skills.rest
Norfolk-Group
Norfolk-GroupOFFICIAL
Explore all skills by this author →
GitHub

marcela-whatsapp

Build and debug a WhatsApp AI chatbot using Gemini 2.5 Flash on Vercel serverless.

Updated Mar 17, 2026
Search Tags:#serverless#vercel#whatsapp#gemini#chatbot#twilio#twiml
One-click install
npx skills add https://github.com/Norfolk-Group/marcela-norfolk-ai --skill marcela-whatsapp-norfolk-group
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: marcela-whatsapp
Source: https://github.com/Norfolk-Group/marcela-norfolk-ai/tree/main/skills/marcela-whatsapp
Command: npx skills add https://github.com/Norfolk-Group/marcela-norfolk-ai --skill marcela-whatsapp-norfolk-group

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests.

What problem does it solve? Maintaining a WhatsApp AI chatbot on Vercel serverless involves tricky constraints: Python SDK dependency conflicts, Meta-level messaging errors, cold-start memory loss, and webhook debugging. This Skill provides the architecture knowledge, constraints, and debugging checklist needed to build and maintain the Marcela WhatsApp agent without rediscovering these pitfalls. ## Core Features & Use Cases - Serverless Architecture Guidance: Documents the Vercel entry point, direct HTTP calls to Gemini 2.5 Flash (no SDK), and Twilio TwiML inline responses. - Group Chat Trigger System: Implements @marcela mentions, /ask, /quick, and /translate commands with distinct response behaviors. - Debugging Checklist: Maps Twilio error codes (63112, 11200) to root causes and fixes, plus health-check and log inspection steps. - Use Case: A developer sees Twilio error 63112 in message logs and uses this Skill to learn it is a Meta/WABA-level block requiring a fix in Meta Business Suite, not a code change. ## Quick Start Use the marcela-whatsapp skill to diagnose why my Twilio WhatsApp webhook is returning error 11200 on the Vercel deployment.

Frequently Asked Questions about marcela-whatsapp

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

FAQPage Schema
How do I build a WhatsApp AI chatbot with Gemini on Vercel?▼

Deploy a Vercel serverless function that receives Twilio WhatsApp webhooks, calls the Gemini 2.5 Flash API via direct HTTP requests, and replies with TwiML inline responses. Avoid heavy Python SDKs, which cause dependency conflicts on Vercel.

How to handle group chat triggers in a Twilio WhatsApp bot?▼

Parse incoming message text for triggers like @marcela, /ask, /quick, or /translate before generating a response. Each trigger maps to a behavior: normal reply, ultra-short 1-3 sentence reply, or translation. In direct messages, the bot always responds.

Why does Twilio WhatsApp error 63112 occur?▼

Error 63112 is a Meta/WABA-level block, meaning Meta disabled the WhatsApp Business Account. It cannot be fixed with code or TwiML changes; resolve it in Meta Business Suite.

Can I use the Twilio Python SDK on Vercel serverless?▼

No. The Twilio SDK and Anthropic SDK both cause dependency conflicts on Vercel. Use the requests library for direct HTTP calls to the Gemini and Twilio APIs instead.

What are the limitations of a serverless WhatsApp chatbot?▼

Conversation history is stored in memory and resets on cold start, which is acceptable for serverless deployments. WhatsApp messages are also truncated to 1500 characters, so long responses must be split or shortened.

Related Skills

Explore More Software Engineering Skills→
openaiopenai
5.3k

twilio-whatsapp-manage-senders

Registers and manages WhatsApp Business senders via Twilio's Channels Senders API.

Official
Intermediate
DMT123DMT123

logs

Retrieve and display Vercel deployment logs for diagnosing issues.

Community
Basic
project-axproject-ax
5

provider-storage

Manage AI agent persistent storage including queues, conversations, sessions, and documents via database backend.

Official
Advanced
cpfcoachingcpfcoaching

gcp-cloud-run

Deploys serverless apps to Google Cloud Platform with configurable settings.

Community
Advanced