What is gan-ai-automation?

A workflow to automate Gan AI tasks through the Gan AI toolkit using Rube MCP and the required discovery and connection steps.

Do I need to hardcode tool slugs?

No. Always call RUBE_SEARCH_TOOLS to fetch current slugs and schemas before execution.

What if tool schemas change?

RUBE_SEARCH_TOOLS should be re-run to obtain updated input fields, then run the workflow accordingly, including memory.

gan-ai-automation

Scanned

npx machina-cli add skill ComposioHQ/awesome-claude-skills/gan-ai-automation --openclaw

Files (1)

SKILL.md

2.8 KB

Gan AI Automation via Rube MCP

Automate Gan AI operations through Composio's Gan AI toolkit via Rube MCP.

Toolkit docs: composio.dev/toolkits/gan_ai

Prerequisites

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

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["gan_ai"]
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 Gan AI-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `gan_ai`
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/gan-ai-automation/SKILL.mdView on GitHub

Overview

Gan AI Automation via Rube MCP automates Gan AI operations using Composio's Gan AI toolkit. It requires searching tools first to fetch current schemas, establishing a Gan AI connection, and executing tools through a guided workflow. This approach keeps tool usage accurate and repeatable as schemas change.

How This Skill Works

First, discover available Gan AI tools with RUBE_SEARCH_TOOLS to obtain current slugs and input schemas. Next, verify the Gan AI connection with RUBE_MANAGE_CONNECTIONS and ensure the status is ACTIVE. Finally, run tools via RUBE_MULTI_EXECUTE_TOOL, including memory and session_id, following the exact schema names from the discovery results.

When to Use It

When you need up to date Gan AI tool schemas fetched before every run
When you must confirm an ACTIVE Gan AI connection prior to execution
When you want to discover tools and reuse discovered slugs in workflows
When you perform batch or multi tool runs using RUBE_MULTI_EXECUTE_TOOL
When tool schemas may change and pagination tokens require continued fetching

Quick Start

Step 1: Configure RUBE MCP by adding the rube app MCP endpoint and verify RUBE_SEARCH_TOOLS responds
Step 2: Connect gan_ai via RUBE_MANAGE_CONNECTIONS and confirm ACTIVE status
Step 3: Discover tools with RUBE_SEARCH_TOOLS and execute a chosen tool with RUBE_MULTI_EXECUTE_TOOL, including memory and session_id

Best Practices

Always call RUBE_SEARCH_TOOLS first to fetch current tool schemas
Check that RUBE_MANAGE_CONNECTIONS shows ACTIVE before executing tools
Use exact field names and types from the search results
Always include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty
Reuse session IDs for a workflow and avoid hardcoding tool slugs across runs

Example Use Cases

Discover Gan AI tool slugs for a data preprocessing task and execute with a session id
Establish gan_ai connection, fetch available tools, then run a tool with a memory payload
Bulk execute multiple discovered tools via RUBE_MULTI_EXECUTE_TOOL in a single session
Fetch full tool schemas with RUBE_GET_TOOL_SCHEMAS to validate inputs before running
Handle pagination by continuing RUBE_SEARCH_TOOLS calls until all tokens are consumed

Frequently Asked Questions

Add this skill to your agents