SalZaki
UserClaude Code plugin with skills for removing AI-generated tells from writing. Humanize prose without losing your voice.
Categories
Indexed Skills (3)
remove-ai-slop
Use when the user pastes text and asks to make it "less AI", "less ChatGPT", "less slop", "more human", "humanize", "de-slop", "de-AI", "edit out the AI tells", "remove AI giveaways", "clean up this generated copy", or says "this sounds AI-generated". Also use when the user asks to check writing before publishing, or when pasted draft copy shows multiple co-occurring AI tells (em-dash overuse, hedging filler, promotional padding, recap intros, copula avoidance, bullet-and-bold soup, assistant scaffolding) even if the user hasn't named the problem.
detect-ai-slop
Use when the user wants to SEE which AI tells are in a piece of text without rewriting it. Triggers include "flag the AI slop", "where are the tells", "show me what to fix", "detect AI-generated writing", "check this for slop but don't change it", "what would you flag here", or any editorial / pre-publish review that lists issues by location. This is the report lens; it returns located findings (category, severity, the offending text), never a rewrite and never a single 0-10 score. To rewrite instead, use remove-ai-slop.
score-ai-slop
Use when the user wants a slop quality-pass rather than a rewrite or a located list. Triggers include "score this for slop", "how sloppy is this", "give me a slop breakdown", "rate this writing for AI tells", "is this ready to publish", or "slop report by category". Returns a per-category breakdown (deterministic counts plus judged notes) and a publish-readiness read, deliberately without a single 0-10 headline number, because one number invites gaming. For located findings use detect-ai-slop; to rewrite the text use remove-ai-slop.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.