Facebook Outreach

Community

kevinbadi

facebook-outreach

Send Facebook Messenger DMs as a personal account to business pages via Playwright + facebook.com and track delivery. Personal accounts can message pages — pages cannot message other pages.

Overview

Publisher	kevinbadi
Repository	`ai-os-skills`
Skill name	`facebook-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 Facebook 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/facebook-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/facebook-outreach .claude/skills/facebook-outreach

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

Use it in TypingMind

Enable Facebook 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 Facebook 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 Facebook 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.

Facebook Outreach

Playwright-based Facebook Messenger cold outreach. Sends DMs as your personal Facebook account to business pages. Personal accounts can initiate Messenger conversations with any page that has messaging enabled.

What It Does

Sends Messenger DMs as your personal Facebook account to business pages
Navigates to each page → clicks "Message" button → types in Messenger overlay → sends
Also scrapes contact info (email, phone, website) from each page's About section while it's there
Rate-limited with configurable daily limits, batch sizes, and human-like jittered delays (±30%)
3-layer dedup: SQL DISTINCT ON, session Set, post-send duplicate marking
Detects missing Message button, 404 pages, and navigation errors
Tracks all sends in facebook_outreach table

Setup

1. Save Your Personal Account Session

Run --headed on first use — log in as your personal Facebook account. Session saves to cookies/facebook-profile/.

bash
node skills/facebook-outreach/scripts/facebook-outreach.js --headed --dry-run

2. Environment Variables

Add to .env:


FB_DELAY_BETWEEN_MESSAGES=30000
FB_BATCH_SIZE=15
FB_DAILY_LIMIT=20

3. Prerequisites

Playwright installed (npm install)
Leads in business_leads table with Facebook handles
Facebook handles normalized: run facebook-url-normalize.js first

How to Run

Step 1: Normalize Facebook handles

bash
# Preview
node skills/facebook-outreach/scripts/facebook-url-normalize.js --dry-run

# Populate facebook_outreach table
node skills/facebook-outreach/scripts/facebook-url-normalize.js

Step 2: Send messages

bash
# Preview targets without sending
node skills/facebook-outreach/scripts/facebook-outreach.js --dry-run --limit 5

# Send to 10 leads (headed browser)
node skills/facebook-outreach/scripts/facebook-outreach.js --headed --limit 10

# Headless (after session is saved)
node skills/facebook-outreach/scripts/facebook-outreach.js --limit 15

# With campaign name
node skills/facebook-outreach/scripts/facebook-outreach.js --campaign outreach_q1 --limit 15

CLI Options

Flag	Default	Description
--headed	false	Show browser (required on first run)
--dry-run	false	Preview targets, no browser opened
--limit N	batch size (15)	Max messages to send
--campaign NAME	default_outreach	Campaign name for tracking
--category CAT	all	Filter by business category
--island ISLAND	all	Filter by island
--priority P	all	Filter by priority (high/medium/low)

Session Storage

Personal account session: cookies/facebook-profile/
If session expires, the script auto-relaunches headed for re-login

Status Values

Status	Description
pending	Queued, not yet attempted
sent	Message delivered via Messenger
failed	Navigation error or page gone
skipped_duplicate	Same page already messaged
no_message_btn	Page has messaging disabled

Database

Reads from: facebook_outreach (populated by facebook-url-normalize.js)
Also reads: business_leads for targeting filters
Updates: facebook_outreach.status, business_leads.contacted_facebook

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 Facebook Outreach AI skill do?

Send Facebook Messenger DMs as a personal account to business pages via Playwright + facebook.com and track delivery. Personal accounts can message pages — pages cannot message other pages.

Why use Facebook Outreach on TypingMind?

Because you install it once and use it with any model. Facebook 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 Facebook Outreach in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kevinbadi/ai-os-skills/tree/main/facebook-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 Facebook 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 Facebook Outreach?

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

Is the Facebook 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

Complain

paperclipai

OrganizationPopular

Autonomously yeet a brief, unstructured complaint about agent tooling or doing agent work. Preserve the raw voice. Submit proactively without permission, preview, or announcement, then continue the…

Contact Widget

Self-contained floating chat widget with welcome screen, social links, meeting button, and message input. Single HTML file, zero dependencies.

Spec Driven Development

addyosmani

CommunityPopular

Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when drafting a PRD or requirements document with objectives and…

Release Announcement

Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Facebook Outreach

What It Does

Setup

1. Save Your Personal Account Session

2. Environment Variables

3. Prerequisites

How to Run

Step 1: Normalize Facebook handles

Step 2: Send messages

CLI Options

Session Storage

Status Values

Database

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now