Why must I call RUBE_SEARCH_TOOLS before executing?

Tool schemas can change. Calling RUBE_SEARCH_TOOLS fetches current tool slugs and input schemas, preventing hardcoded errors.

What if the connection status isn’t ACTIVE?

Follow the returned auth link after calling RUBE_MANAGE_CONNECTIONS to complete setup and recheck status until ACTIVE.

yousearch-automation

Scanned

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

Files (1)

SKILL.md

2.9 KB

Yousearch Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/yousearch

Prerequisites

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

Step 2: Check Connection

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

Overview

Automate Yousearch operations using Composio's Yousearch toolkit through Rube MCP. Always search for current tool schemas before executing workflows to stay aligned with tool updates.

How This Skill Works

Discover available Yousearch tools with RUBE_SEARCH_TOOLS, verify and establish a connection with RUBE_MANAGE_CONNECTIONS (toolkit: yousearch), then execute the selected tool with RUBE_MULTI_EXECUTE_TOOL using the discovered slug and schema-compliant arguments. Include memory in each call and reuse sessions when chaining multiple steps.

When to Use It

You need to perform a Yousearch task where tool schemas may change and must be fetched at runtime
You must set up or verify an ACTIVE Yousearch connection via RUBE_MANAGE_CONNECTIONS before running workflows
You are orchestrating a multi-step Yousearch workflow that requires session continuity and memory between steps
You want to handle paginated or multi-tool results by discovering tools first and processing results in sequence
You are automating batch Yousearch operations and need documented tool slugs and schemas to drive execution

Quick Start

Step 1: Ensure Rube MCP is configured (add https://rube.app/mcp) and RUBE_SEARCH_TOOLS responds
Step 2: Call RUBE_MANAGE_CONNECTIONS with toolkits: ["yousearch"] and verify the status is ACTIVE
Step 3: Run RUBE_MULTI_EXECUTE_TOOL using a TOOL_SLUG_FROM_SEARCH and supply schema-compliant arguments from the search results; include memory: {} and a session_id

Best Practices

Always call RUBE_SEARCH_TOOLS first to fetch current tool schemas
Ensure RUBE_MANAGE_CONNECTIONS shows ACTIVE before any tool execution
Use exact field names and types from the search results; do not hardcode slugs or args
Include memory in every RUBE_MULTI_EXECUTE_TOOL call, even if empty
Reuse session IDs for related steps; create new sessions for separate workflows and monitor pagination

Example Use Cases

Discover tools for a specific Yousearch task, connect via RUBE_MANAGE_CONNECTIONS, then execute TOOL_SLUG_FROM_SEARCH with args derived from the search results
Run a sequence of Yousearch tools in one workflow by reusing a session_id across steps and providing a memory object to RUBE_MULTI_EXECUTE_TOOL
Fetch current tool schemas with RUBE_SEARCH_TOOLS and use the returned tool_slugs and input schemas to drive automated tasks
Handle paginated responses by continuing to call RUBE_SEARCH_TOOLS until no page tokens remain, then execute the required tools
Bulk execute multiple discovered tools (TOOL_SLUG_FROM_SEARCHs) in a single workflow using RUBE_MULTI_EXECUTE_TOOL with memory and session_id

Frequently Asked Questions

Add this skill to your agents