no-ai-slop

Edits and audits human-facing prose to remove AI-sounding writing patterns while preserving author voice.

Updated May 19, 2026
One-click install
npx skills add https://github.com/Curcolor/CLAUDEMAX --skill no-ai-slop-curcolor
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: no-ai-slop
Source: https://github.com/Curcolor/CLAUDEMAX/tree/main/skills/no-ai-slop
Command: npx skills add https://github.com/Curcolor/CLAUDEMAX --skill no-ai-slop-curcolor

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Drafts of documentation, READMEs, articles, and messages often contain recognizable AI writing patterns—banned buzzwords, binary contrasts, hollow openers, inflated importance—that make prose sound generic and machine-generated. This Skill edits or audits that prose, removing the slop while preserving the author's personal voice, cadence, and edge. ## Core Features & Use Cases - Minimal-effective editing: Rewrites drafts with the smallest changes needed, cutting 14 cataloged AI patterns (binary contrasts, throat-clearing, rhetorical setups, colon reveals, synonym cycling, fake-profound kickers, em-dash overuse, and more) while protecting distinctive voice traits. - Detection mode: Audits a draft without rewriting it, reporting each named pattern with the exact quoted line and a brief suggested fix—no scores, no AI-authorship guesses. - Banned vocabulary enforcement: Removes prohibited words and filler phrases in both English and Spanish (delve, leverage, robust, streamline, "it's worth noting", etc.). - Use Case: Paste a README draft that reads like AI output and ask for an edit; receive the cleaned draft plus a short "What changed" section explaining every modification. ## Quick Start Paste your draft and ask: edit this README to remove anything that sounds like AI while keeping my voice.

Frequently Asked Questions about no-ai-slop

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I remove AI-sounding phrases from my writing?

Paste your draft and request an edit. The skill applies minimal changes that cut banned words, filler phrases, and 14 cataloged patterns like binary contrasts and hollow openers, then returns the edited draft with a short "What changed" section.

How to detect AI writing patterns without rewriting the text?

Ask for an audit or detection pass. The skill names each pattern found, quotes the exact line, and gives a brief fix suggestion without rewriting, scoring, or guessing whether AI wrote the text.

Does this work for Spanish or bilingual documentation?

Yes. The banned word and filler phrase lists cover both English and Spanish equivalents (delve/profundizar, leverage/aprovechar, streamline/optimizar), and the editing principles apply to prose in either language.

Will editing my draft flatten my personal writing style?

No. The skill first identifies 3-5 voice signals—vocabulary, cadence, humor, uncertainty, digressions—and preserves them. It makes the minimum effective change and leaves strong human sentences untouched rather than polishing everything uniformly.

When should I not use AI-slop detection on text?

Do not apply it to live chat responses from an AI session, since those are not prose a human will read later. It is designed only for files, messages, and documents that someone will read outside the current session.