Stop Slop

Stop Slop targets three specific categories of AI-generated 'slop':

1. Banned phrases: Includes throat-clearing openers, emphasis crutches, business jargon, all adverbs, vague declaratives, and meta-commentary (detailed in references/phrases.md).
2. Structural clichés: Includes binary contrasts, negative listings, dramatic fragmentation, rhetorical setups, false agency, narrator-from-a-distance voice, and passive voice (detailed in references/structures.md).
3. Sentence-level rules: Enforces constraints such as no 'Wh-' sentence starters, no em dashes, no staccato fragmentation, no lazy extremes, and a requirement for active voice.

To use these rules, ensure the references/ directory is available to the LLM to provide specific examples and lists.

Stop Slop is a skill designed to remove AI-typical patterns (predictable phrases, structures, and rhythms) from prose. Depending on your interface, use the following methods to implement it:

• Claude Code: Add the stop-slop/ folder as a skill.
• Claude Projects: Upload SKILL.md and the files in the references/ directory to your project knowledge.
• Custom Instructions: Copy the core rules directly from SKILL.md into your system instructions.
• API Calls: Include the contents of SKILL.md in your system prompt. Note that reference files are intended to be loaded on demand.

# Implementation methods

1. Claude Code: Add this folder as a skill.
2. Claude Projects: Upload SKILL.md and reference files to project knowledge.
3. Custom instructions: Copy core rules from SKILL.md.
4. API calls: Include SKILL.md in your system prompt.

Remove hedging words (e.g., "most") and throat-clearing phrases. Avoid ending segments with permission-granting or reassuring phrases (e.g., "And that's okay") that do not add substantive value to the core message.

Before:
"It turns out that most teams struggle with alignment. The uncomfortable truth is that nobody wants to admit they're confused. And that's okay."

After:
"Teams struggle with alignment. Nobody admits confusion."

Identify and eliminate clusters of corporate jargon such as "In today's fast-paced landscape," "lean into discomfort," or "navigate uncertainty with clarity." Replace these with the core message expressed in as few words as possible.

Before:
"In today's fast-paced landscape, we need to lean into discomfort and navigate uncertainty with clarity. This matters because your competition isn't waiting."

After:
"Move faster. Your competition is."

Avoid using rhetorical setups or questions to introduce a point (e.g., "What if I told you..." or "Here's what I mean..."). Replace the scaffolding with a direct claim to increase impact and clarity.

Before:
"What if I told you that the best teams don't optimize for productivity? Here's what I mean: they optimize for learning. Think about it."

After:
"The best teams optimize for learning, not productivity."

Avoid starting sentences with conversational openers like "Here's the thing" or "It turns out that". Instead of using binary contrast structures (e.g., "Not because X. Because Y.") or emphasis crutches (e.g., "Let that sink in"), use direct, declarative statements to convey information more efficiently.

Before:
"Here's the thing: building products is hard. Not because the technology is complex. Because people are complex. Let that sink in."

After:
"Building products is hard. Technology is manageable. People aren't."

Avoid using performative emphasis through fragmented, single-word sentences (e.g., "Speed. Quality. Cost."). Instead, consolidate these ideas into a single, cohesive sentence to avoid unnecessary dramatic effect.

Before:
"Speed. Quality. Cost. You can only pick two. That's it. That's the tradeoff."

After:
"Speed, quality, cost—pick two."

You can evaluate the quality of prose using the Stop Slop scoring system. Rate each of the following five dimensions on a scale of 1-10:

Threshold: A total score below 35/50 indicates that the text requires revision.

Avoid corporate jargon and replace it with direct, plain language to improve clarity.