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

wati-automation skill

safe

/wati-automation

This skill automates Wati tasks via Composio MCP, ensuring tools are discovered first and connections verified for reliable workflows.

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

# Wati Automation via Rube MCP

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

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

## Prerequisites

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

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["wati"]
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 Wati-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `wati` |
| 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 Wati tasks through Composio's Wati toolkit using the Rube MCP control plane. It provides a clear pattern for discovering tools, validating connections, and executing toolkit calls reliably. The skill enforces live schema discovery so calls remain compatible with changing tool interfaces.

How this skill works

Before any action it calls RUBE_SEARCH_TOOLS to retrieve current tool slugs, input schemas, and recommended execution plans. It verifies and activates the Wati connection via RUBE_MANAGE_CONNECTIONS, then runs actions through RUBE_MULTI_EXECUTE_TOOL (or RUBE_REMOTE_WORKBENCH for bulk jobs) using schema-compliant arguments and a session context. The workflow always includes memory and handles pagination and session reuse as returned by Rube.

When to use it

Automate sending messages, templates, and campaigns via Wati
Perform contact management or bulk updates against Wati from an agent workflow
Orchestrate multi-step Wati operations that require tool discovery and session state
Run repeated or scheduled Wati tasks where schema drift is possible
Execute bulk operations using the remote workbench for higher throughput

Best practices

Always call RUBE_SEARCH_TOOLS first; do not hardcode tool slugs or argument shapes
Confirm toolkit connection status with RUBE_MANAGE_CONNECTIONS and finish any auth flow until ACTIVE
Pass exact field names and types from the returned schemas; validate payloads before execute
Include an explicit memory object (even {}) in RUBE_MULTI_EXECUTE_TOOL calls
Reuse session IDs for a logical workflow and generate new sessions for separate workflows
Check for pagination tokens and fetch until responses are complete

Example use cases

Discover the latest Wati send-message tool, then send templated messages to a contact list
Validate and complete an incomplete Wati connection flow via returned auth link, then run a campaign
Bulk-update contact metadata using RUBE_REMOTE_WORKBENCH with run_composio_tool()
Query tool schemas with RUBE_GET_TOOL_SCHEMAS to build a UI that maps form fields to live Wati inputs
Create an automated workflow that checks schema changes before each deployment to prevent runtime failures

FAQ

What if RUBE_SEARCH_TOOLS returns a different schema than my last run?

Treat the returned schema as authoritative: adapt argument shapes to the new schema or re-run discovery and update payload generation before executing tools.

Do I need API keys to connect to Rube MCP?

No API keys are required; add the MCP server endpoint (https://rube.app/mcp) in your client configuration and use RUBE_MANAGE_CONNECTIONS to establish the toolkit connection.

Can I run bulk jobs?

Yes—use RUBE_REMOTE_WORKBENCH with run_composio_tool() for bulk or long-running operations and follow pagination and memory patterns.