deslop
Clean AI-generated slop from staged changes before commit
When & Why to Use This Skill
The Deslop Claude skill is an automated code refinement tool designed to eliminate 'AI slop' from your development workflow. It acts as a specialized subagent that reviews staged changes or recent commits to remove redundant comments, unnecessary defensive programming, and inconsistent styling often introduced by AI code generation. By ensuring your code remains clean, concise, and aligned with human-written standards, it significantly reduces technical debt and improves maintainability.
Use Cases
- Pre-commit Cleanup: Automatically strip away verbose AI-generated comments and redundant boilerplate before pushing code to a shared repository.
- Code Quality Enforcement: Identify and remove unnecessary 'try/catch' blocks or defensive checks that are abnormal for specific validated codepaths.
- Type Integrity Maintenance: Detect and fix lazy 'Any' type casts introduced by AI to bypass type checkers, ensuring robust TypeScript or Python codebases.
- Style Alignment: Scan diffs to ensure that AI-generated snippets match the existing architectural patterns and stylistic conventions of the project.
| name | deslop |
|---|---|
| description | Use a subagent to review the code change and remove AI generated slop |
Check the diff against main, and remove all AI generated slop introduced in the outstanding code changes, most recent commit, or branch based on the user instructions.
This includes:
- Extra comments that a human wouldn't add or is inconsistent with the rest of the file
- Extra defensive checks or try/catch blocks that are abnormal for that area of the codebase (especially if called by trusted / validated codepaths)
- Casts to
Anyto get around type issues - Any other style that is inconsistent with the file
Report at the end with only a 1-3 sentence summary of what you changed.