run-whatsapp-automation

Automate WhatsApp group content collection and service orchestration.

9|1|Updated Jun 22, 2026
One-click install
npx skills add https://github.com/sumioshi/whatsapp-automation --skill run-whatsapp-automation
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: run-whatsapp-automation
Source: https://github.com/sumioshi/whatsapp-automation/tree/main/.claude/skills/run-whatsapp-automation
Command: npx skills add https://github.com/sumioshi/whatsapp-automation --skill run-whatsapp-automation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the tedious, error-prone work of manually sifting through dozens of WhatsApp groups to find important messages, lost media, and untranscribed audio, which is a major pain point for anyone managing client communications, support, or team collaborations via WhatsApp.

Core Features & Use Cases

  • Full Service Orchestration: Automates the startup and management of all 5 core components of the WhatsApp group collector: the Baileys collector daemon, Next.js web panel, MLX audio transcriber, message notifier service, and MCP server for AI integration, with support for both local development and 24/7 production deployment.
  • Safe Message Workflows: Enforces strict guardrails for sending, replying, or drafting messages in WhatsApp groups, including mandatory humanization of AI-generated text and client communication tone checks to avoid unprofessional or robotic responses.
  • Use Case: If you run a client support team that uses WhatsApp groups for ticket management, you can use this Skill to automatically collect all group messages, transcribe client audio notes, search for specific issue mentions across all groups, and send polished, natural responses to clients without manually scrolling through hundreds of messages.

Quick Start

Use the run-whatsapp-automation skill to start all WhatsApp collector services, pull a summary of today's messages from your client's support group, and draft a natural response to their latest question.

Frequently Asked Questions about run-whatsapp-automation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate WhatsApp group message collection and audio transcription?

Automating WhatsApp group message collection involves running a Baileys collector daemon to aggregate texts and media, alongside an MLX audio transcriber to process voice notes for AI analysis. This orchestration supports both local development and 24/7 production deployment.

Do I need macOS Apple Silicon to transcribe WhatsApp audio notes locally?

Yes, macOS Apple Silicon is strictly required for local MLX audio transcription of WhatsApp voice notes. Production deployment also requires Node.js 20+, pm2 for process management, and ffmpeg for processing media files.

How to send automated WhatsApp replies without sounding robotic?

To send automated WhatsApp replies without sounding robotic, the system enforces strict guardrails by integrating with humanizer and client communication skills. This ensures mandatory humanization and tone checks are applied to AI-generated text before dispatching.

What is the best way to manage a 24/7 WhatsApp group collector service?

The best way to manage a 24/7 WhatsApp group collector is using pm2 for production process management to orchestrate the Baileys daemon, Next.js web panel, audio transcriber, notifier, and MCP server, ensuring continuous message aggregation and analysis.

Can I search across multiple WhatsApp groups for specific client issues?

Yes, you can search for specific issue mentions across multiple WhatsApp groups by aggregating messages, media, and transcribed audio into a unified system. This collected data is then made accessible for AI-powered search and analysis via the MCP server.

Why does WhatsApp automation require a Next.js web panel and MCP server?

WhatsApp automation requires a Next.js web panel to provide a user interface for managing collected group content, and an MCP server to expose the aggregated messages and transcribed audio for seamless integration with external AI models and analysis tools.