NanoSkill
submit your skill

AI Writing Cleanup Skill

byhardikpandya12KGitHub starsGitHub

AI writing cleanup skill that detects and removes common AI patterns like throat-clearing openers and business jargon, resulting in natural human prose.

slopSecurity scan passed
Result preview

Full Demo

See AI-generated writing transformed into clear, direct, and authentic content, with before-and-after scores for Directness, Rhythm, Trust, Authenticity, and Density.

Get started

Run Your First Task

  1. a simple demonstration of the first step in using AI Writing Cleanup Skill
    01

    Install

    Add the skill to your agent.

  2. a simple demonstration of the second step in using AI Writing Cleanup Skill
    02

    Describe Your Writing

    Provide AI-generated text for cleanup and humanization.

  3. a simple demonstration of the third step in using AI Writing Cleanup Skill
    03

    Review Result

    Get AI writing patterns identified and a natural, human-sounding revision.

Install command

$ npx skills add https://github.com/hardikpandya/stop-slop

Installation signals

Installation activity

About

AI writing often suffers from predictable rhythms and telltale phrases that make it feel robotic. Stop Slop is a free skill for Claude that identifies and removes these AI tells, transforming stiff prose into natural, human-sounding text. Whether you're editing blog posts, emails, or marketing copy, it helps your content connect authentically with readers.

Unlike generic grammar tools, Stop Slop targets the specific patterns that mar AI-generated content: throat-clearing openers, business jargon, binary contrasts, dramatic fragmentation, and passive voice. It enforces active voice, varied sentence structure, and directness, then scores your text on five dimensions—directness, rhythm, trust, authenticity, and density—so you can objectively measure improvement.

Integration is simple: add the folder as a skill in Claude Code, upload files to a Claude Project, or drop the rules into any LLM's system prompt. The MIT license means you can use it freely in any workflow. Start cleaning your AI writing in seconds—no installation, no cost.

Key features

What makes it powerful

  • AI writing pattern removal

    Detects and strips banned phrases like throat-clearing openers, emphasis crutches, and business jargon.

  • Structural decluttering

    Eliminates clichéd structures such as binary contrasts, dramatic fragmentation, and passive voice.

  • Sentence-level enforcement

    Applies rules: no Wh- starters, no em dashes, no staccato fragmentation, active voice required.

  • Built-in quality scoring

    Rates text 1-10 on directness, rhythm, trust, authenticity, and density—aim for 35+.

  • Easy LLM integration

    Works with Claude Code, Projects, API, or custom instructions for seamless setup.

Use cases

When to reach for it

  • Clean AI-generated blog posts

    Bloggers humanize AI-written drafts by removing repetitive patterns and improving engagement.

  • Edit AI-drafted business communications

    Professionals refine AI emails, reports, and proposals to sound authentic and professional.

  • Improve marketing copy

    Marketers scrub AI tics from ad copy and landing pages to boost credibility.

  • Refine creative writing

    Authors using AI assistance can apply the skill to eliminate predictable rhythms and make stories more original.

SKILL.md

Stop Slop

A skill for removing AI tells from prose.

What this is

AI writing has patterns. Predictable phrases, structures, rhythms. This skill teaches Claude (or any LLM) to catch and remove them.

Skill Structure

stop-slop/
├── SKILL.md              # Core instructions
├── references/
│   ├── phrases.md        # Phrases to remove
│   ├── structures.md     # Structural patterns to avoid
│   └── examples.md       # Before/after transformations
├── README.md
└── LICENSE

Quick start

Claude Code: Add this folder as a skill.

Claude Projects: Upload SKILL.md and reference files to project knowledge.

Custom instructions: Copy core rules from SKILL.md.

API calls: Include SKILL.md in your system prompt. Reference files load on demand.

What it catches

Banned phrases - Throat-clearing openers, emphasis crutches, business jargon, all adverbs, vague declaratives, meta-commentary. See references/phrases.md.

Structural clichés - Binary contrasts, negative listings, dramatic fragmentation, rhetorical setups, false agency, narrator-from-a-distance voice, passive voice. See references/structures.md.

Sentence-level rules - No Wh- sentence starters, no em dashes, no staccato fragmentation, no lazy extremes, active voice required.

Scoring

Rate 1-10 on each dimension:

DimensionQuestion
DirectnessStatements or announcements?
RhythmVaried or metronomic?
TrustRespects reader intelligence?
AuthenticitySounds human?
DensityAnything cuttable?

Below 35/50: revise.

Author

Hardik Pandya

License

MIT. Use freely, share widely.

FAQ