How do I ensure tool schemas are up to date?

Always search with RUBE_SEARCH_TOOLS before executing; tool schemas can change and you should not hardcode slugs or arguments.

What must I include in a tool execution call?

Include memory, session_id, and the schema-compliant arguments for the discovered tool_slug.

How do I verify the bench connection is ready?

Use RUBE_MANAGE_CONNECTIONS to check the bench toolkit status and ensure it shows ACTIVE before running tools.

bench-automation

Scanned

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

Files (1)

SKILL.md

2.8 KB

Bench Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/bench

Prerequisites

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

Step 2: Check Connection

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

Overview

Bench Automation via Rube MCP lets you orchestrate bench operations using Composio's Bench toolkit. It emphasizes searching for current tool schemas before execution to avoid drift and misconfigurations.

How This Skill Works

Connect Rube MCP to the bench toolkit, verify an ACTIVE connection, and then discover available bench tools with RUBE_SEARCH_TOOLS. Retrieve tool slugs and input schemas, then execute chosen tools via RUBE_MULTI_EXECUTE_TOOL, ensuring memory and session_id are included.

When to Use It

Automating repetitive bench workflows to save time and reduce manual steps
When bench tool schemas frequently change and you must fetch the latest definitions
When orchestrating multiple bench tools in a single session
When reusing session IDs within a workflow for continuity
When you need to verify an ACTIVE bench connection before running any tools

Quick Start

Step 1: Add https://rube.app/mcp as an MCP server in your client; no API keys needed. Verify RUBE_SEARCH_TOOLS responds.
Step 2: Call RUBE_MANAGE_CONNECTIONS with toolkits: ["bench"] and complete auth if the state is not ACTIVE.
Step 3: Use RUBE_SEARCH_TOOLS to discover tools, then execute with RUBE_MULTI_EXECUTE_TOOL using memory: {} and a discovered tool_slug.

Best Practices

Always search first for current tool schemas to avoid hardcoding slugs or arguments
Check the bench connection is ACTIVE with RUBE_MANAGE_CONNECTIONS before executing tools
Use exact field names and types from the search results (schema compliance)
Always include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({})
Reuse session IDs within a workflow and generate new ones for new tasks

Example Use Cases

Discover available bench tools with RUBE_SEARCH_TOOLS, then execute a chosen tool using RUBE_MULTI_EXECUTE_TOOL in a single session
Establish a bench connection via RUBE_MANAGE_CONNECTIONS with the bench toolkit and run a sequence of tools
Iterate through paginated tool results to fetch all bench tasks and execute them as a batch
Run multiple bench tool calls in one workflow while maintaining a consistent memory map and session_id
Validate that the connection status is ACTIVE before starting a bench automation workflow and handle any required auth flow

Frequently Asked Questions

Add this skill to your agents