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

agent tool_use skill risk: medium

Coassemble Automation via Rube MCP

Provides instructions for automating Coassemble operations through Composio's toolkit via Rube MCP, including prerequisites, setup steps, tool discovery with RUBE_SEARCH_TOOLS, con…

  • External action: high

SKILL 1 file

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

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

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

## Prerequisites

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

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["coassemble"]
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 Coassemble-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `coassemble` |
| 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 Coassemble connection via RUBE_MANAGE_CONNECTIONS

OPTIONAL CONTEXT

  • existing session_id
  • specific Coassemble use case

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 coassemble
  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

  • Search tools before executing any workflow
  • Verify ACTIVE connection status
  • Use schema-compliant arguments from search results
  • Include memory parameter on every execute call
  • Reuse session IDs within workflows

FAILURE MODES

  • Hardcoding tool slugs without first calling RUBE_SEARCH_TOOLS
  • Skipping connection status verification
  • Using incorrect field names or types
  • Omitting the memory parameter on execute calls
  • Failing to handle pagination tokens

EXAMPLES

Includes multiple example RUBE_* tool calls for discovery, connection check, and execution with sample arguments and session handling.

CAVEATS

Dependencies
  • Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
  • Active Coassemble connection via RUBE_MANAGE_CONNECTIONS
Missing context
  • Target client or environment (e.g., Claude Desktop, Cursor) for MCP configuration
Ambiguities
  • Placeholder text 'your specific Coassemble task' left in example without explicit instruction on how to fill it.

QUALITY

OVERALL
0.83
CLARITY
0.82
SPECIFICITY
0.88
REUSABILITY
0.78
COMPLETENESS
0.85

IMPROVEMENT SUGGESTIONS

  • Replace inline placeholder 'your specific Coassemble task' with a clearly marked {{use_case}} variable and add a short 'Variables' section at the top.

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