deslop

Detect excessive comments, over-defensive error handling, and unnecessary abstractions in AI-generated code.

3|Updated Jul 4, 2020
One-click install
npx skills add https://github.com/mei28/dotfiles --skill deslop-mei28
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deslop
Source: https://github.com/mei28/dotfiles/tree/main/.claude/skills/deslop
Command: npx skills add https://github.com/mei28/dotfiles --skill deslop-mei28

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Detects and removes unnecessary additions and over-engineering in AI-generated code to improve consistency across a codebase.

Core Features & Use Cases

  • Detect excessive comments that restate obvious code.
  • Identify over-defensive error handling and unnecessary abstractions.
  • Suggest targeted refactors to align with project style and conventions. Use Case: When reviewing AI-proposed changes, Deslop helps prune noise and harmonize patterns across files.

Quick Start

Execute a cleanup pass on a target AI-generated file and apply recommended removals and refactors to match project style.

Frequently Asked Questions about deslop

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I remove unnecessary comments and abstractions from AI-generated code?

To remove unnecessary comments and abstractions from AI-generated code, run a targeted cleanup pass that detects excessive documentation and over-defensive handling, outputting concrete refactoring suggestions to align with project conventions.

What is the best way to clean up over-defensive error handling during a code review?

The best way to clean up over-defensive error handling is to audit the AI-proposed changes to identify unnecessary abstractions, pruning the noise by applying targeted refactors that harmonize patterns across your codebase.

Can I refactor multiple programming languages to enforce style consistency?

Yes, you can refactor multiple programming languages to enforce style consistency, as the cleanup process is applicable to code audits and refactoring projects across languages to harmonize patterns across files.

How do I audit AI-generated code for excessive noise and over-engineering?

You audit AI-generated code for noise by detecting unnecessary additions like comments that restate obvious code, identifying over-defensive error handling, and suggesting targeted removals to improve codebase consistency.

When should I not use a targeted refactor for AI code cleanup?

You should avoid targeted refactoring for AI code cleanup when the generated code introduces novel, necessary logic rather than excessive comments or over-defensive error handling, as forcing style alignment may obscure functional requirements.