slop-detector

Detect low-effort LLM generated code by scanning for architectural shortcuts, ghost logic, placeholderism, and boilerplate bloat. This Skill analyzes your codebase using grep commands to flag common anti-patterns and linguistic LLM-isms masked by professional-sounding comments.

Common code smells indicating AI-assisted development include ghost logic, placeholderism, fragile string parsing, and insecure defaults. This Skill identifies these specific code smells alongside excessive copy-pasted boilerplate and recognizable LLM-isms within your codebase.

Find redundant boilerplate and ghost logic by running targeted pattern detection scans. This Skill flags excessive copy-pasted code instead of abstractions and identifies comments that merely restate the code or explain the obvious, cutting through architectural shortcuts.

This LLM detection approach requires no external dependencies. It operates by utilizing grep commands for pattern detection within your codebase, making it a basic and self-contained solution for identifying low-effort AI-assisted development anti-patterns.

The best way to flag fragile string parsing and placeholderism is to scan for simple string manipulation used for complex data and hardcoded placeholder values within seemingly final logic. This Skill automates detecting these architectural shortcuts.

You should understand that automated code quality detection provides basic pattern matching rather than deep semantic analysis. It flags structural anti-patterns like LLM-isms and boilerplate bloat using grep commands, meaning complex architectural technical debt may still require manual review.