eng-ai-slop-remover

Remove AI-generated code patterns that are inconsistent with human-written code in the codebase.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "eng-ai-slop-remover" with this command: npx skills add hungv47/agent-skills/hungv47-agent-skills-eng-ai-slop-remover

AI Slop Remover

Remove AI-generated code patterns that are inconsistent with human-written code in the codebase.

Workflow

  • Get the diff against main branch

  • For each changed file, analyze patterns to remove

  • Make edits to remove identified slop

  • Report a 1-3 sentence summary of changes

Step 1: Get the Diff

git diff main --name-only

Then view each changed file to understand existing code style.

Step 2: Identify AI Slop Patterns

Comments to remove:

  • Obvious or redundant comments explaining what code clearly does

  • Comments that don't match the commenting style elsewhere in the file

  • Section divider comments when not used elsewhere

Defensive code to remove:

  • Try/catch blocks around code that doesn't throw or is already in a trusted path

  • Null/undefined checks when callers guarantee valid input

  • Type guards that duplicate earlier validation

  • Redundant error handling when parent functions already handle it

Type issues to fix:

  • Casts to any that bypass TypeScript's type system

  • Type assertions that hide real type mismatches

  • Overly broad generic types when specific types exist

Style inconsistencies:

  • Naming conventions that differ from the file

  • Spacing/formatting patterns that differ from the file

  • Import organization that differs from the file

Step 3: Make Edits

Remove identified patterns while preserving code functionality. Match the existing file's style.

Step 4: Report

End with only a 1-3 sentence summary of what was changed. No lists, no detailed breakdowns.

Example: "Removed 12 redundant comments and 3 unnecessary try/catch blocks across 4 files. Fixed 2 casts to any by using proper interface types."

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Coding

eng-codebase-cleanup

No summary provided by upstream source.

Repository SourceNeeds Review
Coding

tool-skill-development

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

mkt-copywriting

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

design-user-flow

No summary provided by upstream source.

Repository SourceNeeds Review