What are the cardinal signs of AI-generated slop?

Key signs include generic naming (e.g., 'data1', 'result'), hollow performance claims in comments, logic that fails edge cases, and the presence of conversational phrases like 'As a large language model'.

Can I use this for automated code reviews?

Yes, it is designed to be integrated into CI/CD pipelines and pre-commit hooks to flag conversational artifacts and low-quality patterns before they reach production.

What is 'AI slop' in software development?

AI slop refers to low-quality, unoptimized, or unvetted code generated by AI that lacks contextual awareness, often introducing redundant logic or maintenance issues.

How does the skill detect hallucinated packages?

It performs 'slopsquatting' checks by identifying plausible-sounding but non-existent package names and suggesting verification against official registries like npm or PyPI.

Does this skill replace human code review?

No, it enhances it. The skill follows a mandatory human oversight framework where high-risk findings are flagged for expert review by developers or architects.

AI Slop Detector

Name: AI Slop Detector
Author: UtsavBalar1231

byUtsavBalar1231

보안 및 테스팅

Audits codebases to identify and remediate low-quality AI-generated patterns, security vulnerabilities, and hallucinated dependencies.

소개

The AI Slop Detector is a comprehensive diagnostic toolkit designed to maintain high standards in AI-assisted development environments. It systematically identifies 'AI slop'—code that lacks thoughtfulness, introduces logic errors, or contains conversational artifacts—through a multi-phase approach of pattern recognition and deep analysis. By scanning for high-risk issues like 'slopsquatting' (hallucinated packages) and hollow performance claims, this skill provides developers with a structured remediation framework and CI/CD integration strategies to ensure that AI-generated contributions are robust, secure, and maintainable.

주요 기능

0 GitHub stars
Systematic analysis of logical fallacies and inefficient AI-generated logic
Pattern recognition for conversational AI artifacts and hollow documentation
Detection of 'slopsquatting' and hallucinated third-party dependencies
CI/CD integration guardrails for proactive quality prevention
Multi-phase remediation strategy with human-in-the-loop oversight

사용 사례

Verifying the security and existence of package dependencies in AI-suggested code
Auditing large codebases with significant AI-assisted contributions for technical debt
Establishing automated linting rules to filter out generic AI-generated naming patterns

소개

주요 기능

0 GitHub stars
Systematic analysis of logical fallacies and inefficient AI-generated logic
Pattern recognition for conversational AI artifacts and hollow documentation
Detection of 'slopsquatting' and hallucinated third-party dependencies
CI/CD integration guardrails for proactive quality prevention
Multi-phase remediation strategy with human-in-the-loop oversight

사용 사례

Verifying the security and existence of package dependencies in AI-suggested code
Auditing large codebases with significant AI-assisted contributions for technical debt
Establishing automated linting rules to filter out generic AI-generated naming patterns