de-slop

AI-generated writing patterns in markdown files are detected using regex and heuristic analysis to identify structural tells, hyperbolic language, and filler phrases. The analysis produces per-file slop scores and line-level flags with suggested fixes.

Common AI writing anti-patterns in technical documentation include buzzword stacking, defensive framing, repetitive structures, excessive emoji, and motivational tone. These filler patterns make content sound robotic and reduce reader trust.

Scan a directory for AI writing artifacts by running a Python script that analyzes markdown and text files. The script flags specific lines containing AI patterns and assigns a slop score to evaluate overall content quality.

This AI content detection requires Python to execute the analysis script, but relies on no external dependencies. It uses built-in regex and heuristic analysis to evaluate markdown files without needing third-party APIs.

Line-level suggestions to fix robotic sounding documentation are generated automatically during the heuristic analysis. The scanner flags specific lines containing AI writing patterns and provides targeted fixes to improve natural language flow.

The best way to remove buzzwords and filler from markdown content is using a heuristic scanner that detects repetitive structures and hyperbolic language. It flags problematic lines and suggests improvements to restore natural language quality.