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

sidetracker-automation skill

safe

/sidetracker-automation

This skill automates Sidetracker tasks via Rube MCP, prioritizing tool discovery and current schemas to streamline workflow execution.

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

# Sidetracker Automation via Rube MCP

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

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

## Prerequisites

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

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["sidetracker"]
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 Sidetracker-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `sidetracker` |
| 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 Sidetracker tasks through Composio’s Rube MCP bridge, letting agents discover and run Sidetracker tools programmatically. It enforces a discovery-first pattern so tool schemas and slugs are always current. The skill coordinates connection checks, schema-compliant execution, session reuse, and pagination handling.

How this skill works

The skill first calls RUBE_SEARCH_TOOLS to retrieve current tool slugs, input schemas, recommended execution plans, and pagination tokens. It then verifies an active Sidetracker connection via RUBE_MANAGE_CONNECTIONS and follows returned auth links if needed. Executions are performed with RUBE_MULTI_EXECUTE_TOOL (including a memory object) or bulk runs via RUBE_REMOTE_WORKBENCH, using schema-compliant arguments and session IDs. It also supports fetching full tool schemas with RUBE_GET_TOOL_SCHEMAS when schemaRef is present.

When to use it

Automate routine Sidetracker operations (reports, syncs, imports) from an agent workflow.
Before running any Sidetracker tool to ensure you have the latest schema and tool slug.
When orchestrating multi-step workflows that require session reuse and state across calls.
When you need bulk execution or remote workbench runs for high-volume tasks.
When building integrations that must respect changing tool schemas and connection status.

Best practices

Always call RUBE_SEARCH_TOOLS first; never hardcode tool slugs or argument structures.
Verify Sidetracker connection is ACTIVE via RUBE_MANAGE_CONNECTIONS before executing tools.
Pass a memory object (even {}) in RUBE_MULTI_EXECUTE_TOOL calls and reuse session_id for a workflow.
Use exact field names and types from the search results; validate payloads against returned schemas.
Handle pagination tokens and iterate until complete when search responses are paginated.

Example use cases

Discover available Sidetracker report exporters, then run the correct export tool with schema-compliant args.
Automate a daily data sync: confirm connection ACTIVE, search tools, then execute the sync tool using RUBE_MULTI_EXECUTE_TOOL.
Bulk-run a set of Sidetracker transforms with RUBE_REMOTE_WORKBENCH using run_composio_tool() for high-throughput jobs.
Retrieve full tool schemas via RUBE_GET_TOOL_SCHEMAS before constructing complex payloads or validations.
Interactive agent flow that prompts user for parameters, searches tools, and executes the chosen Sidetracker operation.

FAQ

What is the first call I must make when using this skill?

Always call RUBE_SEARCH_TOOLS to fetch the current tool list and input schemas before any other action.

What if RUBE_MANAGE_CONNECTIONS shows the toolkit is not active?

Follow the auth link returned by RUBE_MANAGE_CONNECTIONS to complete connection setup, then re-check until status is ACTIVE.