gemini-automation
Scannednpx machina-cli add skill ComposioHQ/awesome-claude-skills/gemini-automation --openclawGemini 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_CONNECTIONSwith toolkitgemini - Always call
RUBE_SEARCH_TOOLSfirst 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_TOOLSresponds - Call
RUBE_MANAGE_CONNECTIONSwith toolkitgemini - 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_CONNECTIONSshows ACTIVE status before executing tools - Schema compliance: Use exact field names and types from the search results
- Memory parameter: Always include
memoryinRUBE_MULTI_EXECUTE_TOOLcalls, 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
Source
git clone https://github.com/ComposioHQ/awesome-claude-skills/blob/master/composio-skills/gemini-automation/SKILL.mdView on GitHub Overview
Automate Gemini operations through Composio's Gemini toolkit via Rube MCP. This skill orchestrates discovery, connection validation, and execution of Gemini tools, always querying current schemas before running workflows.
How This Skill Works
Connect to Gemini through Rube MCP by ensuring RUBE_SEARCH_TOOLS is available and the Gemini connection is ACTIVE via RUBE_MANAGE_CONNECTIONS. Discover tool slugs and input schemas with RUBE_SEARCH_TOOLS, then execute the selected tool with RUBE_MULTI_EXECUTE_TOOL, including a memory payload and session_id. Always use the latest tool schemas and avoid hardcoding slugs or arguments.
When to Use It
- Automating Gemini tasks end-to-end within a workflow.
- When tool schemas may change and you must fetch current slugs and arguments via RUBE_SEARCH_TOOLS.
- Setting up a new Gemini integration and verifying an ACTIVE connection.
- Reusing a session ID to maintain context across related Gemini tasks.
- Coordinating multi-step Gemini operations that require memory and pagination-aware tool discovery.
Quick Start
- Step 1: Add the Rube MCP endpoint (https://rube.app/mcp) and verify RUBE_SEARCH_TOOLS is available.
- Step 2: Call RUBE_MANAGE_CONNECTIONS with toolkits: ["gemini"] and ensure the connection is ACTIVE.
- Step 3: Use RUBE_SEARCH_TOOLS to discover tools, then run RUBE_MULTI_EXECUTE_TOOL with the chosen tool_slug, a session_id, and memory.
Best Practices
- Always call RUBE_SEARCH_TOOLS before executing any tool to fetch current schemas.
- Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE before running workflows.
- Use exact field names and types from the discovered tool schemas; avoid hardcoding.
- Include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({}).
- Reuse session IDs within a workflow and generate new ones for separate workflows; watch for pagination tokens.
Example Use Cases
- Discover Gemini data-pull tools with RUBE_SEARCH_TOOLS and execute the chosen tool slug using RUBE_MULTI_EXECUTE_TOOL, preserving context with a session_id.
- Before running a Gemini task, confirm the connection is ACTIVE via RUBE_MANAGE_CONNECTIONS.
- Chain multiple Gemini tasks by reusing a session_id and memory payload across RUBE_MULTI_EXECUTE_TOOL calls.
- Adapt to schema changes by re-fetching tool slugs through RUBE_SEARCH_TOOLS rather than hardcoding.
- Always pass a memory object in tool executions to maintain state across steps.
