What is required to use yandex-automation?

Rube MCP connected, and the Yandex toolkit. You must first call RUBE_SEARCH_TOOLS to get current tool schemas.

Do I need API keys for Yandex tasks?

No API keys are needed. Add the MCP endpoint and manage the connection with RUBE_MANAGE_CONNECTIONS.

How do I ensure tool schemas are up to date?

Always call RUBE_SEARCH_TOOLS before using tools; schemas can change and you should use the latest slugs and argument names.

yandex-automation

Scanned

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

Files (1)

SKILL.md

2.8 KB

Yandex Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/yandex

Prerequisites

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

Step 2: Check Connection

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

Overview

Automate Yandex operations through Composio's Yandex toolkit using Rube MCP. This skill emphasizes discovering current tool schemas before execution to avoid broken slugs and args.

How This Skill Works

RUBE_SEARCH_TOOLS fetches available Yandex tool slugs and input schemas. RUBE_MANAGE_CONNECTIONS verifies an ACTIVE Yandex connection. Finally, RUBE_MULTI_EXECUTE_TOOL runs the chosen tool with memory and session_id, ensuring schema-compliant arguments.

When to Use It

When you need up-to-date tool schemas before running any Yandex operation
When establishing or verifying a Yandex connection via RUBE_MANAGE_CONNECTIONS
When selecting and executing a specific Yandex tool after discovery
When chaining multiple Yandex tool executions within a single session
When handling pagination in tool discovery results to ensure all tools are considered

Quick Start

Step 1: Get Rube MCP — add https://rube.app/mcp as an MCP server in your client config.
Step 2: Verify availability — call RUBE_SEARCH_TOOLS and ensure RUBE_MANAGE_CONNECTIONS with toolkit yandex shows ACTIVE.
Step 3: Execute a tool — pick a tool_slug from search results and call RUBE_MULTI_EXECUTE_TOOL with memory and session_id.

Best Practices

Always call RUBE_SEARCH_TOOLS first to obtain current tool schemas
Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE before executing any tools
Do not hardcode tool slugs or arguments; rely on search results
Always include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({})
Reuse session IDs within a workflow and generate new ones for new workflows

Example Use Cases

Discover Yandex tools for a given use case and execute a selected tool with proper arguments using RUBE_MULTI_EXECUTE_TOOL
Connect to Yandex via RUBE_MANAGE_CONNECTIONS, then confirm ACTIVE before running any workflows
Use RUBE_SEARCH_TOOLS to fetch current schemas for a batch of Yandex operations and adapt the workflow accordingly
Run a multi-step Yandex workflow in a single session, reusing the same session_id across steps
Handle pagination tokens when fetching tool schemas to ensure all available Yandex tools are considered

Frequently Asked Questions

Add this skill to your agents