What are the prerequisites to use openrouter-automation?

You must have RUBE MCP connected, RUBE_SEARCH_TOOLS available, an active Openrouter connection via RUBE_MANAGE_CONNECTIONS with the openrouter toolkit, and you should always search for current tool schemas before execution.

What is the memory parameter and why must it be included?

Memory is a required payload in RUBE_MULTI_EXECUTE_TOOL calls to maintain context across tools. Include memory even if it’s empty ({}), and reuse session IDs within a workflow.

openrouter-automation

Scanned

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

Files (1)

SKILL.md

2.9 KB

Openrouter Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/openrouter

Prerequisites

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

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["openrouter"]
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 Openrouter-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `openrouter`
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/openrouter-automation/SKILL.mdView on GitHub

Overview

Openrouter automation via Composio's Rube MCP lets you orchestrate Openrouter operations end-to-end. Use RUBE_SEARCH_TOOLS to fetch current tool schemas and avoid hard-coded slugs. This approach keeps tool execution aligned with live Openrouter capabilities.

How This Skill Works

The process starts by discovering available tools with RUBE_SEARCH_TOOLS to obtain current tool slugs and input schemas. Then you verify the Openrouter connection via RUBE_MANAGE_CONNECTIONS, ensuring the status is ACTIVE. Finally, you execute the chosen tool with RUBE_MULTI_EXECUTE_TOOL, including the required memory payload and session_id, and you repeat the discovery step to keep schemas up-to-date.

When to Use It

When starting a new Openrouter workflow and you need up-to-date tool schemas
When establishing or validating an ACTIVE Openrouter connection before a run
When orchestrating a sequence of Openrouter tasks within a single workflow using a session
When performing bulk or remote execution of multiple Openrouter tools
When troubleshooting tool schema changes or pagination while discovering tools

Quick Start

Step 1: Add https://rube.app/mcp as an MCP server and run RUBE_SEARCH_TOOLS to fetch current Openrouter tool schemas
Step 2: Call RUBE_MANAGE_CONNECTIONS with toolkits: ["openrouter"] to establish/verify the ACTIVE Openrouter connection
Step 3: Execute a selected tool with RUBE_MULTI_EXECUTE_TOOL, including memory and session_id; re-run discovery as needed

Best Practices

Always call RUBE_SEARCH_TOOLS first to fetch current tool schemas
Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE before executing tools
Use exact field names and types from the search results; do not hardcode slugs
Include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({})
Reuse session IDs within a workflow and handle pagination tokens to complete fetches

Example Use Cases

Discover Openrouter tools, connect, and run a single operation with an up-to-date tool slug
Bulk-run a set of Openrouter tools in a single session using RUBE_MULTI_EXECUTE_TOOL
Fetch full tool schemas with RUBE_GET_TOOL_SCHEMAS and generate an executable plan
Establish a new Openrouter workflow, verify ACTIVE connection, and execute with memory
Iterate through tool listings with RUBE_SEARCH_TOOLS, handling pagination until complete

Frequently Asked Questions

Add this skill to your agents