Stop Slop

A skill for removing AI tells from prose. AI writing has patterns—predictable phrases, structures, and rhythms. Once you notice them, you see them everywhere.

What It Catches

Banned Phrases

Throat-clearing openers — Generic openings that delay the actual content:

• "Certainly!"
• "It is important to note that..."
• "It should be noted that..."
• "It is worth noting that..."
• "In today's fast-paced world..."
• "In the ever-evolving landscape of..."

Emphasis crutches — Overused emphasis patterns:

• "plays a crucial role"
• "is absolutely essential"
• "cannot be overstated"
• "is particularly important"

Business jargon — Empty corporate speak:

• "leverage the power of"
• "dive right in"
• "moving on to"
• "at the end of the day"

Structural Clichés

Binary contrasts — Forced either/or framings:

• "This isn't just X, it's Y"
• "On one hand... on the other hand..."

Dramatic fragmentation — Unnecessary line breaks for emphasis:

• Short sentences after long ones just for effect

Rhetorical setups — Predictable question-answer patterns:

• "So what does this mean?"
• "The answer is..."

Stylistic Habits

Tripling — Lists of three as a pattern:

• Examples, evidence, and expertise
• Fast, flexible, and affordable

Metronomic endings — Sentences that all end the same way

Immediate question-answers — Ask and answer in same paragraph

Scoring

Rate 1-10 on each dimension:

Below 35/50: Revise the content.

Process

When editing content:

1. Scan for banned phrases — Remove throat-clearing openers
2. Fix structural clichés — Break binary contrasts, reduce tripling
3. Check rhythm — Vary sentence length and structure
4. Respect trust — Don't over-explain, don't state obvious
5. Verify authenticity — Does it sound like a human wrote it?
6. Trim density — Cut anything that doesn't add value

What to Remove

• Filler phrases and hedging
• Overused transitions (Furthermore, Moreover, Additionally)
• Artificial formality (due to the fact that, in order to)
• Redundant expressions (each and every, various different)
• Meta-commentary (As mentioned above, This demonstrates...)
• Generic openings (Certainly!, In today's fast-paced world...)

What to Preserve

While removing slop, keep:

• Genuine technical explanations
• Actual insights and analysis
• Meaningful examples and evidence
• The author's authentic voice
• Facts and accurate information

Anti-Goals

This skill does NOT:

• Dumb down the writing
• Remove all complexity
• Change your personal style
• Eliminate necessary explanations
• Make everything short

Quick Reference

Transformation Examples

Example 1

BEFORE (AI Slop):

"It is important to note that consistent practice plays a crucial role in skill development. Furthermore, one must consider that motivation is a key factor in maintaining this consistency. Moreover, this highlights the importance of setting realistic goals."

AFTER (Human):

"Consistent practice develops skills. Motivation keeps you going, so set realistic goals."

Example 2

BEFORE (AI Slop):

"It should be noted that there are various different approaches to solving this problem. Each approach offers a unique set of advantages and disadvantages. In conclusion, the best choice depends on the specific context."

AFTER (Human):

"Several approaches can solve this problem. Each has pros and cons. Pick what fits your situation."

Example 3

BEFORE (AI Slop):

"Certainly! Let's dive right in. In today's fast-paced digital landscape, businesses must leverage the power of technology to stay competitive. It's crucial to understand that digital transformation is not just a buzzword."

AFTER (Human):

"Let's dive in. To stay competitive, businesses need technology. Digital transformation matters."

Usage

Claude Code: This folder is a skill. Invoke @stop-slop when editing prose.

Claude Projects: Upload SKILL.md to project knowledge.

API calls: Include SKILL.md in your system prompt.

Reference Files

For complete lists, see:

• references/phrases.md — Full banned phrases list
• references/structures.md — Structural patterns to avoid
• references/examples.md — More before/after transformations

Based on work by Hardik Pandya