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

SKILL

deepgram-automation

Name: deepgram-automation
Author: Composio

Automate Deepgram tasks and connect speech workflows through Rube MCP.

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 a prompt-style guide for using Rube MCP/Composio rather than standalone executable code, and the material does not declare local code execution, file access, or direct secret injection. The main consideration is that it steers usage toward a remote MCP service and external Deepgram connection management, so the overall posture is caution rather than high risk.

CredentialsCaution

The material says the skill itself requires no local API key, but it requires activating a Deepgram connection via `RUBE_MANAGE_CONNECTIONS` and completing an external auth link, which implies third-party account authorization/tokens are involved. Secrets are not exposed in the skill install fields, but there is a normal credential usage surface through Rube/Composio-managed connections.

Network egressCaution

The instructions require adding the remote MCP endpoint `https://rube.app/mcp` and performing operations through Composio/Deepgram-related services; therefore user requests and task-related data are likely sent to those external services. The endpoint is explicitly declared in the material, so this is expected networked behavior rather than a hidden egress path, but it is not purely local.

Code executionLow risk

Based on the provided material, this is a prompt/workflow description with no visible local install script, shell command, dependency execution, or requirement to start processes on the host. Its core function is to invoke existing MCP tool interfaces rather than directly execute code on the user's system.

Data accessLow risk

The material does not declare reading/writing local files, databases, or system resources, nor does it request host permissions beyond the Deepgram automation scenario. The visible data access is mainly limited to handling content submitted into the remote workflow, with no clear sign of excessive local authorization.

Supply chainLow risk

The source is an open GitHub repository with very high community adoption (64.7k stars), both of which are strong risk-reducing signals. Although the license is not stated and maintenance status is unknown, and the skill depends on the external Rube/Composio ecosystem, overall auditability is still reasonably good and no major supply-chain red flags are evident.

Recommendations

Use it only if you trust the Rube/Composio and Deepgram data-processing chain, and review their privacy and authorization details.
Use least-privilege accounts when connecting Deepgram, and regularly review or revoke connections that are no longer needed.
Before sending audio, transcripts, or metadata, confirm whether they contain sensitive content and whether third-party transfer is acceptable.
Verify `rube.app`, the Composio toolkit documentation, and repository maintenance status, and avoid untrusted mirrors or variants.

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

// download

Download SKILL.mdInstall manifest ↗

// docs

Deepgram Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/deepgram

Prerequisites

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

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["deepgram"]
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 Deepgram-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `deepgram`
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 BigML tasks and machine learning workflows through Rube MCP.

ComposioGet→

$ loading_