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

piggy-automation skill

safe

/piggy-automation

This skill helps automate Piggy operations via Rube MCP by discovering tools first and validating connections before execution.

npx playbooks add skill composiohq/awesome-claude-skills --skill piggy-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: piggy-automation
description: "Automate Piggy tasks via Rube MCP (Composio). Always search tools first for current schemas."
requires:
  mcp: [rube]
---

# Piggy Automation via Rube MCP

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

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

## Prerequisites

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

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["piggy"]
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 Piggy-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `piggy` |
| 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 Piggy tasks using Composio's Piggy toolkit accessed through Rube MCP. It guides tool discovery, connection management, and safe execution of Piggy operations. The skill enforces always searching tools first to use current schemas and avoid hardcoded arguments.

How this skill works

The skill first calls RUBE_SEARCH_TOOLS to retrieve available Piggy tool slugs, input schemas, and recommended execution plans. It then verifies or establishes a Piggy connection via RUBE_MANAGE_CONNECTIONS and ensures the connection is ACTIVE. Finally it runs one or more tools with RUBE_MULTI_EXECUTE_TOOL (including memory and session handling) or uses RUBE_REMOTE_WORKBENCH for bulk workbench runs.

When to use it

Automate routine Piggy workflows (transactions, reports, reconciliation)
Integrate Piggy operations into larger agent workflows
Run multi-step Piggy tool chains that require schema-aware execution
Operate in environments where tool schemas can change frequently
Perform bulk or remote Piggy operations via a workbench

Best practices

Always call RUBE_SEARCH_TOOLS first; never hardcode tool slugs or argument shapes
Verify Piggy connection state with RUBE_MANAGE_CONNECTIONS and complete any auth flows until status is ACTIVE
Use the exact field names and types from the returned schemas—schema compliance is required
Include a memory parameter (even if empty) in RUBE_MULTI_EXECUTE_TOOL calls
Reuse a session_id for a contiguous workflow; generate a new session_id for separate workflows
Handle pagination tokens when searching tools or fetching long lists

Example use cases

Discover Piggy tools for monthly reconciliation and run the discovered execute steps via RUBE_MULTI_EXECUTE_TOOL
Connect a new Piggy account, follow the returned auth link, confirm ACTIVE, then trigger automated data ingestion
Run a bulk update across many Piggy records using RUBE_REMOTE_WORKBENCH and run_composio_tool()
Embed Piggy operations into a Claude agent flow where the agent searches tools, verifies connection, and executes schema-compliant calls

FAQ

What must I do before executing any Piggy tool?

Always run RUBE_SEARCH_TOOLS to get current tool slugs and schemas, then confirm the Piggy connection shows ACTIVE via RUBE_MANAGE_CONNECTIONS.

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 Rube MCP endpoints.