Whatsapp Outreach

Community

kevinbadi

whatsapp-outreach

Send WhatsApp messages to Samoan businesses via Playwright + WhatsApp Web and track delivery

Overview

Publisher	kevinbadi
Repository	`ai-os-skills`
Skill name	`whatsapp-outreach`
Stars	73
Forks	29
Bundled files	2
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
2 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by kevinbadi on GitHub. Read the source before you install it.

Installation

Install the Whatsapp Outreach AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/kevinbadi/ai-os-skills/tree/main/whatsapp-outreach
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/kevinbadi/ai-os-skills.git /tmp/ai-os-skills
mkdir -p .claude/skills
cp -r /tmp/ai-os-skills/whatsapp-outreach .claude/skills/whatsapp-outreach

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Whatsapp Outreach in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Whatsapp Outreach on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Whatsapp Outreach is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

What It Does

Normalizes Samoan phone numbers from business_leads to E.164 format (+685XXXXX)
Sends WhatsApp messages via Playwright browser automation on web.whatsapp.com
Uses https://web.whatsapp.com/send?phone=...&text=... URL scheme (works for numbers not in contacts)
Rate-limited with configurable daily limits, batch sizes, and human-like jittered delays
Filters by category, island, priority
Detects "not on WhatsApp" errors and marks as failed

Setup

1. First-Run QR Login

On first run (no cookies/whatsapp-web.json), the script opens a visible browser to WhatsApp Web. Scan the QR code with your phone's WhatsApp app. Cookies are saved automatically.

bash
# First run — will open browser for QR scan
node skills/whatsapp-outreach/scripts/whatsapp-outreach.js --limit 1

To re-authenticate, delete the cookie file and run again:

bash
rm cookies/whatsapp-web.json
node skills/whatsapp-outreach/scripts/whatsapp-outreach.js --limit 1

2. Environment Variables

Add to .env:


WA_DELAY_BETWEEN_MESSAGES=12000
WA_BATCH_SIZE=25
WA_DAILY_LIMIT=50

3. Prerequisites

Clawdbot CDP browser running (clawdbot browser start --profile clawd --headless) — script auto-starts it if needed
WhatsApp account linked on your phone
Playwright installed (npm install)

How to Run

Step 1: Normalize phone numbers

bash
# Preview which leads have valid Samoan mobile numbers
node skills/whatsapp-outreach/scripts/whatsapp-phone-normalize.js --dry-run

# Populate whatsapp_outreach table with normalized numbers
node skills/whatsapp-outreach/scripts/whatsapp-phone-normalize.js

Step 2: Send messages

bash
# Preview targets without sending (no browser opened)
node skills/whatsapp-outreach/scripts/whatsapp-outreach.js --dry-run --limit 5

# Send to 10 high-priority leads on Upolu
node skills/whatsapp-outreach/scripts/whatsapp-outreach.js --limit 10 --priority high --island Upolu

# Send with a specific campaign name
node skills/whatsapp-outreach/scripts/whatsapp-outreach.js --campaign samoa_tourism_q1 --limit 25

CLI Options

whatsapp-phone-normalize.js

Flag	Default	Description
--dry-run	false	Preview without DB writes
--limit N	all	Max leads to process

whatsapp-outreach.js

Flag	Default	Description
--dry-run	false	Preview without sending (no browser)
--limit N	batch size (25)	Max messages to send
--campaign NAME	discover_samoa_intro	Campaign name for tracking
--category CAT	all	Filter by business category
--island ISLAND	all	Filter by island (Upolu, Savai'i)
--priority P	all	Filter by priority (high/medium/low)

Database

Table: whatsapp_outreach (see migrations/003_whatsapp_outreach.sql)

Scripts

scripts/whatsapp-phone-normalize.js — Phone number normalizer
scripts/whatsapp-outreach.js — Main message sender (Playwright + WhatsApp Web)

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Whatsapp Outreach AI skill do?

Send WhatsApp messages to Samoan businesses via Playwright + WhatsApp Web and track delivery

Why use Whatsapp Outreach on TypingMind?

Because you install it once and use it with any model. Whatsapp Outreach is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Whatsapp Outreach in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kevinbadi/ai-os-skills/tree/main/whatsapp-outreach. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Whatsapp Outreach?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Whatsapp Outreach?

As many as you like. As long as a model supports skills, you can use Whatsapp Outreach with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Whatsapp Outreach AI skill free?

It is published on GitHub by kevinbadi. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Claw Score

openclaw

OrganizationPopular

Audit or refresh OpenClaw maturity scorecard docs from root taxonomy, maturity scores, and QA evidence artifacts without using maintainer discrawl data or committed inventory reports.

Clawdtributor

Clawtributor PRs here, last week or another window: discover conversation refs, recheck GitHub, rank by impact.

Control Ui E2e

Use when designing, testing, fixing, or extending the OpenClaw Control UI GUI, including UI stress-test galleries with feedback inputs, Vitest + Playwright end-to-end checks, mocked Gateway flows,…

Discord E2e

Test Discord with Convex-leased QA bots: check credentials without a Gateway, exercise owned messages, or prove OpenClaw replies, files, threads, reactions, streaming, and typing. Distinguish API and…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

What It Does

Setup

1. First-Run QR Login

2. Environment Variables

3. Prerequisites

How to Run

Step 1: Normalize phone numbers

Step 2: Send messages

CLI Options

whatsapp-phone-normalize.js

whatsapp-outreach.js

Database

Scripts

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now