# twitter-algorithm-optimizer

twitter-algorithm-optimizer — a skill for Claude Code and Cursor that rewrites tweets to match X ranking algorithms so your post reaches more followers and non-followers.

- skill · `type=skill` · Claude Code, Cursor, Codex, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 3785 repo stars
- Author: BuildWithClaude Community
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/davepoon/buildwithclaude/tree/HEAD/plugins/all-skills/skills/twitter-algorithm-optimizer/SKILL.md
- Updated: 2026-10-25
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/twitter-algorithm-optimizer

## What it does

The skill analyzes tweet text against X (Twitter) ranking models: Real-graph predicts follower engagement, SimClusters finds communities with shared interests, TwHIN checks if the topic fits your profile. Then it rewrites the tweet to widen reach: rephrases a statement as a question to get replies, adds niche terminology to trigger SimClusters, removes vague wording that confuses TwHIN categorization. Explicit signals (likes, retweets, replies) weigh more than implicit ones (clicks, dwell time), and blocks or reports cut reach hard. The skill builds on X's open-sourced algorithm code.

Works in Claude Code and Cursor. When rewriting, it keeps your voice but changes structure to fit algorithm signals: adds a debate-starter for discussion, narrows the topic to a single focus, strips words that blur categorization. The skill does not write new tweets from scratch — it only edits your draft. No X API key or platform integration required; it acts as a text editor inside your IDE.

## Install

### Claude Code (native platform)

1. **Plugin marketplace**
In the agent chat (not a shell):
```text
/plugin marketplace add davepoon/buildwithclaude
```
In the agent chat (not a shell):
```text
/plugin install all-skills@buildwithclaude
```
This installs the whole all-skills plugin with all its skills

2. **Skills CLI (Vercel)**
```bash
npx skills add davepoon/buildwithclaude --skill twitter-algorithm-optimizer -a claude-code
```

3. **Manually: put the files in place**
- File: `~/.claude/skills/twitter-algorithm-optimizer/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/twitter-algorithm-optimizer/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add davepoon/buildwithclaude --skill twitter-algorithm-optimizer -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/twitter-algorithm-optimizer/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add davepoon/buildwithclaude --skill twitter-algorithm-optimizer -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/twitter-algorithm-optimizer/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install davepoon/buildwithclaude plugins/all-skills/skills/twitter-algorithm-optimizer
```

2. **Manually: put the files in place**
- File: `.github/skills/twitter-algorithm-optimizer/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add davepoon/buildwithclaude --skill twitter-algorithm-optimizer -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/davepoon/buildwithclaude --path plugins/all-skills/skills/twitter-algorithm-optimizer
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/twitter-algorithm-optimizer/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/davepoon/buildwithclaude/tree/HEAD/plugins/all-skills/skills/twitter-algorithm-optimizer/SKILL.md

## When to use it
- rewrite a tweet so X algorithm shows it to followers more often
- diagnose why a post got low reach and fix the structure
- add reply and retweet triggers aligned with Real-graph and SimClusters models
- remove vague phrasing that stops the algorithm from understanding the topic

## Example prompts
- Break down this tweet against X algorithms and rewrite it for better reach: [text]
- Why did this post underperform? What does X algorithm dislike about it?
- Rework this tweet to trigger SimClusters and get more retweets

## Similar
- [command-viral-tweet](https://affpapa.org/en/nevibecode/plugins/command-viral-tweet.md) — plugin · ★ 2707 repo stars
- [x-twitter-growth](https://affpapa.org/en/nevibecode/skills/x-twitter-growth.md) — skill · 695 installs
- [x-impact-checker](https://affpapa.org/en/nevibecode/skills/x-impact-checker.md) — skill · 219 installs
- [twitter-automation](https://affpapa.org/en/nevibecode/skills/twitter-automation.md) — skill · 1000000 installs
- [reply-and-comment-writer](https://affpapa.org/en/nevibecode/skills/reply-and-comment-writer.md) — skill · 1300 installs
- [twitter](https://affpapa.org/en/nevibecode/skills/twitter.md) — skill · 7900 installs

From the same set: [davepoon/buildwithclaude](https://affpapa.org/en/nevibecode/by/davepoon/buildwithclaude.md) — 235 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
