home / skills / composiohq / awesome-claude-skills / gemini-automation

gemini-automation skill

safe

/gemini-automation

This skill automates Gemini operations via Rube MCP, discovering current tool schemas first to ensure adaptive, schema-aware tool execution.

npx playbooks add skill composiohq/awesome-claude-skills --skill gemini-automation

Review the files below or copy the command above to add this skill to your agents.

Files (1)

SKILL.md

2.8 KB

---
name: gemini-automation
description: "Automate Gemini tasks via Rube MCP (Composio). Always search tools first for current schemas."
requires:
  mcp: [rube]
---

# Gemini Automation via Rube MCP

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

**Toolkit docs**: [composio.dev/toolkits/gemini](https://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.

1. Verify Rube MCP is available by confirming `RUBE_SEARCH_TOOLS` responds
2. Call `RUBE_MANAGE_CONNECTIONS` with toolkit `gemini`
3. If connection is not ACTIVE, follow the returned auth link to complete setup
4. 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](https://composio.dev)*

Overview

This skill automates Gemini tasks through Composio’s Gemini toolkit using Rube MCP. It provides a reproducible pattern: discover tools, confirm Gemini connection, then execute schema-compliant calls. The workflow emphasizes always searching tools first to fetch current schemas and avoid hardcoding.

How this skill works

The skill uses RUBE_SEARCH_TOOLS to discover available Gemini tool slugs, input schemas, and recommended plans. It verifies or establishes an active Gemini connection with RUBE_MANAGE_CONNECTIONS, then runs operations with RUBE_MULTI_EXECUTE_TOOL (including a memory object) or RUBE_REMOTE_WORKBENCH for bulk jobs. It handles session management, pagination, and schema validation returned by the search step.

When to use it

Automating Gemini prompts, uploads, or model operations from an orchestration agent
Building repeatable Gemini-driven pipelines that must stay schema-safe
Running bulk or parallel Gemini tasks through Composio tooling
Integrating Gemini actions into broader workflows that require connection management
When tool schemas may change frequently and must be discovered at runtime

Best practices

Always call RUBE_SEARCH_TOOLS first to get current tool slugs and input schemas; never hardcode slugs or fields
Check RUBE_MANAGE_CONNECTIONS and ensure the toolkit `gemini` is ACTIVE before executing tools
Supply the exact field names and types returned by search responses to avoid schema validation errors
Always include a memory parameter (can be empty {}) in RUBE_MULTI_EXECUTE_TOOL calls
Reuse session IDs across related steps; generate new session IDs for separate workflows
Watch for pagination tokens in search responses and iterate until all results are fetched

Example use cases

Discover Gemini upload or prompt tools dynamically, then run model inference without manual schema wiring
Automate a nightly batch that executes multiple Gemini operations via RUBE_MULTI_EXECUTE_TOOL or RUBE_REMOTE_WORKBENCH
Build an agent that conditionally invokes different Gemini tools based on the search-recommended execution plan
Create fail-safe workflows that validate connection status and prompt re-auth when RUBE_MANAGE_CONNECTIONS reports non-ACTIVE
Perform schema-aware transformations: fetch tool schema, adapt inputs, and execute to avoid runtime errors

FAQ

Do I need API keys to use Rube MCP?

No. Add https://rube.app/mcp as an MCP server in your client configuration; the MCP endpoint handles access flows and RUBE_MANAGE_CONNECTIONS provides auth links if needed.

What if a tool slug or schema changes mid-workflow?

Always re-run RUBE_SEARCH_TOOLS before execution steps that may be affected. Reuse sessions for continuity, but rediscover tools if the task surface could change.