How do I ensure tool schemas are current?

Always call RUBE_SEARCH_TOOLS before execution to fetch the latest tool schemas.

What should I do if the connection isn't ACTIVE?

Use RUBE_MANAGE_CONNECTIONS for the 'reply' toolkit and follow the auth flow until the status becomes ACTIVE.

Is memory required in execute calls?

Yes. Include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty {}; and reuse session_id where appropriate.

reply-automation

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

Files (1)

SKILL.md

2.8 KB

Reply Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/reply

Prerequisites

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

Step 2: Check Connection

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

Overview

This skill automates Reply operations through Composio's Reply toolkit via Rube MCP. It emphasizes discovering current tool schemas first and ensuring an ACTIVE Reply connection before execution.

How This Skill Works

The workflow starts by discovering available Reply tools with RUBE_SEARCH_TOOLS to obtain live input schemas. Next, it verifies and manages the Reply connection using RUBE_MANAGE_CONNECTIONS, ensuring the status is ACTIVE. Finally, it executes the chosen tool via RUBE_MULTI_EXECUTE_TOOL, supplying the discovered inputs and a memory payload with a session_id.

When to Use It

Start a new Reply automation by first discovering current tool schemas with RUBE_SEARCH_TOOLS.
Set up or refresh the Rube MCP connection for the 'reply' toolkit using RUBE_MANAGE_CONNECTIONS.
Prepare to run a specific reply workflow by selecting the discovered tool slug and providing required arguments.
Handle workflows that may return paginated tool results and require continuing discovery.
Reuse a session_id across related Reply tasks within a single workflow to optimize context.

Quick Start

Step 1: Ensure RUBE_SEARCH_TOOLS is available and discover Reply tools for your use case.
Step 2: Run RUBE_MANAGE_CONNECTIONS to connect the 'reply' toolkit and confirm ACTIVE.
Step 3: Execute a tool with RUBE_MULTI_EXECUTE_TOOL using the discovered slug, proper arguments, memory: {}, and a session_id.

Best Practices

Always call RUBE_SEARCH_TOOLS before executing any workflow to fetch current tool schemas.
Check that RUBE_MANAGE_CONNECTIONS shows ACTIVE status before running tools.
Use exact field names and types from the live tool schemas returned by the search.
Include memory in every RUBE_MULTI_EXECUTE_TOOL call, even if empty ({}).
Reuse session IDs where possible and manage new sessions only when starting a new workflow.

Example Use Cases

Example: Discover tools for a customer support auto-reply flow, then execute a tool to generate a templated response.
Example: Connect to the Reply toolkit, verify ACTIVE status, and prepare a multi-tool workflow for follow-up replies.
Example: Execute a tool with the correct input schema to draft an escalation reply based on a current case.
Example: Retrieve multiple tools with pagination, continuing discovery until all suitable tools are identified.
Example: Process several replies in a batch by reusing a session_id across related tool executions.

Frequently Asked Questions

Add this skill to your agents