What is the first step to set up abstract automation?

Add the Rube MCP endpoint (https://rube.app/mcp) to your client and verify RUBE_SEARCH_TOOLS responds to fetch Abstract tool slugs and schemas.

Why must tools be discovered before execution?

Tool schemas can change; you must fetch current slugs and input requirements to avoid hardcoding.

What ensures safety during execution?

Verify the Abstract connection is ACTIVE via RUBE_MANAGE_CONNECTIONS and include a memory payload in RUBE_MULTI_EXECUTE_TOOL, using a valid session_id and avoiding hardcoded tool slugs.

abstract-automation

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

Files (1)

SKILL.md

2.9 KB

Abstract Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/abstract

Prerequisites

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

Step 2: Check Connection

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

Overview

Automate Abstract operations using Composio's Abstract toolkit through Rube MCP. It emphasizes discovering current tool schemas before execution to avoid stale slugs and arguments. Requires a connected RUBE MCP and an active Abstract connection.

How This Skill Works

First, fetch available Abstract tool slugs and schemas with RUBE_SEARCH_TOOLS. Then validate the Abstract connection with RUBE_MANAGE_CONNECTIONS and ensure it is ACTIVE. Finally, execute tools using RUBE_MULTI_EXECUTE_TOOL, including a memory payload and the session_id, reusing sessions when appropriate.

When to Use It

Starting a new Abstract workflow and needing current tool schemas
Tool schemas have changed; re-fetch slugs with RUBE_SEARCH_TOOLS before execution
Ensuring the Abstract toolkit connection is ACTIVE before running tools
Chaining multiple Abstract tools in one session using the same session_id
Performing bulk or bulk-ops with RUBE_REMOTE_WORKBENCH and run_composio_tool

Quick Start

Step 1: Get Rube MCP endpoint and ensure RUBE_SEARCH_TOOLS responds for Abstract tools
Step 2: Call RUBE_MANAGE_CONNECTIONS for toolkit 'abstract' and confirm ACTIVE status
Step 3: Execute a discovered tool with RUBE_MULTI_EXECUTE_TOOL, including memory and a session_id

Best Practices

Always call RUBE_SEARCH_TOOLS before selecting tools
Check RUBE_MANAGE_CONNECTIONS status is ACTIVE
Use exact field names and types from the search results
Include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty
Reuse session IDs within a workflow and generate new ones for new workflows

Example Use Cases

Discover tools, connect, and execute a single Abstract operation in one run
Update an automation when tool schemas change by re-searching first
Chain three Abstract tools in one session using the same session_id
Bulk export: use RUBE_REMOTE_WORKBENCH with run_composio_tool for multiple tasks
Pull full tool schemas with RUBE_GET_TOOL_SCHEMAS to verify inputs against schemaRef

Frequently Asked Questions

Add this skill to your agents