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

heyreach-automation skill

/heyreach-automation

This skill helps you automate Heyreach operations via Rube MCP by discovering tools first and executing with schema-compliant inputs.

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

# Heyreach Automation via Rube MCP

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

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

## Prerequisites

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

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["heyreach"]
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 Heyreach-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `heyreach` |
| 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 Heyreach operations through Composio's Heyreach toolkit via the Rube MCP interface. It provides a clear discovery-first workflow to find current tool schemas, manage Heyreach connections, and execute composable Heyreach actions reliably. The focus is on safe, schema-compliant automation for production workflows.

How this skill works

The skill always begins by calling RUBE_SEARCH_TOOLS to fetch current tool slugs, input schemas, and execution guidance. It then verifies an active Heyreach connection via RUBE_MANAGE_CONNECTIONS and runs tool operations through RUBE_MULTI_EXECUTE_TOOL (or RUBE_REMOTE_WORKBENCH for bulk jobs), passing memory and session context. It enforces schema compliance, session reuse, and pagination handling to avoid runtime errors.

When to use it

  • Automate recurring Heyreach tasks such as contact updates, campaign triggers, or data exports.
  • Integrate Heyreach actions into larger agent workflows orchestrated by Rube MCP or Composio.
  • Run bulk or batched Heyreach operations safely with schema validation and pagination support.
  • Prototype or productionize Heyreach automation where tool schemas can change frequently.
  • Coordinate multi-step Heyreach operations that require session state and memory between calls.

Best practices

  • Always call RUBE_SEARCH_TOOLS first — never hardcode tool slugs or input shapes.
  • Verify Heyreach connection status with RUBE_MANAGE_CONNECTIONS and ensure it is ACTIVE before executing tools.
  • Use the exact field names and types returned by the search results; schema compliance prevents runtime failures.
  • Include a memory object in every RUBE_MULTI_EXECUTE_TOOL call, even if empty, to satisfy execution requirements.
  • Reuse session_id for related steps; generate a new session for a new workflow to maintain isolation.
  • Check responses for pagination tokens and continue fetching until results are complete.

Example use cases

  • Perform a contact import: search for the import tool, confirm connection, then execute with schema-compliant CSV metadata and mapping fields.
  • Trigger a campaign sequence: discover send/trigger tools, validate templates, and execute multi-step sends within a single session.
  • Export engagement reports: find reporting tools, handle pagination for large datasets, and store results to external storage.
  • Bulk update contacts: use RUBE_REMOTE_WORKBENCH to run run_composio_tool() across many records while tracking progress in memory.

FAQ

Why must I call RUBE_SEARCH_TOOLS every time?

Tool schemas and available slugs can change; searching ensures you have the current inputs and prevents broken executions.

What if RUBE_MANAGE_CONNECTIONS shows the toolkit is not ACTIVE?

Follow the returned auth link to complete setup, then recheck until status reports ACTIVE before running workflows.