agentleFS
nirholasnirholas/XActions/skills/notifications-management/SKILL.md

notifications-management

Skill648 starsChanged 9 months agoApache-2.0View on GitHub

Manages X/Twitter notifications including filtering by type, bulk management, notification scraping, and automated notification handling. Use when users want to manage, filter, scrape, or process X notifications in bulk.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run src/notificationManager.js to filter for mentions

    line 72
  2. Very specific:

    Use src/engagementLeaderboard.js to cross-reference top engagers

    line 75
  3. Very specific:

    Run src/welcomeNewFollowers.js to detect new followers

    line 78

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Notifications Management

Browser console script for managing and filtering X/Twitter notifications.

Script Selection

GoalFileNavigate to
Filter and manage notificationssrc/notificationManager.jsx.com/notifications
Scrape notification datascripts/scrapeNotifications.jsx.com/notifications
Welcome new followerssrc/welcomeNewFollowers.jsx.com/USERNAME/followers

Notification Manager

File: src/notificationManager.js

Manages X notifications: filter by type (mentions, likes, reposts, follows, replies), mark as read, and track notification activity.

How to Use

  1. Navigate to x.com/notifications
  2. Open DevTools (F12) -> Console
  3. Paste the script -> Enter

Configuration

const CONFIG = {
  filterTypes: ['mentions', 'likes', 'reposts', 'follows'],
  markAsRead: true,
  scrollToLoadMore: true,
  maxNotifications: 200,
  actionDelay: 1000,
};

Features

  • Filter notifications by type
  • Count notifications by category
  • Scrape notification content with author and timestamp
  • Export notification data as JSON
  • Identify most-engaged users from notifications

Notification Scraper

File: scripts/scrapeNotifications.js

Standalone scraper that exports all visible notifications as structured JSON with author, type, content, and timestamp.

DOM Selectors

ElementSelector
Notification cells[data-testid="notification"]
Toggle switch[data-testid="settingsSwitch"]
Notifications taba[href="/notifications"]
Mentions taba[href="/notifications/mentions"]
Notification text[data-testid="notification"] [dir="auto"]

Strategy Guide

Identifying engagement opportunities

  1. Run src/notificationManager.js to filter for mentions
  2. Identify high-value mentions (verified users, large accounts)
  3. Prioritize replies to mentions from users with 1000+ followers
  4. Use src/engagementLeaderboard.js to cross-reference top engagers

Automated new follower pipeline

  1. Run src/welcomeNewFollowers.js to detect new followers
  2. Review generated welcome message templates
  3. Customize messages per follower based on their bio/niche

Notes

  • Notifications page loads in batches — script scrolls to collect more
  • Rate limit: process with 1-2s delays between actions
  • Navigate to the Notifications tab before running
  • Mentions tab shows only @mentions for easier filtering

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.