Do I need API keys to use this skill?

No. The prerequisites show that you add the MCP endpoint (https://rube.app/mcp) and connect Hookdeck via the toolkit; no API keys are required.

Why should I always search for tools before running workflows?

Tool schemas change. RUBE_SEARCH_TOOLS returns the current tool slugs, input schemas, recommended execution plans, and known pitfalls, preventing failures.

How should I structure executions safely?

Ensure the connection is ACTIVE (RUBE_MANAGE_CONNECTIONS), include a memory payload in RUBE_MULTI_EXECUTE_TOOL, and use exact field names/types from the discovered schemas; reuse session IDs for related steps and handle pagination.

hookdeck-automation

Scanned

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

Files (1)

SKILL.md

2.9 KB

Hookdeck Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/hookdeck

Prerequisites

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

Step 2: Check Connection

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

Overview

Automate Hookdeck operations through Composio's Hookdeck toolkit using Rube MCP. It coordinates discovery, connection setup, and execution of Hookdeck tasks with up-to-date schemas. This helps you build reliable, repeatable webhook workflows.

How This Skill Works

Rube MCP first discovers available Hookdeck tools (RUBE_SEARCH_TOOLS). It then validates an ACTIVE Hookdeck connection (RUBE_MANAGE_CONNECTIONS). Finally, it executes the selected tool (RUBE_MULTI_EXECUTE_TOOL) using the proper memory payload and a session_id.

When to Use It

Automating repetitive Hookdeck tasks across environments
Ensuring tool schemas are current before any workflow by discovering tools first
Setting up a new Hookdeck integration or first-run workflow
Orchestrating sequential Hookdeck operations with shared session state
Conducting bulk or multi-tool executions in a single workflow using discovered tool slugs

Quick Start

Step 1: Discover available Hookdeck tools with RUBE_SEARCH_TOOLS (queries: [{use_case: "Hookdeck operations"}])
Step 2: Connect to Hookdeck with RUBE_MANAGE_CONNECTIONS (toolkit: ["hookdeck"])
Step 3: Execute your chosen tool with RUBE_MULTI_EXECUTE_TOOL using memory and a session_id

Best Practices

Always call RUBE_SEARCH_TOOLS first to fetch current tool schemas
Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE before executing tools
Use exact field names and types from tool schemas; avoid hardcoding slugs or arguments
Always include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({})
Reuse session IDs for related tasks within a workflow and handle pagination when listing tools

Example Use Cases

Discover tools for a Hookdeck task, then execute a 'Create webhook' operation with dynamic inputs
Connect to Hookdeck via Rube MCP and run a sequence: discovery → connection check → tool execution
Execute multiple Hookdeck tools in a single workflow by using discovered tool slugs and a shared session
Reuse a session_id to perform related Hookdeck operations without re-authenticating between steps
Paginate through tool results from RUBE_SEARCH_TOOLS to locate a target tool and run it

Frequently Asked Questions

Add this skill to your agents