What do I need to start automating Hystruct tasks?

You need a connected Rube MCP, an active Hystruct connection via RUBE_MANAGE_CONNECTIONS, and access to RUBE_SEARCH_TOOLS to fetch current tool schemas.

Do I have to hardcode tool slugs?

No. Always call RUBE_SEARCH_TOOLS to obtain current tool slugs and input schemas before execution.

What if the Hystruct connection isn't ACTIVE?

Follow the returned auth link from RUBE_MANAGE_CONNECTIONS to complete setup, then recheck status until ACTIVE before running workflows.

hystruct-automation

Scanned

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

Files (1)

SKILL.md

2.9 KB

Hystruct Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/hystruct

Prerequisites

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

Step 2: Check Connection

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

Overview

Automate Hystruct operations through Composio's Hystruct toolkit via Rube MCP. Always search for current tool schemas before executing to avoid hardcoding slugs or arguments.

How This Skill Works

Connect to Rube MCP and verify RUBE_SEARCH_TOOLS is available. Use RUBE_SEARCH_TOOLS to discover Hystruct tool slugs and schemas, then establish a Hystruct connection with RUBE_MANAGE_CONNECTIONS. When ready, execute tools with RUBE_MULTI_EXECUTE_TOOL, including memory: {} and a valid session_id, reusing sessions when appropriate.

When to Use It

When starting a Hystruct workflow to ensure you use the latest tool schemas
When establishing or refreshing a Hystruct connection via Rube MCP
Before executing any Hystruct tool to confirm the discovered slug and input schema
When reusing a session across multiple Hystruct steps to maintain context
When troubleshooting Hystruct automation and validating pagination or schema changes

Quick Start

Step 1: Add the Rube MCP endpoint https://rube.app/mcp to your client and verify RUBE_SEARCH_TOOLS responds.
Step 2: Discover tools with RUBE_SEARCH_TOOLS using use_case: 'Hystruct operations' to obtain tool slugs and schemas.
Step 3: Manage your Hystruct connection with RUBE_MANAGE_CONNECTIONS (toolkits: ['hystruct']) and run a first tool with RUBE_MULTI_EXECUTE_TOOL including memory: {} and a valid session_id.

Best Practices

Always search first with RUBE_SEARCH_TOOLS to get current tool schemas
Verify the RUBE_MANAGE_CONNECTIONS status is ACTIVE before execution
Use exact field names and types from the search results for arguments
Include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({})
Reuse session_id within a workflow to maintain continuity

Example Use Cases

Discover Hystruct tools with RUBE_SEARCH_TOOLS, select a tool_slug from the results, and execute it via RUBE_MULTI_EXECUTE_TOOL using the discovered input schema.
Establish a Hystruct connection with RUBE_MANAGE_CONNECTIONS and run a workflow only after the status shows ACTIVE.
Always include memory: {} in multi-tool executions to satisfy the schema requirements.
Reuse a single session_id across several Hystruct steps to optimize performance and maintain context.
Handle pagination tokens in RUBE_SEARCH_TOOLS responses and continue fetching until all tools are discovered.

Frequently Asked Questions

Add this skill to your agents