# tweet-draft-reviewer

Evaluates tweet drafts against eight style benchmarks, rates them out of ten, and rewrites posts scoring under seven.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · ★ 449
- Author: BrianRWagner
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/BrianRWagner/ai-marketing-claude-code-skills/tree/HEAD/tweet-draft-reviewer/SKILL.md
- Updated: 2026-03-19
- HTML: https://affpapa.org/en/nevibecode/skills/tweet-draft-reviewer

## What it does

This skill runs drafts through an eight-point editorial check. It flags generic opening questions, standalone self-referential starters, corporate filler, and robotic phrasing. When a draft scores lower than seven points, the assistant generates an improved rewrite that fixes those weaknesses.

You can inspect a single post directly in the prompt or review multiple markdown notes at once. For batch evaluations, the skill executes a bash script inside `content/tweet-drafts/` to inspect files without the `reviewed: true` flag. No external API keys are required because the evaluation relies entirely on model reasoning.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add BrianRWagner/ai-marketing-claude-code-skills --skill tweet-draft-reviewer -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/tweet-draft-reviewer/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/tweet-draft-reviewer/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add BrianRWagner/ai-marketing-claude-code-skills --skill tweet-draft-reviewer -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add BrianRWagner/ai-marketing-claude-code-skills --skill tweet-draft-reviewer -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install BrianRWagner/ai-marketing-claude-code-skills tweet-draft-reviewer
```

2. **Manually: put the files in place**
- File: `.github/skills/tweet-draft-reviewer/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add BrianRWagner/ai-marketing-claude-code-skills --skill tweet-draft-reviewer -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/BrianRWagner/ai-marketing-claude-code-skills --path tweet-draft-reviewer
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add BrianRWagner/ai-marketing-claude-code-skills --skill tweet-draft-reviewer -a opencode
```

### 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/BrianRWagner/ai-marketing-claude-code-skills/tree/HEAD/tweet-draft-reviewer/SKILL.md

## When to use it
- strip robotic filler words and generic phrasing from posts
- rewrite underperforming drafts that score below seven points
- scan markdown files in bulk using local bash execution
- verify character limits and thread structure

## Example prompts
- Review this post draft: Shipped our real-time database sync engine in 48 hours.
- Inspect unreviewed markdown posts inside `content/tweet-drafts/`.
- Grade this draft against the eight voice benchmarks and rewrite if needed.

## Similar
- [seo-audit](https://affpapa.org/en/nevibecode/skills/coreyhaines31-seo-audit.md) — skill · 238500 installs
- [programmatic-seo](https://affpapa.org/en/nevibecode/skills/coreyhaines31-programmatic-seo.md) — skill · 150800 installs
- [copy-editing](https://affpapa.org/en/nevibecode/skills/coreyhaines31-copy-editing.md) — skill · 149800 installs
- [marketing-ideas](https://affpapa.org/en/nevibecode/skills/coreyhaines31-marketing-ideas.md) — skill · 147400 installs
- [sales-enablement](https://affpapa.org/en/nevibecode/skills/sales-enablement.md) — skill · 119400 installs
- [revops](https://affpapa.org/en/nevibecode/skills/revops.md) — skill · 114000 installs

From the same set: [brianrwagner/ai-marketing-claude-code-skills](https://affpapa.org/en/nevibecode/by/brianrwagner/ai-marketing-claude-code-skills.md) — 23 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