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

agent tool_use skill risk: medium

Cloudpress Rube MCP Automation Guide

Instructs the model to automate Cloudpress operations through Composio's toolkit via Rube MCP, requiring initial calls to RUBE_SEARCH_TOOLS and RUBE_MANAGE_CONNECTIONS before execu…

  • External action: medium

SKILL 1 file

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

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

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

## Prerequisites

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

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["cloudpress"]
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 Cloudpress-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `cloudpress` |
| 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_SEARCH_TOOLS availability
  • active Cloudpress connection via RUBE_MANAGE_CONNECTIONS

OPTIONAL CONTEXT

  • existing session_id

TOOLS REQUIRED

  • RUBE_SEARCH_TOOLS
  • RUBE_MANAGE_CONNECTIONS
  • RUBE_MULTI_EXECUTE_TOOL
  • RUBE_REMOTE_WORKBENCH
  • RUBE_GET_TOOL_SCHEMAS

ROLES & RULES

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

EXPECTED OUTPUT

Format
markdown
Constraints
  • always search tools first
  • verify active connection before execution
  • reuse session IDs within workflow

SUCCESS CRITERIA

  • Verify Rube MCP connection before use
  • Maintain ACTIVE Cloudpress connection status
  • Follow core workflow pattern of discover then check then execute
  • Comply with discovered tool schemas

FAILURE MODES

  • May skip RUBE_SEARCH_TOOLS and hardcode outdated tool slugs
  • May attempt execution without confirming ACTIVE connection
  • May omit memory parameter or reuse stale session IDs

EXAMPLES

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

CAVEATS

Dependencies
  • Rube MCP must be connected
  • Active Cloudpress connection via RUBE_MANAGE_CONNECTIONS
  • RUBE_SEARCH_TOOLS available
Missing context
  • Concrete example of a full end-to-end task (e.g., publish post)
  • Client environment or MCP client configuration details
Ambiguities
  • Tool call examples use pseudo-code without specifying exact JSON or function-call syntax
  • 'generate_id: true' and session handling mechanics are not fully defined

QUALITY

OVERALL
0.76
CLARITY
0.78
SPECIFICITY
0.72
REUSABILITY
0.85
COMPLETENESS
0.68

IMPROVEMENT SUGGESTIONS

  • Replace the generic 'your specific Cloudpress task' placeholder with two complete worked examples
  • Add an 'Error handling' subsection covering common failure modes and recovery steps

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