home / skills / composiohq / awesome-claude-skills / abstract-automation

abstract-automation skill

safe

/abstract-automation

This skill automates Abstract tasks via Composio using Rube MCP, ensuring live tool discovery and verified connections before workflow execution.

npx playbooks add skill composiohq/awesome-claude-skills --skill abstract-automation

Review the files below or copy the command above to add this skill to your agents.

Files (1)

SKILL.md

2.9 KB

---
name: abstract-automation
description: "Automate Abstract tasks via Rube MCP (Composio). Always search tools first for current schemas."
requires:
  mcp: [rube]
---

# Abstract Automation via Rube MCP

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

**Toolkit docs**: [composio.dev/toolkits/abstract](https://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.

1. Verify Rube MCP is available by confirming `RUBE_SEARCH_TOOLS` responds
2. Call `RUBE_MANAGE_CONNECTIONS` with toolkit `abstract`
3. If connection is not ACTIVE, follow the returned auth link to complete setup
4. 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](https://composio.dev)*

Overview

This skill automates Abstract tasks through Composio’s Abstract toolkit using Rube MCP. It orchestrates discovery, connection validation, and execution of Abstract tools so you can run reliable workflows without hardcoding schemas. Use it to perform single-step actions or complex bulk operations with session and memory management handled correctly.

How this skill works

The skill first calls RUBE_SEARCH_TOOLS to retrieve live tool slugs, input schemas, recommended plans, and pagination info. It then verifies an active Abstract connection via RUBE_MANAGE_CONNECTIONS. Finally it runs tools with RUBE_MULTI_EXECUTE_TOOL or RUBE_REMOTE_WORKBENCH, always supplying schema-compliant arguments, a session_id, and a memory payload (even if empty). It recommends fetching full schemas with RUBE_GET_TOOL_SCHEMAS when required.

When to use it

Automate Abstract repository, model, or dataset operations programmatically
Run multi-step Abstract workflows that require session continuity
Perform bulk or parallel Abstract tasks via RUBE_REMOTE_WORKBENCH
Integrate Abstract actions into larger Claude or agent-driven pipelines
When tool schemas may change frequently and you need live discovery

Best practices

Always call RUBE_SEARCH_TOOLS first—do not hardcode tool slugs or arguments
Verify toolkit connection is ACTIVE with RUBE_MANAGE_CONNECTIONS before executing
Use exact field names and types from returned schemas to avoid validation errors
Include a memory object in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({}), and reuse session_ids for related steps
Check for pagination tokens on search responses and iterate until complete

Example use cases

List and inspect available Abstract tools and full schemas before building an automation
Create a session, validate the Abstract connection, and run a sequence of composio tools to update datasets
Execute bulk dataset or repo updates through RUBE_REMOTE_WORKBENCH using run_composio_tool() calls
Build an agent that adapts to schema changes by always searching tools at the start of each workflow
Fetch specific tool schema with RUBE_GET_TOOL_SCHEMAS to validate complex payloads before execution

FAQ

Do I need API keys to connect to Rube MCP?

No. Add https://rube.app/mcp as an MCP server in your client configuration; no API keys are required for the MCP endpoint.

What if RUBE_MANAGE_CONNECTIONS returns a non-ACTIVE status?

Follow the auth link returned by the call to complete setup, then recheck until the toolkit shows ACTIVE before running tools.