Tweet Draft Reviewer

brianrwagner/ai-marketing-claude-code-skills

Reviews your tweet drafts against 8 voice rules that catch the stuff that makes content sound like a chatbot wrote it. Things like "I" openers, AI cliché words (delve, revolutionize), weak question hooks, and vague claims with no numbers. You paste a draft or point it at a folder, it scores each rule, gives you a total out of 10, and rewrites anything below 7. The rules are opinionated but specific, which is the point. Built for people who draft in batches and want a second pass that actually has standards instead of just "sounds good to me." Takes about 30 seconds per draft and runs entirely in Claude Code with no external calls.

skills.sh installs: 379
GitHub stars: 455
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add brianrwagner/ai-marketing-claude-code-skills --skill tweet-draft-reviewer --agent claude-code

Installs into .claude/skills of the current project.

Files

Tweet Draft Reviewer

Paste a tweet draft and get a score out of 10, a rule-by-rule breakdown, and a rewrite if the score is below 7. Takes 30 seconds. Saves you from posting something that sounds like a chatbot wrote it.

Built on 8 voice rules distilled from real content analysis — what separates high-engagement tweets from the ones that get skimmed.

How to Use

Single draft:

Review this tweet draft: [paste tweet here]

Batch scan:

Review all tweet drafts in my content/tweet-drafts/ folder.

Skill Instructions (for Claude Code)

When this skill is invoked, follow these phases exactly.

PHASE 1: INTAKE

Determine input mode:

Mode A — Direct paste: User provided draft text inline. Proceed to PHASE 2 with that text.

Mode B — Folder scan: User asked to review drafts folder. Run:

VAULT="${VAULT_PATH:-$(pwd)}"
find "$VAULT/content/tweet-drafts" -name "*.md" 2>/dev/null | while read f; do
  if ! grep -q 'reviewed: true' "$f" 2>/dev/null; then
    echo "UNREVIEWED:$f"
  fi
done

SKILL.md on GitHub