npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

x-algorithm-skill

v1.2.1

Published

Write viral X posts using deep knowledge of the actual recommendation algorithm

Vulnerabilities

Powered byPowered by Snyk
  • 0High
  • 0Medium
  • 0Low

Links

Git

Maintainers

djbuckdjbuck

Keywords

xtwitteralgorithmviralsocial-mediaclaudeclaude-codeskill

Readme

X Algorithm Skill

Write viral X posts using deep knowledge of the actual recommendation algorithm.

This skill gives Claude Code (and other AI tools) detailed knowledge of how X's "For You" feed algorithm works, enabling it to help you write posts optimized for maximum reach.

Installation

npx x-algorithm-skill init

Or install globally:

npm install -g x-algorithm-skill
x-algorithm-skill init

Usage

After installation, use the skill in Claude Code:

Get Writing Guidance

/x-algorithm

Displays an overview of the algorithm and guidance for writing viral posts.

Review a Draft

/x-algorithm review

Here's my draft: [your draft]

Get algorithm-backed feedback on your draft with specific improvements.

What's Inside

The skill teaches Claude about:

  • Scoring Signals: The 19 engagement signals the algorithm predicts (replies, shares, dwell time, etc.) and their relative weights
  • Retrieval & Discovery: How the two-tower neural network finds relevant posts for users
  • Content Structure: Optimal formatting for dwell time and engagement
  • Viral Patterns: 8 proven templates that trigger high-value signals
  • Anti-Patterns: What gets penalized (engagement bait, rage bait, over-posting)
  • Iteration Framework: A systematic checklist for improving drafts

How It Works

X's "For You" feed is powered by:

  1. Phoenix Retrieval: Two-tower neural network that matches post embeddings to user interest embeddings
  2. Phoenix Ranking: Grok transformer that predicts 19 engagement probabilities
  3. Weighted Scoring: Probabilities × weights = final score
  4. Penalties: Out-of-network penalty, author diversity decay, age filtering

This skill encodes all of this into actionable guidance.

The Key Insight

The algorithm doesn't care about "engagement" generically. It cares about specific actions:

  • High-value: Replies, DM shares, copy-link shares, dwell time, follows
  • Medium-value: Likes, retweets, profile clicks
  • Negative: Not interested, mute, block, report

A post with 50 likes and 20 replies scores better than one with 100 likes and 0 replies.

Source

This skill is based on analysis of the open-sourced X recommendation algorithm:

License

MIT