Do I need API keys to use this skill?

No API keys are required; you add the Rube MCP endpoint and authentication is handled via the MCP workflow.

Why is RUBE_SEARCH_TOOLS important?

Because tool schemas change frequently; searching first ensures you use current tool slugs and argument formats.

What must be included in every RUBE_MULTI_EXECUTE_TOOL call?

Always include the memory parameter, even if it is empty, to preserve workflow state and history.

gigasheet-automation

Scanned

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

Files (1)

SKILL.md

2.9 KB

Gigasheet Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/gigasheet

Prerequisites

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

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["gigasheet"]
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 Gigasheet-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `gigasheet`
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/gigasheet-automation/SKILL.mdView on GitHub

Overview

Automate Gigasheet operations using Composio's Gigasheet toolkit via Rube MCP. This skill emphasizes discovering tool schemas first to adapt to changes and ensure reliableAutomation.

How This Skill Works

Connect to Rube MCP and verify RUBE_SEARCH_TOOLS is available. Ensure an ACTIVE Gigasheet connection via RUBE_MANAGE_CONNECTIONS with the gigsheet toolkit. Discover tools using RUBE_SEARCH_TOOLS, then execute with RUBE_MULTI_EXECUTE_TOOL using the discovered tool slug and the required arguments, always including memory.

When to Use It

Setting up a new Gigasheet workflow and you need the latest tool schemas before proceeding
Automating a specific Gigasheet operation by using a tool slug discovered at runtime
Validating a workflow by confirming the Gigasheet connection remains ACTIVE
Handling schema changes by re-discovering tools prior to execution
Executing multiple Gigasheet actions in a single session using memory and a reusable session_id

Quick Start

Step 1: Verify Rube MCP is accessible and call RUBE_SEARCH_TOOLS to fetch Gigasheet tool schemas
Step 2: Establish or verify an ACTIVE Gigasheet connection with RUBE_MANAGE_CONNECTIONS (toolkit: gigasheet)
Step 3: Execute the desired tool with RUBE_MULTI_EXECUTE_TOOL using the discovered slug and include memory

Best Practices

Always run RUBE_SEARCH_TOOLS first to fetch current tool schemas
Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE before executing any tools
Use exact field names and types from the tool schemas returned by searches
Always include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty
Reuse session IDs within a workflow and generate a new one for new workflows

Example Use Cases

Automate a daily Gigasheet export by discovering the tool slug with RUBE_SEARCH_TOOLS and executing it via RUBE_MULTI_EXECUTE_TOOL in a single session
Update an existing Gigasheet workflow after a schema change by re-discovering tools and re-running the correct slug
Connect to Gigasheet, verify ACTIVE status, then run a batch of tools for bulk sheet processing
Process multiple sheets in a single run using a session_id and memory parameter to chain actions
Use RUBE_REMOTE_WORKBENCH's run_composio_tool() for bulk Gigasheet operations guided by the discovered schemas

Frequently Asked Questions

Add this skill to your agents