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

ynab-automation skill

/ynab-automation

This skill automates Ynab tasks via Rube MCP using Composio toolkit, discovering tool schemas first for current integration options.

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

# Ynab Automation via Rube MCP

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

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

## Prerequisites

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

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["ynab"]
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 Ynab-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `ynab` |
| 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 YNAB (You Need A Budget) operations through Composio’s Ynab toolkit using the Rube MCP orchestration layer. It provides a repeatable pattern to discover tools, verify connections, and run schema-compliant tool executions. The workflow emphasizes always searching for current tool schemas before any execution to avoid breaking changes.

How this skill works

The skill first calls RUBE_SEARCH_TOOLS to fetch available tool slugs, input schemas, and recommended execution plans for Ynab tasks. It then checks or establishes a Ynab connection via RUBE_MANAGE_CONNECTIONS and runs actions using RUBE_MULTI_EXECUTE_TOOL (or RUBE_REMOTE_WORKBENCH for bulk jobs), always passing an explicit memory object and reusing a session ID for the workflow. Responses must be checked for pagination and schema fields must match the returned definitions exactly.

When to use it

  • Automate routine Ynab tasks like syncing accounts, creating/updating transactions, or reconciling budgets.
  • Run bulk or scheduled Ynab operations where manual UI interaction is slow or error-prone.
  • Integrate Ynab actions into broader agent workflows that require transactional budget updates.
  • Build repeatable, auditable financial workflows that rely on Composio’s toolkit orchestration.
  • When you need programmatic access while ensuring you always use the latest tool schema.

Best practices

  • Always call RUBE_SEARCH_TOOLS first to retrieve current tool slugs and input schemas; never hardcode fields or slugs.
  • Verify Ynab connection status with RUBE_MANAGE_CONNECTIONS and follow any returned auth link until status is ACTIVE.
  • Include a memory object (even empty {}) in RUBE_MULTI_EXECUTE_TOOL calls and reuse session IDs for the same workflow.
  • Match input field names and types exactly to the schema returned by RUBE_SEARCH_TOOLS; validate data before executing.
  • Handle pagination tokens in responses and iterate until results are complete; generate new session IDs for distinct workflows.

Example use cases

  • Sync transactions from linked bank accounts into Ynab on a nightly schedule using RUBE_MULTI_EXECUTE_TOOL.
  • Bulk-update category assignments for a set of transactions using RUBE_REMOTE_WORKBENCH run_composio_tool().
  • Create a workflow that checks budget totals and posts corrective transactions when thresholds are exceeded.
  • Onboard a new Ynab connection: search tools, run RUBE_MANAGE_CONNECTIONS, follow auth link, confirm ACTIVE, then run an initial reconciliation.

FAQ

Do I need API keys to use Rube MCP?

No API keys are required for the MCP endpoint; add https://rube.app/mcp to your client configuration and use the Rube MCP methods.

What if a tool schema changes mid-workflow?

Always call RUBE_SEARCH_TOOLS before executing tools in a workflow to fetch the current schema. If a schema changed after discovery, re-run the search and adapt arguments before retrying.