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

SKILL

gemini-automation

Name: gemini-automation
Author: Composio

Automate Gemini workflows via Rube MCP with schema-first tool discovery.

Stars

★ 67,763

Source

GitHub

Updated

2026-07-15

// securityCaution

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

Summary

Overall this appears to be a prompt-only skill built on Rube MCP, with open-source provenance and high community adoption. No credentials, fixed remote endpoint, or local code execution are indicated; the main consideration is standard MCP/Composio tool egress and data handling.

CredentialsLow risk

The material explicitly says no API keys/secrets are needed, and no additional credentials are requested; it only mentions managing a Gemini connection via RUBE_MANAGE_CONNECTIONS, with no credential-abuse red flags.

Network egressCaution

The skill uses Rube MCP/Composio to call external tools, which implies routine egress of user queries and workflow data to the declared service/tool chain; no unknown or unrelated endpoint is shown.

Code executionCaution

The description only shows MCP-based remote tool invocation and workflow orchestration; there is no evidence of local process spawning, arbitrary code execution, or system-level permission requests.

Data accessCaution

Its scope is limited to Gemini-related operations and connection management, with no indication of broad filesystem or local resource access; however, it still handles session and tool inputs, so this remains routine data exposure.

Supply chainCaution

The source is a GitHub open-source repository with high community adoption (64.7k stars), which lowers supply-chain risk; however, the license is unspecified and maintenance status is unknown, so caution is still warranted.

Recommendations

Enable this skill only when Gemini/Rube workflows are actually needed.
Verify at runtime that it only contacts the declared Rube/Composio endpoints.
Avoid putting unnecessary sensitive data into tool inputs.
If possible, review the upstream repository and the actual loaded tool list.

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

// download

Download SKILL.mdInstall manifest ↗

// docs

Gemini Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/gemini

Prerequisites

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

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["gemini"]
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 Gemini-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `gemini`
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 Refiner workflows via Rube MCP using current tool schemas first.

ComposioGet→

$ loading_