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.
npx skills add https://github.com/brianrwagner/ai-marketing-claude-code-skills --skill tweet-draft-reviewer