What are the prerequisites?

Rube MCP must be connected, RUBE_SEARCH_TOOLS must be available, and an ACTIVE Lever Sandbox connection should be established via RUBE_MANAGE_CONNECTIONS with the lever_sandbox toolkit.

How do I ensure current schemas?

Always run RUBE_SEARCH_TOOLS first to fetch the latest tool slugs and input schemas, then use those results to build your RUBE_MULTI_EXECUTE_TOOL calls.

Is memory required for tool execution?

Yes. Include a memory object in every RUBE_MULTI_EXECUTE_TOOL call, even if empty, to maintain state and context across the workflow.

lever-sandbox-automation

Scanned

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

Files (1)

SKILL.md

2.9 KB

Lever Sandbox Automation via Rube MCP

Automate Lever Sandbox operations through Composio's Lever Sandbox toolkit via Rube MCP.

Toolkit docs: composio.dev/toolkits/lever_sandbox

Prerequisites

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

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["lever_sandbox"]
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 Lever Sandbox-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `lever_sandbox`
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/lever-sandbox-automation/SKILL.md

View on GitHub

Overview

This skill automates Lever Sandbox operations through Composio's Lever Sandbox toolkit using Rube MCP. It emphasizes discovering current tool schemas before executing workflows to adapt to updates.

How This Skill Works

First, discover available Lever Sandbox tools with RUBE_SEARCH_TOOLS to obtain current slugs and input schemas. Next, verify an ACTIVE connection via RUBE_MANAGE_CONNECTIONS and then execute the chosen tool with RUBE_MULTI_EXECUTE_TOOL, including memory and a persistent session.

When to Use It

You need to automate Lever Sandbox operations without manual repetition, while keeping tool schemas up to date.
You must fetch current tool slugs and input schemas before running tasks.
You want to ensure the Lever Sandbox connection is ACTIVE before executing workflows.
You are performing bulk or multi-tool tasks across a single workflow and want to reuse a session.
You need to adapt to schema changes without hardcoding tool details.

Quick Start

Step 1: Ensure Rube MCP is available and RUBE_SEARCH_TOOLS returns Lever Sandbox schemas.
Step 2: Establish or verify an ACTIVE Lever Sandbox connection using RUBE_MANAGE_CONNECTIONS with toolkit lever_sandbox.
Step 3: Discover tools and execute a task with RUBE_MULTI_EXECUTE_TOOL, including memory and the correct session_id.

Best Practices

Always call RUBE_SEARCH_TOOLS first to get current tool schemas.
Check that RUBE_MANAGE_CONNECTIONS shows ACTIVE before executing tools.
Do not hardcode tool slugs or arguments; rely on schemas returned by search.
Include memory in every RUBE_MULTI_EXECUTE_TOOL call, even if empty.
Reuse session IDs within a workflow and generate new ones for new workflows.

Example Use Cases

Discover tools, connect to Lever Sandbox, and run a single tool end-to-end.
Bulk-run several Lever Sandbox tasks by discovering tool slugs and executing them via RUBE_MULTI_EXECUTE_TOOL.
Handle tool discovery pagination to fetch all available operations.
Maintain a persistent session across related tasks to speed automation.
Re-authenticate or re-check connection if ACTIVE is lost during a workflow.

Frequently Asked Questions

Add this skill to your agents