$ ~/registry/skill/composiohq-composio-skills-rev-ai-automation

SKILL

rev-ai-automation

Name: rev-ai-automation
Author: Composio

Automate Rev AI workflows through Rube MCP for transcription and audio processing.

Stars

★ 67,763

Source

GitHub

Updated

2026-07-15

// securityCaution

Prompt only, no code
Open source
Community-trusted· 64.7k

Summary

This skill is primarily prompt-style operational guidance, with a public source and strong community adoption, so overall risk is low. However, its real-world use depends on external Rube MCP and a Rev AI connection, which introduces external authorization and data transfer that should be verified at runtime.

CredentialsCaution

The material states the skill itself does not require a local API key, but it explicitly requires establishing a rev_ai connection via RUBE_MANAGE_CONNECTIONS and completing authorization through a returned auth link. This still involves third-party account credentials or OAuth grants, creating normal credential exposure risk, and the README does not describe least-privilege scope.

Network egressCaution

The README explicitly requires adding the remote MCP endpoint https://rube.app/mcp and using Composio/Rube to call Rev AI-related tools. This means workflow inputs, session IDs, tool arguments, and potentially business data will be sent to external services. The material does not provide a detailed data-flow map, retention policy, or full list of recipients.

Code executionLow risk

Based on the objective checks, this is a prompt-only skill. The material does not describe running local scripts, spawning processes, installing dependencies, or directly invoking system commands; it mainly instructs how to use existing MCP tools rather than providing code-execution capability itself.

Data accessCaution

The skill targets Rev AI automation and performs tasks through remote tools such as RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH. While it does not claim direct local file read/write, the actual accessible data scope depends on the permissions granted to the connected Rev AI/Composio tools, and the material does not define clear boundaries.

Supply chainLow risk

The source is an open GitHub repository with high stated community trust (64.7k stars), both strong risk-reducing signals. The provided material does not show obfuscated installation steps, hidden dependencies, or suspicious injection content. The missing license declaration and unknown maintenance status are worth noting, but not enough on their own to raise this to high risk.

Recommendations

Before use, verify the real ownership of rube.app/mcp and the Rev AI authorization page, and grant only the minimum permissions required.
Do not send unnecessary sensitive audio, transcripts, or customer data in tool arguments; prefer redaction before transmission.
In organizational environments, document and review the data flows, logging retention, and deletion policies for Composio/Rube and Rev AI.
Test first in a restricted environment and confirm the available tool set and actual permission boundaries before using production data.

Audited by: gpt-5.4 · 2026-06-17

// install

Copy the install command and let the AI configure it · recommended for beginners

Please install the "rev-ai-automation" skill from askskill:
1. Download https://raw.githubusercontent.com/ComposioHQ/awesome-claude-skills/master/composio-skills/rev-ai-automation/SKILL.md
2. Save it as ~/.claude/skills/rev-ai-automation/SKILL.md
3. Reload skills and tell me it's ready

// download

Download SKILL.mdInstall manifest ↗

// docs

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

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.

Verify Rube MCP is available by confirming RUBE_SEARCH_TOOLS responds
Call RUBE_MANAGE_CONNECTIONS with toolkit rev_ai
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: "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

Automate Wit AI workflows via Rube MCP using current tool schemas first.

ComposioGet→

$ loading_