Do I need to call RUBE_SEARCH_TOOLS before every tool execution?

Yes. It ensures you have the current tool slugs and input schemas and prevents hardcoding.

What indicates a ready-to-run state for automated tools?

RUBE_MANAGE_CONNECTIONS should report ACTIVE for the 'customjs' toolkit, and you should include a valid session_id and memory in RUBE_MULTI_EXECUTE_TOOL.

Can I bulk-run tools or use remote benches?

Yes. The Quick Reference mentions RUBE_REMOTE_WORKBENCH and run_composio_tool for bulk or batch operations.

customjs-automation

Scanned

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

Files (1)

SKILL.md

2.9 KB

Customjs Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/customjs

Prerequisites

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

Step 2: Check Connection

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

Overview

This skill automates Customjs operations through Composio's Rube MCP toolkit. It emphasizes discovering current tool schemas with RUBE_SEARCH_TOOLS before execution and managing a live Customjs connection for reliable workflows.

How This Skill Works

Connect Rube MCP and the Customjs toolkit, then use RUBE_SEARCH_TOOLS to fetch up-to-date tool slugs and input schemas. Validate the connection with RUBE_MANAGE_CONNECTIONS, and finally run tools via RUBE_MULTI_EXECUTE_TOOL using the discovered slug and proper arguments, always including memory and a valid session_id.

When to Use It

You need to automate a recurring Customjs workflow end-to-end and want end-to-end orchestration.
Tool schemas change frequently and you must fetch current slugs and args with RUBE_SEARCH_TOOLS before running anything.
You must verify that the Customjs connection is ACTIVE before executing any tools.
You want to design a multi-tool workflow by discovering tools, planning execution, and running them in sequence.
You need to perform bulk or batch Customjs operations using RUBE_REMOTE_WORKBENCH or run_composio_tool.

Quick Start

Step 1: Add https://rube.app/mcp as an MCP server and confirm RUBE_SEARCH_TOOLS responds.
Step 2: Run RUBE_SEARCH_TOOLS with a use_case like 'Customjs operations' to discover available tools and schemas.
Step 3: Run RUBE_MANAGE_CONNECTIONS for toolkit 'customjs', then execute a chosen tool with RUBE_MULTI_EXECUTE_TOOL using memory and a session_id.

Best Practices

Always call RUBE_SEARCH_TOOLS first to get current tool schemas and avoid hardcoding slugs.
Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE before executing tools.
Use exact field names and types from the tool schemas returned by search results.
Include memory in every RUBE_MULTI_EXECUTE_TOOL call, even if empty ({}).
Reuse session IDs for related steps in a workflow; generate new IDs only for independent runs.

Example Use Cases

Nightly ETL: Discover tools with RUBE_SEARCH_TOOLS, connect, and execute a data_transform tool with a scheduled session.
Schema-driven task: Retrieve tool schemas for a new Customjs task, adapt inputs accordingly, then run the tool.
Connection verification: Validate ACTIVE status via RUBE_MANAGE_CONNECTIONS before performing any tool executions.
Bulk update: Use RUBE_REMOTE_WORKBENCH with run_composio_tool to perform a batch set of Customjs operations.
New multi-step workflow: Generate a new session_id, orchestrate multiple tools in sequence, and reuse the session for subsequent steps.

Frequently Asked Questions

Add this skill to your agents