$ ~/registry/skill/composiohq-composio-skills-retellai-automation

SKILL

retellai-automation

Name: retellai-automation
Author: Composio

Automate RetellAI tasks and workflows through Rube MCP with up-to-date schemas

Stars

★ 67,763

Source

GitHub

Updated

2026-07-15

// securityCaution

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

Summary

This skill appears to be primarily prompt/instruction content for operating Rube MCP/Composio, and is low risk overall due to being open source and widely adopted. The main caveat is that its real security posture depends on the external MCP service and Retellai connection, where data egress and authorization boundaries are determined outside the skill text itself.

CredentialsCaution

The material says the skill itself requires no keys, but the README explicitly requires establishing a Retellai connection via `RUBE_MANAGE_CONNECTIONS` and following an auth link if the connection is not active. So the skill does not directly collect credentials, but it does initiate external account authorization; credential handling is effectively delegated to Rube MCP/Retellai and should be reviewed for scope and token management.

Network egressCaution

The README points to the external MCP endpoint `https://rube.app/mcp` and performs Retellai operations through Composio/Rube remote tool discovery, connection management, and tool execution. This means task-related inputs, session IDs, tool arguments, and possibly business data may transit through external services; however, the material does not show a concrete red flag such as exfiltration to unrelated or suspicious endpoints.

Code executionLow risk

Based on the provided material, the skill itself is an instruction/prompt template and does not include local scripts, install commands, or direct requests to execute code on the host. It references calling existing MCP tools rather than the skill itself obtaining additional system execution privileges.

Data accessCaution

The skill text does not declare direct read/write access to local files or local data, but its workflow uses Rube MCP to discover tools, manage connections, and execute Retellai-related operations, so the real data access scope depends on external tool schemas and the Retellai account authorization. The instruction to 'always search tools first' indicates dynamically discovered capabilities, so exposed data permissions should be reviewed before use.

Supply chainLow risk

The source is an open-source GitHub repository with very high community adoption (64.7k stars), which are strong risk-reducing signals. The material appears to be a skill description from an awesome-style repository rather than a standalone closed-source binary; while license and maintenance status are not clearly stated, the supply-chain risk remains low in the absence of other red flags.

Recommendations

Before connecting to `https://rube.app/mcp`, verify the MCP operator, privacy policy, log retention, and data-handling practices.
Apply least privilege to the Retellai connection and review the authorization scopes returned by `RUBE_MANAGE_CONNECTIONS` to avoid unnecessary access.
Before running any `RUBE_MULTI_EXECUTE_TOOL`, inspect the actual capabilities and parameters returned by `RUBE_SEARCH_TOOLS`/schema so dynamically discovered tools do not access more data than expected.
If sensitive business data is involved, test in an isolated environment first and document the data flows between the external MCP service and Retellai.

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

// download

Download SKILL.mdInstall manifest ↗

// docs

Retellai Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/retellai

Prerequisites

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

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["retellai"]
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 Retellai-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `retellai`
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 Chatfai tasks via Rube MCP with schema lookup first.

ComposioGet→

$ loading_