Do I need API keys to use this skill?

No API keys are required. Add the MCP endpoint and use Rube MCP to access Claid AI tools.

What happens if tool schemas change?

Always search for current schemas with RUBE_SEARCH_TOOLS before running tools; do not hardcode slugs or arguments.

How can I ensure a successful run?

Ensure the connection is ACTIVE via RUBE_MANAGE_CONNECTIONS, include a memory object in RUBE_MULTI_EXECUTE_TOOL calls, and manage session IDs appropriately for the workflow

claid-ai-automation

Scanned

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

Files (1)

SKILL.md

2.9 KB

Claid AI Automation via Rube MCP

Automate Claid AI operations through Composio's Claid AI toolkit via Rube MCP.

Toolkit docs: composio.dev/toolkits/claid_ai

Prerequisites

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

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["claid_ai"]
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 Claid AI-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `claid_ai`
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/claid-ai-automation/SKILL.mdView on GitHub

Overview

Automate Claid AI operations through Composio's Claid AI toolkit using Rube MCP. The workflow always searches for current tool schemas before execution to avoid brittle automation.

How This Skill Works

This integration requires RUBE_SEARCH_TOOLS to be connected and a Claid AI connection via RUBE_MANAGE_CONNECTIONS with the claid_ai toolkit. You first discover available tools and their input schemas, then verify the connection is ACTIVE, and finally execute the chosen tools with RUBE_MULTI_EXECUTE_TOOL using the discovered tool slug, proper arguments, memory, and a session_id.

When to Use It

You need to automate Claid AI tasks and want up to date tool schemas before running any workflow
You are setting up a new Claid AI workflow and must ensure the connection is ACTIVE before use
You want to move from discovery to execution in a structured core workflow (discover, check, execute)
You need to run multiple Claid AI tools in sequence and want to reuse a session within a workflow
Tool schemas change and you want to avoid hardcoding slugs or arguments

Quick Start

Step 1: Add https://rube.app/mcp as an MCP server in your client configuration; no API keys are needed
Step 2: Verify RUBE_SEARCH_TOOLS responds and call RUBE_MANAGE_CONNECTIONS with toolkit claid_ai to activate the connection
Step 3: Use RUBE_SEARCH_TOOLS to discover tools for your Claid AI task, then run RUBE_MULTI_EXECUTE_TOOL with the chosen tool slug and proper memory and session_id

Best Practices

Always call RUBE_SEARCH_TOOLS first to fetch current tool slugs and schemas
Check that RUBE_MANAGE_CONNECTIONS shows ACTIVE status before executing any tool
Use exact field names and types from the search results; do not guess
Include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty
Reuse session IDs within a workflow and generate new ones for distinct workflows

Example Use Cases

Automate a Claid AI data labeling workflow by discovering tools for Claid AI operations and executing the labeling tool with correct arguments
Run daily Claid AI quality checks by discovering relevant tools and orchestrating tools in a scheduled session
Perform bulk Claid AI tasks via a batch workflow using multi tool execution after tool discovery
Migrate workflows when tool schemas change by re discovering tools and updating execution steps
Rebuild a failed workflow by reestablishing the claid_ai connection and re running discovery before execution

Frequently Asked Questions

Add this skill to your agents