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

goody-automation skill

safe

/goody-automation

This skill automates Goody tasks via Rube MCP, discovering tool schemas first to ensure up-to-date integrations and reliable workflows.

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

# Goody Automation via Rube MCP

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

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

## Prerequisites

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

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["goody"]
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 Goody-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `goody` |
| 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 Goody tasks through Composio's Goody toolkit using the Rube MCP interface. It provides a repeatable workflow for discovering tools, validating connections, and executing composable Goody operations. The skill emphasizes always searching for current tool schemas before running any actions.

How this skill works

The skill first calls RUBE_SEARCH_TOOLS to retrieve available tool slugs, input schemas, execution plans, and pagination tokens. It then verifies an active Goody connection via RUBE_MANAGE_CONNECTIONS and runs actions with RUBE_MULTI_EXECUTE_TOOL or RUBE_REMOTE_WORKBENCH using schema-compliant arguments. Sessions and memory objects are managed explicitly: reuse session IDs for a workflow, include memory (even if empty), and follow pagination until all results are fetched.

When to use it

Automating repetitive Goody tasks or bulk operations
When integrating Goody actions into an agent-driven workflow
Before executing any tool to avoid schema mismatches
When you need to orchestrate multiple composable tools in sequence
When running remote workbench jobs or bulk runs via Composio

Best practices

Always call RUBE_SEARCH_TOOLS first; never hardcode tool slugs or inputs
Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE for the goody toolkit before executing tools
Use exact field names and types from returned schemas to avoid validation errors
Include an explicit memory object in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({})
Reuse session IDs for the same workflow; generate fresh session IDs for new, separate workflows
Check and follow pagination tokens on search responses until complete

Example use cases

Discover current Goody tooling for a specific automation and run a single tool with RUBE_MULTI_EXECUTE_TOOL
Connect and authenticate the Goody toolkit, then confirm ACTIVE status before launching workflows
Execute a bulk batch using RUBE_REMOTE_WORKBENCH with run_composio_tool() to process many items
Build an agent flow that queries available tools, composes a multi-step plan, and executes it while preserving session memory
Fetch full tool schemas with RUBE_GET_TOOL_SCHEMAS to pre-validate complex inputs

FAQ

Do I need API keys to use Rube MCP?

No. Add https://rube.app/mcp as an MCP server in your client configuration; no API keys are required.

What if a tool schema changes mid-workflow?

Always call RUBE_SEARCH_TOOLS before executing each distinct step or workflow. If schema changes are detected, adapt inputs to match the latest schema and revalidate connection status.