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

givebutter-automation skill

safe

This skill helps automate Givebutter operations using Composio's toolkit by discovering tool schemas first and ensuring active connection.

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

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

Files (1)

SKILL.md

2.9 KB

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

# Givebutter Automation via Rube MCP

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

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

## Prerequisites

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

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["givebutter"]
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 Givebutter-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `givebutter` |
| 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 Givebutter tasks using Composio’s Givebutter toolkit via a Rube MCP server. It provides a predictable workflow: discover current tools, verify the Givebutter connection, and execute schema-compliant tool calls. Follow the search-first pattern to avoid breaking changes and ensure reliable automation.

How this skill works

The skill uses Rube MCP RPCs to discover available Givebutter tools, manage the Givebutter connection, and run one or more tool invocations. First call RUBE_SEARCH_TOOLS to fetch tool slugs, input schemas, and recommended plans. Then call RUBE_MANAGE_CONNECTIONS to confirm the toolkit connection is ACTIVE. Finally use RUBE_MULTI_EXECUTE_TOOL (or RUBE_REMOTE_WORKBENCH for bulk jobs) with exact schema fields and an included memory object.

When to use it

Automate recurring Givebutter tasks like donor imports, donation reconciliation, or campaign updates
Build agent-driven flows that interact with Givebutter without embedding SDKs or credentials
Execute bulk or batched Givebutter operations through Rube MCP workbench
Orchestrate multi-step workflows that require discovery, connection checks, and schema-driven execution
Integrate Givebutter operations into larger automation pipelines managed by Rube MCP

Best practices

Always call RUBE_SEARCH_TOOLS first to get the current tool slugs and input schemas; never hardcode tool names or fields
Verify Givebutter connection status with RUBE_MANAGE_CONNECTIONS and ensure it shows ACTIVE before executing tools
Supply the memory parameter in RUBE_MULTI_EXECUTE_TOOL calls (use {} if empty) and reuse session IDs for workflow consistency
Respect exact field names and types from the search result schemas to avoid validation errors
Handle pagination tokens: inspect responses and fetch additional pages until complete

Example use cases

Create a nightly donor-sync job that searches for the import tool, verifies connection, and runs a donor import with batch data
Reconcile donations by discovering transaction-retrieval tools, paging through results, and updating accounting systems
Run bulk campaign updates through RUBE_REMOTE_WORKBENCH using run_composio_tool() for parallel operations
Build a conversational agent that asks for user intent, calls RUBE_SEARCH_TOOLS for the selected action, confirms connection, and then executes the chosen Givebutter tool

FAQ

What is the first RPC I should call?

Always call RUBE_SEARCH_TOOLS to retrieve current tool slugs, schemas, and execution guidance before any other call.

What if the Givebutter connection is not ACTIVE?

Use RUBE_MANAGE_CONNECTIONS to get the returned auth link and complete authorization; confirm ACTIVE before running workflows.

Can I hardcode tool slugs and argument shapes?

No. Tool schemas change. Hardcoding leads to failures. Always rely on RUBE_SEARCH_TOOLS results for exact fields and types.