Remove telltale signs of AI-generated 'slop' writing from README files and documentation. Make your docs sound authentically human.
Purpose: Make your documentation sound like it was written by a human, not an LLM.
Key Insight: You can't do this with regex or a script—it requires manual, systematic review of each line.
AI slop refers to writing patterns that LLMs produce disproportionately more commonly than human writers. These patterns make text sound inauthentic and "cringe."
| Pattern | Problem |
|---|---|
| Emdash overuse | LLMs love emdashes—they use them constantly—even when other punctuation works better |
| "It's not X, it's Y" | Formulaic contrast structure |
| "Here's why" | Clickbait-style lead-in |
| "Here's why it matters:" | Same energy |
| "Let's dive in" | Forced enthusiasm |
| "In this guide, we'll..." | Overly formal setup |
| "It's worth noting that..." | Unnecessary hedge |
| "At its core..." | Pseudo-profound opener |
I want you to read through the complete text carefully and look for any telltale signs of "AI slop" style writing; one big tell is the use of emdash. You should try to replace this with a semicolon, a comma, or just recast the sentence accordingly so it sounds good while avoiding emdash.
Also, you want to avoid certain telltale writing tropes, like sentences of the form "It's not [just] XYZ, it's ABC" or "Here's why" or "Here's why it matters:". Basically, anything that sounds like the kind of thing an LLM would write disproportionately more commonly that a human writer and which sounds inauthentic/cringe.
And you can't do this sort of thing using regex or a script, you MUST manually read each line of the text and revise it manually in a systematic, methodical, diligent way. Use ultrathink.
The prompt explicitly states:
"And you can't do this sort of thing using regex or a script, you MUST manually read each line of the text and revise it manually in a systematic, methodical, diligent way."
Reasons:
When you encounter an emdash (—), consider:
| Original | Alternative |
|---|---|
X—Y—Z | X; Y; Z or X, Y, Z |
The tool—which is powerful—works well | The tool, which is powerful, works well |
We built this—and it works | We built this, and it works |
Here's the thing—it matters | Here's the thing: it matters or recast entirely |
Sometimes the best fix is to split into two sentences or restructure entirely.
Before (sloppy):
This tool—which we built from scratch—handles everything automatically—from parsing to output.
After (clean):
This tool handles everything automatically, from parsing to output. We built it from scratch.
Before (sloppy):
We chose Rust for this component. Here's why: performance matters, and Rust delivers.
After (clean):
We chose Rust for this component because performance matters.
Before (sloppy):
It's not just a linter—it's a complete code quality system.
After (clean):
This is a complete code quality system, not just a linter.
Or even better:
This complete code quality system goes beyond basic linting.
Before (sloppy):
# Getting Started
Let's dive in! We're excited to help you get up and running with our amazing tool.
After (clean):
# Getting Started
Install the tool and run your first command in under a minute.
bd create "De-slopify README.md" -t docs -p 3
bd create "De-slopify API documentation" -t docs -p 3
Now, before we commit, please read through README.md and look for any telltale signs of "AI slop" style writing...
Some things are fine even if they seem "AI-like":
I want you to read through the complete text carefully and look for any telltale signs of "AI slop" style writing; one big tell is the use of emdash. You should try to replace this with a semicolon, a comma, or just recast the sentence accordingly so it sounds good while avoiding emdash.
Also, you want to avoid certain telltale writing tropes, like sentences of the form "It's not [just] XYZ, it's ABC" or "Here's why" or "Here's why it matters:". Basically, anything that sounds like the kind of thing an LLM would write disproportionately more commonly that a human writer and which sounds inauthentic/cringe.
And you can't do this sort of thing using regex or a script, you MUST manually read each line of the text and revise it manually in a systematic, methodical, diligent way. Use ultrathink.
Review this text and remove any AI slop patterns: excessive emdashes, "Here's why" constructions, "It's not X, it's Y" formulas, and other LLM writing tells. Recast sentences to sound more naturally human. Use ultrathink.