How do I install the Linkedin Notifications skill?

Run npx skillmds@latest add kevinbadi/linkedin-notifications in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Linkedin Notifications safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Linkedin Notifications?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Linkedin Notifications free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Linkedin Notifications?

kevinbadi (@kevinbadi) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Linkedin Notifications by kevinbadi

Name: Linkedin Notifications
Author: kevinbadi

Linkedin Notifications

Check LinkedIn notifications and report new ones via iMessage. Deduplicates against database so only new notifications are reported. Covers connection acceptances, reactions, comments, profile views, mentions, and more.

kevinbadi 650383d 2 files · 12.6 KB Updated Sep 17, 2026

File contents

LinkedIn Notifications Checker

Scrapes LinkedIn notifications page, deduplicates against DB, and outputs new notifications for reporting.

Prerequisites

Chrome with CDP running
Logged into LinkedIn
ws and pg npm packages
DATABASE_URL env var

Quick Usage

node skills/linkedin-notifications/scripts/linkedin-notifications.js

Workflow

Navigate to linkedin.com/notifications/
Scroll to load notifications
Scrape all visible notifications (text, link, time)
Hash each notification, check against linkedin_notifications DB table
Store new ones, skip already-seen
Output JSON summary of new notifications
Navigate away from notifications page

Notification Types Detected

Type	Example
`connection_accepted`	"John Doe accepted your invitation"
`connection_request`	"Jane wants to connect"
`reaction`	"5 people liked your post"
`comment`	"John commented on your post"
`share`	"Jane shared your post"
`mention`	"You were mentioned in a post"
`profile_view`	"3 people viewed your profile"
`endorsement`	"John endorsed you for Python"
`milestone`	"Jane started a new position"
`job`	"New jobs matching your alerts"
`other`	Anything else

Database

Uses linkedin_notifications table:

notification_hash: MD5 of content (dedup key)
notification_type: classified type
actor_name: extracted person name
content: full notification text
link: URL if available
reported: whether it was included in a report

CLI Options

Flag	Default	Description
`--limit`	30	Max notifications to process
`--cdp-port`	18800	Chrome CDP port

---name: linkedin-notificationsdescription: Check LinkedIn notifications and report new ones via iMessage. Deduplicates against database so only new notifications are reported. Covers connection acceptances, reactions, comments, profile views, mentions, and more.---# LinkedIn Notifications CheckerScrapes LinkedIn notifications page, deduplicates against DB, and outputs new notifications for reporting.## Prerequisites- Chrome with CDP running- Logged into LinkedIn- `ws` and `pg` npm packages- `DATABASE_URL` env var## Quick Usage```bashnode skills/linkedin-notifications/scripts/linkedin-notifications.js```## Workflow1. Navigate to linkedin.com/notifications/2. Scroll to load notifications3. Scrape all visible notifications (text, link, time)4. Hash each notification, check against `linkedin_notifications` DB table5. Store new ones, skip already-seen6. Output JSON summary of new notifications7. Navigate away from notifications page## Notification Types Detected| Type | Example ||------|---------|| `connection_accepted` | "John Doe accepted your invitation" || `connection_request` | "Jane wants to connect" || `reaction` | "5 people liked your post" || `comment` | "John commented on your post" || `share` | "Jane shared your post" || `mention` | "You were mentioned in a post" || `profile_view` | "3 people viewed your profile" || `endorsement` | "John endorsed you for Python" || `milestone` | "Jane started a new position" || `job` | "New jobs matching your alerts" || `other` | Anything else |## DatabaseUses `linkedin_notifications` table:- `notification_hash`: MD5 of content (dedup key)- `notification_type`: classified type- `actor_name`: extracted person name- `content`: full notification text- `link`: URL if available- `reported`: whether it was included in a report## CLI Options| Flag | Default | Description ||------|---------|-------------|| `--limit` | 30 | Max notifications to process || `--cdp-port` | 18800 | Chrome CDP port |

Frequently asked questions