Do I need API keys to use this skill?

No. Get RUBE MCP via https://rube.app/mcp and you do not need API keys to use the tool endpoints.

Why should I always search tools first?

Tool schemas change over time; always fetch current slugs and argument schemas to avoid failures and incompatibilities.

How should I manage sessions and memory?

Reuse a session_id within a workflow; generate new session_ids for new workflows and include a memory object in every RUBE_MULTI_EXECUTE_TOOL call.

project-bubble-automation

Scanned

npx machina-cli add skill ComposioHQ/awesome-claude-skills/project-bubble-automation --openclaw

Files (1)

SKILL.md

3.0 KB

Project Bubble Automation via Rube MCP

Automate Project Bubble operations through Composio's Project Bubble toolkit via Rube MCP.

Toolkit docs: composio.dev/toolkits/project_bubble

Prerequisites

Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
Active Project Bubble connection via RUBE_MANAGE_CONNECTIONS with toolkit project_bubble
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.

Verify Rube MCP is available by confirming RUBE_SEARCH_TOOLS responds
Call RUBE_MANAGE_CONNECTIONS with toolkit project_bubble
If connection is not ACTIVE, follow the returned auth link to complete setup
Confirm connection status shows ACTIVE before running any workflows

Tool Discovery

Always discover available tools before executing workflows:

RUBE_SEARCH_TOOLS
queries: [{use_case: "Project Bubble 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 Project Bubble task"}]
session: {id: "existing_session_id"}

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["project_bubble"]
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 Project Bubble-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `project_bubble`
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

Source

git clone https://github.com/ComposioHQ/awesome-claude-skills/blob/master/composio-skills/project-bubble-automation/SKILL.md

View on GitHub

Overview

Automate Project Bubble operations using Composio's project_bubble toolkit through Rube MCP. Always search tools first to fetch current schemas, then ensure an ACTIVE connection before executing the discovered tool slugs.

How This Skill Works

First, discover available Project Bubble tools with RUBE_SEARCH_TOOLS. Next, verify or establish a connection to the project_bubble toolkit using RUBE_MANAGE_CONNECTIONS. Finally, execute the selected tool with RUBE_MULTI_EXECUTE_TOOL using the discovered slug and required arguments, including a memory payload and a session_id; reuse the session_id within a workflow and refresh for new workflows.

When to Use It

Automate routine Project Bubble tasks (create/update items) by discovering and running toolkit tools.
When tool schemas change, fetch current slugs and arguments via RUBE_SEARCH_TOOLS before execution.
Before running workflows, verify the ACTIVE connection to the project_bubble toolkit with RUBE_MANAGE_CONNECTIONS.
Chain multiple tool calls in one flow using RUBE_MULTI_EXECUTE_TOOL and reuse a session_id across the workflow.
Perform bulk or batch operations using RUBE_REMOTE_WORKBENCH and run_composio_tool for scalable Project Bubble tasks.

Quick Start

Step 1: Add RUBE MCP server (https://rube.app/mcp) to your client configuration.
Step 2: Run RUBE_SEARCH_TOOLS to verify available Project Bubble tools and schemas.
Step 3: Run RUBE_MANAGE_CONNECTIONS for toolkit project_bubble, then execute a tool with RUBE_MULTI_EXECUTE_TOOL using the discovered slug, including memory and a session_id.

Best Practices

Always search first to fetch the latest tool schemas; avoid hardcoding slugs or arguments.
Check that the toolkit connection is ACTIVE (RUBE_MANAGE_CONNECTIONS) before executing tools.
Use exact field names and types from the tool schemas returned by RUBE_SEARCH_TOOLS.
Include the memory parameter in every RUBE_MULTI_EXECUTE_TOOL call, even if empty ({}).
Reuse session IDs within a workflow and generate new ones for new workflows; manage pagination tokens if returned.

Example Use Cases

Discover a Project Bubble operation and execute a tool slug to create a new Bubble task with proper arguments.
Connect to the project_bubble toolkit, then update a Bubble record using the appropriate tool slug from the discovery results.
Fetch full tool schemas with RUBE_GET_TOOL_SCHEMAS for a new operation before integrating it into a workflow.
Chain several actions in a single flow by using RUBE_MULTI_EXECUTE_TOOL with a shared session_id and memory payload.
Run multiple Bubble actions in bulk via RUBE_REMOTE_WORKBENCH and run_composio_tool for batch processing.

Frequently Asked Questions

Add this skill to your agents