pagination tokens from search responses and fetch until the result set is complete.

Example use cases

Discover available Rev AI operations, confirm connection, then transcribe a batch of audio files using discovered tool inputs.
Run a multi-step workflow that performs speaker diarization followed by caption generation and stores results in downstream systems.
Perform bulk processing using RUBE_REMOTE_WORKBENCH and run_composio_tool() for high-throughput transcription jobs.
Validate tool schema changes by polling RUBE_GET_TOOL_SCHEMAS and adjusting agent arguments before execution.

FAQ

What is the first call I must make every run?

Always call RUBE_SEARCH_TOOLS to retrieve current tool slugs, input schemas, and recommended execution plans.

What if the Rev AI connection is not active?

Call RUBE_MANAGE_CONNECTIONS for the rev_ai toolkit, follow any returned auth link, and confirm status is ACTIVE before executing tools.