What is the agentql-automation skill for?

It automates Agentql operations via Rube MCP, emphasizing tool discovery, connection management, and schema-compliant execution.

Do I always need to call RUBE_SEARCH_TOOLS before running a tool?

Yes. The skill requires discovering current tool slugs and input schemas to avoid hardcoding and ensure compatibility.

What should I do if tool schemas change or pagination appears in discovery?

Re-run RUBE_SEARCH_TOOLS to fetch updated slugs and schemas, adjust your arguments accordingly, and handle pagination tokens until complete.

agentql-automation

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

Files (1)

SKILL.md

2.9 KB

Agentql Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/agentql

Prerequisites

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

Step 2: Check Connection

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

Overview

This skill automates Agentql operations using Composio's Rube MCP. It emphasizes discovering current tool schemas before execution, establishing an ACTIVE Agentql connection, and executing tools with proper memory and schema compliance to avoid hard-coded slugs.

How This Skill Works

The workflow starts by using RUBE_SEARCH_TOOLS to discover available Agentql tools and their input schemas. Next, RUBE_MANAGE_CONNECTIONS ensures the Agentql toolkit is connected and ACTIVE. Finally, RUBE_MULTI_EXECUTE_TOOL runs the chosen tool slug with memory and schema-compliant arguments, reusing session IDs when appropriate.

When to Use It

You are starting a new Agentql workflow and the tool list is unknown, so you must discover tools first.
You need to verify the Agentql connection is ACTIVE before executing any tools.
You want to execute Agentql tools with dynamic, schema-driven arguments and avoid hardcoding slugs.
You must handle pagination or schema changes when discovering tools via RUBE_SEARCH_TOOLS.
You are automating multiple Agentql tasks within a single workflow and should reuse session IDs for efficiency.

Quick Start

Step 1: Verify RUBE_SEARCH_TOOLS is available and fetch Agentql tool schemas.
Step 2: Establish an ACTIVE Agentql connection with RUBE_MANAGE_CONNECTIONS and toolkit 'agentql'.
Step 3: Discover a tool, then execute it with RUBE_MULTI_EXECUTE_TOOL using memory: {} and the correct session_id.

Best Practices

Always run RUBE_SEARCH_TOOLS first to fetch current tool slugs and input schemas.
Check RUBE_MANAGE_CONNECTIONS shows ACTIVE before executing tools.
Use exact field names and types from the discovered tool schemas; avoid hardcoding.
Include the memory parameter in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({}).
Reuse session IDs within a workflow when appropriate and generate new ones for new tasks.

Example Use Cases

Automate a recurring Agentql query by discovering the available tools, connecting via RUBE_MANAGE_CONNECTIONS, and executing the chosen query tool with a memory object to track results.
Migrate a manual Agentql workflow to automation by performing tool discovery, confirming an ACTIVE connection, and executing the tool with dynamic inputs derived from RUBE_SEARCH_TOOLS results.
Handle tool schema changes by re-running RUBE_SEARCH_TOOLS, updating slugs and argument names, and reconfiguring RUBE_MULTI_EXECUTE_TOOL calls accordingly.
Perform bulk operations using RUBE_REMOTE_WORKBENCH and run_composio_tool() after discovering tools and ensuring a valid session.
Obtain the full tool schema via RUBE_GET_TOOL_SCHEMAS to validate inputs before integrating into a CI/CD pipeline.

Frequently Asked Questions

Add this skill to your agents