home / skills / composiohq / awesome-claude-skills / ragic-automation

ragic-automation skill

safe

/ragic-automation

This skill automates Ragic tasks via Rube MCP, discovering current tool schemas first to ensure up-to-date execution.

npx playbooks add skill composiohq/awesome-claude-skills --skill ragic-automation

Review the files below or copy the command above to add this skill to your agents.

Files (1)

SKILL.md

2.8 KB

---
name: ragic-automation
description: "Automate Ragic tasks via Rube MCP (Composio). Always search tools first for current schemas."
requires:
  mcp: [rube]
---

# Ragic Automation via Rube MCP

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

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

## Prerequisites

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

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["ragic"]
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 Ragic-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `ragic` |
| 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)*

Overview

This skill automates Ragic operations by orchestrating Composio’s Ragic toolkit through Rube MCP. It directs discovery of current tool schemas, manages Ragic connections, and executes composable tool calls to perform reads, writes, and bulk operations reliably. The workflow enforces search-first and connection-check patterns to avoid schema drift and runtime errors.

How this skill works

First, it queries Rube MCP with RUBE_SEARCH_TOOLS to retrieve live tool slugs, input schemas, and recommended execution plans. Next it verifies or activates the Ragic connection via RUBE_MANAGE_CONNECTIONS. Finally it runs the desired operations with RUBE_MULTI_EXECUTE_TOOL or RUBE_REMOTE_WORKBENCH, passing schema-compliant arguments and a session id and memory object for state management.

When to use it

Automate record creation, updates, or queries in Ragic from external workflows
Run bulk imports or batch operations against Ragic forms
Integrate Ragic with other systems via composable MCP tool calls
Execute scheduled or event-driven Ragic tasks with consistent schema validation
Perform multi-step workflows that require session-scoped state and pagination handling

Best practices

Always call RUBE_SEARCH_TOOLS before using any tool—schemas change frequently
Ensure RUBE_MANAGE_CONNECTIONS reports ACTIVE for the ragic toolkit before executing tools
Pass exact field names and types returned by the search results; do not hardcode payloads
Include a memory object in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({}), and reuse session IDs within a workflow
Handle pagination tokens in responses and loop until completion; generate new session IDs for new workflows

Example use cases

Bulk-import customer records into multiple Ragic sheets using RUBE_REMOTE_WORKBENCH run_composio_tool()
Update invoice statuses across forms by discovering the update tool, verifying connection, and executing RUBE_MULTI_EXECUTE_TOOL
Build a sync job that queries changed records from Ragic and sends them to another service, handling pagination and retries
Create an automated approval workflow that opens a session, runs a sequence of Ragic tool calls, and stores state in memory for follow-up actions

FAQ

Do I need API keys to use Rube MCP?

No API keys are required; add https://rube.app/mcp as an MCP server in your client configuration and use the MCP endpoints.

What happens if a tool schema changes?

Always run RUBE_SEARCH_TOOLS before executing work to get the current schema and recommended execution plan; this prevents mismatched arguments and failures.