Open-Source Skill to Strip AI Slop and the 25/50/25 Rule for Writing

ArticlePeter YangTool

Peter Yang has open-sourced an AI skill called /no-ai-slop for harnesses like Claude Code and Codex. The tool detects and removes over 20 repetitive patterns commonly produced by generative models. Alongside the release, Yang outlines a 25/50/25 writing process to retain editorial control.

Key points

  1. Open-source skill /no-ai-slop detects, removes, or parodies over 20 distinct AI writing patterns in tools like Codex and Claude Code.
  2. Filters out recurring tropes including binary contrasts ('It’s not X. It’s Y.'), throat-clearing openers, dramatic fragments, and fake-profound conclusions present even in models like Fable 5 and GPT-5.6.
  3. The 25/50/25 workflow: the first 25% (ideation and rough drafting) and final 25% (line-by-line manual polish) are done without AI, using models only for the middle 50%.
  4. While automated slop can drive engagement metrics, Yang argues it destroys trust with discerning audiences.

Why it matters

Generative text often defaults to predictable, hollow rhetoric. For professionals using AI for writing or coding, maintaining distinctive voice and credibility requires active counter-measures against model clichés and strict personal validation at the start and finish of production.

Analysis

Yang provides a concrete taxonomy of the stylistic tells that undermine AI-generated content. Rather than advocating complete manual writing or total automation, his 25/50/25 framework positions LLMs purely as intermediate editing engines. The approach acknowledges the cognitive friction of manual work while emphasizing that trust is lost when readers encounter unedited synthetic text.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • X post:Meng To

    no-ai-slop: Skill removes repetitive AI writing patterns

    Meng To shares a workflow to counter generic AI writing, highlighting Peter Yang's open-source repository 'no-ai-slop', which strips more than 20 repetitive LLM clichés and robotic phrases from text.

    1.8kbookmarks126.6kviews

    AI & LLMs· Tool

  • Repository:petergyang/no-ai-slop

    no-ai-slop: Agent Skill to Strip Formulaic AI Phrasing

    The open-source project no-ai-slop detects and removes over 20 stereotypical patterns of AI writing without flattening the author's individual voice.

    7kstarsPython

    AI & LLMs· Tool

  • Link:Peter G. Yang

    No AI Slop: An Agent Skill for Eliminating AI Writing Patterns

    Peter G. Yang has released an agent skill designed to identify and remove AI cliches from writing. It acts as an editor to make drafts clearer and more engaging while preserving the author's distinctive voice.

    AI & LLMs· Tool

  • X post:Ren

    no-ai-slop: Tool to Remove AI-Generated Writing Habits

    An X post highlights the open-source project no-ai-slop, designed to strip characteristic AI writing patterns from articles. The repository gathered more than 7,700 GitHub stars within two months.

    777bookmarks33.6kviews

    AI & LLMs· Tool

  • X post:Juampi

    Ranked: The Most Popular Anti-Slop Skills for AI Workflows

    Juampi compiled a top-ten ranking of popular 'anti-slop' skills available on skills.sh. These community-built skills help remove generic AI writing patterns, excessive em dashes, forced metaphors, and redundant examples from LLM outputs.

    7.3kbookmarks590.5kviews

    AI & LLMs· Resource

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.