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

cats-automation skill

safe

/cats-automation

This skill automates Cats tasks via Rube MCP, discovering tool schemas first to ensure correct execution and reliable workflows.

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

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

Files (1)

SKILL.md

2.8 KB

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

# Cats Automation via Rube MCP

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

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

## Prerequisites

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

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["cats"]
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 Cats-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `cats` |
| 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 Cats toolkit tasks through Composio via the Rube MCP bridge. It guides discovery, connection management, and execution of Cats tools while enforcing live schema checks and session best practices. Use it to run single or bulk Cats operations reliably from an agent workflow.

How this skill works

The skill always begins by calling RUBE_SEARCH_TOOLS to retrieve current tool slugs, input schemas, and execution recommendations. It then verifies or establishes a Cats connection with RUBE_MANAGE_CONNECTIONS and executes tools with RUBE_MULTI_EXECUTE_TOOL, including an explicit memory object and consistent session IDs. It handles pagination and can call RUBE_GET_TOOL_SCHEMAS or RUBE_REMOTE_WORKBENCH for full schemas and bulk runs.

When to use it

Automate routine Cats operations that require external toolkit calls
Run multi-step Cats workflows that must respect live tool schemas
Perform bulk or remote Cats jobs using the remote workbench
Integrate Cats tasks into an agent-driven orchestration pipeline
Run operations that require session continuity and explicit memory handling

Best practices

Always call RUBE_SEARCH_TOOLS before using any tool; tool slugs and schemas change frequently
Verify connection status via RUBE_MANAGE_CONNECTIONS and complete auth flows until ACTIVE
Supply schema-compliant arguments exactly as returned by search results
Include a memory object (even empty) in RUBE_MULTI_EXECUTE_TOOL calls
Reuse a session ID for related operations; generate new session IDs for distinct workflows
Inspect responses for pagination tokens and fetch until complete

Example use cases

Discover available Cats tool endpoints for a given task and generate compliant inputs
Connect an agent to the Cats toolkit and complete an OAuth/auth link flow, then run tests
Execute a multi-tool Cats workflow within one session using RUBE_MULTI_EXECUTE_TOOL
Run large or parallel Cats jobs via RUBE_REMOTE_WORKBENCH and run_composio_tool()
Fetch full tool schemas with RUBE_GET_TOOL_SCHEMAS to validate complex payloads before execution

FAQ

Why must I call RUBE_SEARCH_TOOLS first?

Tool slugs and input schemas can change. Searching first returns live schemas, recommended execution plans, and known pitfalls to avoid errors.

What happens if connection is not ACTIVE?

RUBE_MANAGE_CONNECTIONS returns an auth link or instructions. Complete the auth flow and confirm ACTIVE status before executing tools to prevent failures.