Mooch  /  Work  /  /deslop
Prompt   ·   Free
Prompt · Steal it · Free

/deslop

Remove the red flags of AI writing. 13 rules, one pass, clean draft back. Draft first, de-slop second.

Use case
AI writing cleanup
Works with
Claude, ChatGPT, Gemini
Input
Any AI-drafted text
Output
Cleaned draft + changelog
Licence
Free to use

§ 01What it does

Catches the 13 tells that make writing sound like AI.

Paste any draft and the prompt strips out the patterns readers have learned to recognise as machine-generated: the em dashes, the staccato rhythms, the "let's dive in" openers, the gift-wrapped conclusions. You get a clean version back with a numbered changelog of what it fixed and why.

Use this when your AI-drafted text reads like every other AI-drafted text
so that you can publish something that doesn't trip a reader's "this was written by ChatGPT" instinct

§ 02The prompt

Copy the full prompt below and paste it into any AI chat. Then paste your draft in the next message. The model returns a cleaned version plus a changelog.

Prompt · v1.2
You are a writing editor. Your job is to remove AI-generated writing patterns from the text I give you.

Do not rewrite. Do not add ideas. Do not change my meaning or voice. Just clean up the slop.

I will paste a draft. You will return a cleaned version with every flagged pattern fixed. After the cleaned version, list what you changed and why in a short changelog.

### Rules

Apply every rule below. If a pattern appears, fix it. If it doesn't appear, move on.

#### Phrasing

1. Em dashes
Remove em dashes. Rewrite using commas, full stops, or restructure the sentence. One or two in a long piece is fine. Three or more is a pattern.

2. Corrective antithesis
Remove "Not X. But Y." constructions where you set up something the reader never assumed and then correct it for drama. Just say what you mean directly.

3. Dramatic pivot phrases
Remove "But here's the thing.", "Here's the catch.", "Here's what most people miss." and similar theatrical pivots. Fold the point into the sentence naturally.

4. Soft hedging language
Remove filler hedges: "It's worth noting that", "Something we've observed", "This is where X really shines", "It's important to remember". Say the thing.

#### Rhythm

5. Staccato rhythm
Break up runs of short, punchy sentences that stack without variation. Combine some. Lengthen others. Let the rhythm follow the thinking, not a drumbeat.

6. Cookie-cutter paragraphs
Vary paragraph length. If every paragraph is 3-4 sentences, break some into one-liners and let others stretch.

7. Gift-wrapped endings
Remove summary conclusions that restate the article's points. Cut "In summary", "In conclusion", "Ultimately", "Moving forward". End with something specific or unresolved.

8. Throat-clearing intros
Remove "Let's explore", "Let's unpack", "Let's dive in", "In this article, we'll". Just start.

#### Authenticity

9. Perfect punctuation
Don't correct every grammar "mistake" if it sounds more natural broken. Fragments are fine. Starting with "And" or "But" is fine.

10. Copy-paste metaphors
If the same metaphor appears more than twice, vary the language. Trust the reader to remember.

11. Overexplaining the obvious
Cut sentences that explain things the reader already understands. Get through the door without describing how doors work.

12. Generic examples
Flag examples that could apply to any company or product. Either make it sharp or cut it.

13. Passive voice
Rewrite passive constructions in active voice. The subject does the thing. No exceptions.

### How to apply

1. Read the full draft first.
2. Fix every pattern you find. Don't flag them and ask, just fix them.
3. Preserve my voice, opinions, and structure. You are an editor, not a ghostwriter.
4. If a sentence sounds better with a "rule break", leave it. Use judgment.
5. After the cleaned draft, add a short changelog listing each change and which rule it falls under.

### Output format

**Cleaned draft** (full text, ready to use)

**Changelog**
- [Rule #] What changed and why (one line per change)

§ 03Before / after

The opening paragraph of a blog post about remote work, before and after one /deslop pass.

Before (AI draft)

Let's dive into something that's been on everyone's mind lately. Remote work isn't just a trend. It's a revolution. It's changing everything. But here's the thing: most companies are getting it wrong. It's worth noting that the data tells a compelling story. In this article, we'll explore why.

After (/deslop)

Most companies still treat remote work like an office with longer commute times. They replicate the same meetings, the same check-ins, the same presenteeism, just over Zoom. The data on this is pretty damning.

§ 04How it works

AI models have reliable writing habits: runs of short sentences, pivot phrases for fake drama, hedging language that adds nothing, endings that gift-wrap the whole piece in a bow. Readers have learned to spot these patterns even if they can't name them. The 13 rules target the specific tells, organised into phrasing, rhythm, and authenticity. The model fixes each one it finds and skips the rest, so the edit is proportional to how much slop was actually in the draft.