Linkedin Connect logo

Linkedin Connect

Community
kevinbadi
linkedin-connect

Send LinkedIn connection requests with personalized messages via browser automation. Uses pre-scraped leads from linkedin_leads table (populated by Apify during onboarding). Trigger when asked to send LinkedIn connections or run LinkedIn outreach.

Overview

Publisherkevinbadi
Repositoryai-os-skills
Skill namelinkedin-connect
Stars
73
Forks
29
Bundled files
2
Links
  • 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 Linkedin Connect AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/kevinbadi/ai-os-skills/tree/main/linkedin-connect
  4. 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.
2

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/linkedin-connect .claude/skills/linkedin-connect
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Linkedin Connect 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 Linkedin Connect 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 Linkedin Connect 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.

LinkedIn Connect

Send personalized LinkedIn connection requests to pre-scraped leads from your database.

How It Works

  1. Onboarding → Apify scrapes LinkedIn profiles based on your targeting → linkedin_leads table
  2. This skill → Reads from linkedin_leads → Sends connection requests via browser automation
  3. Tracking → Marks leads as connection_sent = TRUE → Won't contact twice

Prerequisites

  • Chrome with CDP running (auto-starts via Clawdbot)
  • Logged into LinkedIn (cookies at cookies/linkedin-*.json)
  • DATABASE_URL env var pointing to your Insforge DB
  • Leads in linkedin_leads table (populated by initial scrape or linkedin-profile-scraper skill)

Quick Usage (Recommended)

Send connections to pre-scraped leads

bash
# Send to 20 uncontacted leads from DB
node skills/linkedin-connect/scripts/batch-connect.js --limit 20

# Filter by campaign (e.g. leads from a specific scrape)
node skills/linkedin-connect/scripts/batch-connect.js --campaign "onboarding_initial" --limit 20

# Custom message template
node skills/linkedin-connect/scripts/batch-connect.js --limit 20 \
  --message "Hey {{firstName}}, saw your work at {{company}} — would love to connect!"

# Dry run (preview which leads would be contacted)
node skills/linkedin-connect/scripts/batch-connect.js --limit 20 --dry-run

Message Templates

VariableSource
{{firstName}}First name from DB
{{lastName}}Last name from DB
{{fullName}}Full name
{{company}}current_company from DB
{{headline}}headline from DB
{{title}}current_title from DB

CLI Options

FlagDefaultDescription
--limit20Max connection requests per run
--campaign—Filter leads by campaign_name
--messageDefault templateMessage with {{variables}}
--delay-min8Min seconds between requests
--delay-max15Max seconds between requests
--dry-runfalsePreview leads, don't send
--cdp-port18800Chrome CDP port

Safety

  • Cap at 20-25/day — LinkedIn flags aggressive behavior
  • Random delays between requests (8-15s default)
  • Real browser automation, not API calls
  • Automatically detects weekly invitation limit and stops
  • Leads marked connection_sent = TRUE won't be contacted again

Database Schema

Reads from linkedin_leads table:

sql
SELECT * FROM linkedin_leads 
WHERE connection_sent = FALSE 
ORDER BY created_at DESC 
LIMIT 20;

Updates after each request:

sql
UPDATE linkedin_leads 
SET connection_sent = TRUE, connection_sent_at = NOW() 
WHERE id = $1;

Output

json
{"sent": 15, "skipped": 2, "errors": 0, "hitWeeklyLimit": false}
  • sent — Connection requests successfully sent
  • skipped — Leads skipped (already connected, no connect button, etc.)
  • errors — Failed attempts
  • hitWeeklyLimit — LinkedIn's weekly limit reached, stop processing

Cron Schedule (Recommended)

Run daily with 20 leads max:

0 10 * * * node skills/linkedin-connect/scripts/batch-connect.js --limit 20

Alternative: Single Profile

For one-off connections (not recommended for scale):

bash
node skills/linkedin-connect/scripts/linkedin-connect.js \
  --url "https://www.linkedin.com/in/someone/" \
  --message "Hey, would love to connect!"

Flow Diagram

┌─────────────────────────────────────────────────────────────────┐
│  ONBOARDING                                                      │
│  User fills out LinkedIn targeting (titles, keywords, location)  │
└──────────────────────────┬──────────────────────────────────────┘
                           │
                           ▼
┌─────────────────────────────────────────────────────────────────┐
│  INITIAL SCRAPE (Apify)                                          │
│  harvestapi~linkedin-profile-search → linkedin_leads table       │
└──────────────────────────┬──────────────────────────────────────┘
                           │
                           ▼
┌─────────────────────────────────────────────────────────────────┐
│  LINKEDIN CONNECT (This Skill)                                   │
│  batch-connect.js reads from DB → sends connection requests      │
│  Marks connection_sent = TRUE after each                         │
└──────────────────────────┬──────────────────────────────────────┘
                           │
                           ▼
┌─────────────────────────────────────────────────────────────────┐
│  LINKEDIN MESSAGE AGENT (Optional)                               │
│  Monitors accepted connections → sends follow-up DMs             │
└─────────────────────────────────────────────────────────────────┘

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 Linkedin Connect AI skill do?

Send LinkedIn connection requests with personalized messages via browser automation. Uses pre-scraped leads from linkedin_leads table (populated by Apify during onboarding). Trigger when asked to send LinkedIn connections or run LinkedIn outreach.

Why use Linkedin Connect on TypingMind?

Because you install it once and use it with any model. Linkedin Connect 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 Linkedin Connect in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kevinbadi/ai-os-skills/tree/main/linkedin-connect. 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 Linkedin Connect?

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 Linkedin Connect?

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

Is the Linkedin Connect 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇