Skip to main content
NEW · APP STORE Now on iOS · macOS · iPad Android & Windows soon GET IT
Prompts Cats Toolkit Automation via Rube MCP

agent operations skill risk: medium

Cats Toolkit Automation via Rube MCP

The prompt provides step-by-step instructions for automating Cats operations through Composio's Cats toolkit using Rube MCP functions such as RUBE_SEARCH_TOOLS, RUBE_MANAGE_CONNECT…

  • Policy sensitive
  • Human review
  • External action: high

SKILL 1 file

SKILL.md
---
name: cats-automation
description: "Automate Cats tasks via Rube MCP (Composio). Always search tools first for current schemas."
---
# 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)*

REQUIRED CONTEXT

  • Rube MCP connection status
  • Cats toolkit connection via RUBE_MANAGE_CONNECTIONS

OPTIONAL CONTEXT

  • specific Cats task use case
  • existing session_id

TOOLS REQUIRED

  • RUBE_SEARCH_TOOLS
  • RUBE_MANAGE_CONNECTIONS
  • RUBE_MULTI_EXECUTE_TOOL
  • RUBE_GET_TOOL_SCHEMAS
  • RUBE_REMOTE_WORKBENCH

ROLES & RULES

  1. Always search tools first for current schemas.
  2. Always call RUBE_SEARCH_TOOLS first to get current tool schemas.
  3. Always discover available tools before executing workflows.
  4. Never hardcode tool slugs or arguments without calling RUBE_SEARCH_TOOLS.
  5. Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE status before executing tools.
  6. Use exact field names and types from the search results.
  7. Always include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty.
  8. Reuse session IDs within a workflow.
  9. Generate new session IDs for new workflows.
  10. Check responses for pagination tokens and continue fetching until complete.

EXPECTED OUTPUT

Format
plain_text
Constraints
  • always call RUBE_SEARCH_TOOLS first
  • verify ACTIVE connection before execution
  • use exact schemas from search results
  • include memory parameter in execute calls

SUCCESS CRITERIA

  • Verify Rube MCP is available by confirming RUBE_SEARCH_TOOLS responds.
  • Confirm connection status shows ACTIVE before running any workflows.

FAILURE MODES

  • Hardcode tool slugs or arguments without calling RUBE_SEARCH_TOOLS.
  • Execute tools before verifying ACTIVE connection status.
  • Omit the memory parameter from RUBE_MULTI_EXECUTE_TOOL calls.
  • Fail to reuse session IDs within a workflow.

EXAMPLES

Includes multiple example calls to RUBE_SEARCH_TOOLS, RUBE_MANAGE_CONNECTIONS, and RUBE_MULTI_EXECUTE_TOOL with sample arguments and session handling.

CAVEATS

Dependencies
  • Rube MCP must be connected (RUBE_SEARCH_TOOLS available).
  • Active Cats connection via RUBE_MANAGE_CONNECTIONS with toolkit cats.
Missing context
  • Target user or agent type expected to follow the prompt
  • Concrete example of a full end-to-end task execution
Ambiguities
  • Unclear what 'Cats' toolkit specifically contains or its domain (e.g., literal cats vs. acronym).
  • Function call syntax shown as pseudo-code without exact expected format or client.

QUALITY

OVERALL
0.77
CLARITY
0.82
SPECIFICITY
0.78
REUSABILITY
0.71
COMPLETENESS
0.80

IMPROVEMENT SUGGESTIONS

  • Replace the placeholder 'your specific Cats task' with 2-3 concrete use-case examples.
  • Add a minimal complete example showing one full RUBE_SEARCH_TOOLS → RUBE_MULTI_EXECUTE_TOOL sequence.

USAGE

Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.

MORE FOR AGENT