---
title: Anti-AI-Slop Patterns (Core)
description: The critical AI-tell patterns caught in every piece of content — 13 always-catch patterns, 4 context-dependent checks, and the whitelist of natural voice patterns that are NOT slop.
source: skills/tier-1-voice-dna/anti-slop.md
updated: 2026-07-02
order: 1
---

# Anti-AI-Slop Patterns (Core)

These are the critical patterns that get caught in every piece of content. The full 29-pattern detection system lives in `ai-pattern-detection.md` (this collection) as a standalone skill for deep scans.

## Always Catch (Critical)

1. **Em-dashes** (---): Delete all. Use periods, commas, or restructure. You use ellipses (...) and arrows (-->) naturally instead.

2. **Authority Signaling Phrases**: "The uncomfortable truth", "Let me be clear", "Here's what nobody tells you", "The hard truth is", "Here's the reality", "What most people miss is..."
   - Exception: "here's how" and "here's the play" are directional in your voice, not performative. Those are fine.

3. **Narrator Setup Lines**: "Here's the thing about...", "here's where it gets interesting..." Delete the setup. Start with the actual point.

4. **Dramatic Rhetorical Framing**: "But here's the part where...", "And that's when it clicked.", "Want to know the crazy part?" State what happened. Let the reader feel it.

5. **Three Parallel Dramatic Sentences**: "You can't see it. You can't copy-paste it away. You have to know it exists." One direct statement lands harder. Cut to one.

6. **The Bookend Summary**: Opening with a thesis, closing with the exact same thesis rephrased 800 words later. AI wraps content in neat bows. Real thinking goes somewhere new by the end.

7. **Self-Branded Concepts**: "This is what I call..." Just explain it.

8. **Artificial Drama Sentences**: "The shift sounds simple. It's not." Show why it's hard with a specific example.

9. **Colon-Listed Everything**: "the result: better data. the impact: faster sales." Reads like a PowerPoint slide. Write natural sentences.

10. **The Humble Brag Disclaimer**: "I don't have all the answers, but..." Share your take or don't. The disclaimer makes it worse.

11. **Hype Words**: "game changer", "chaos", "unleash", "supercharge", "next-level". Lazy energy words that say nothing. Replace with what actually changed or happened.

12. **"No fluff" / "No BS" Disclaimers**: Saying "no fluff" is itself fluff. If the content has no fluff, the reader will know. Delete the disclaimer.

13. **"Nada" Filler**: "Nada this, nada that." Performative emphasis that reads as AI padding. Cut it.

## Context-Dependent (Check but don't auto-delete)

11. **Engagement Bait Endings**: "So here's my question for you..." Generally avoid, BUT on meme posts you do ask "what's your version? drop it in the comments" and that fits the lighter tone.

12. **Bullets for Arguments**: Arguments belong in prose. BUT workflow steps, tool lists, and technical implementations use bullets/emoji markers naturally. The rule: bullets for execution, prose for reasoning.

13. **False Dichotomies**: "It's not X, it's Y." Generally avoid, BUT you naturally contrast old way vs. new way (manual SDR grind vs. automated Clay workflow). That's not a false dichotomy, that's showing evolution.

14. **Bold Headers as Transitions**: Headers for navigation only. Your posts don't typically use headers anyway. LinkedIn formatting is whitespace-driven.

## Your Natural Patterns (Not Slop)

These look like AI tells but are actually your voice. Don't flag them:

- **Ellipses** (...) for trailing thoughts: "true story. 😅", "it feels... prehistoric"
- **Arrows** (-->, ➡️) for workflow steps and progression
- **Emoji section markers** (✅, 🔧, 🔗, 🧠, 🕷️) for structuring workflow walkthroughs
- **"here's how" / "here's the play"** as directional openers into workflow breakdowns
- **Pop culture references** mixed into technical content
- **"no gatekeeping"** as a value statement with resource delivery in comments