anti-slop

Name: anti-slop
Availability: InStock
Author: iuliandita

Audit TypeScript, Python, Rust, Shell, and IaC codebases for AI-generated quality issues.

2|Updated Apr 6, 2026

Search Tags:#code quality #static analysis #refactoring #maintainability #audit #ai-generated

Ready to run

npx skills add https://github.com/iuliandita/skills --skill anti-slop-iuliandita

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: anti-slop
Source: https://github.com/iuliandita/skills/tree/main/skills/anti-slop
Command: npx skills add https://github.com/iuliandita/skills --skill anti-slop-iuliandita

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires ast-grep, shellcheck, ruff, mypy, eslint, tflint, ansible-lint, kubeconform, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill identifies and corrects the common pitfalls of AI-generated code, such as hallucinated APIs, over-abstraction, redundant boilerplate, and "test theater," ensuring your codebase remains maintainable and human-readable.

Core Features & Use Cases

Multi-Language Audit: Performs deep quality checks across TypeScript, Python, Rust, Bash, and IaC (Terraform/Ansible/Helm).
Pattern Detection: Automatically flags "AI-native" smells like defensive overkill, generic naming, and cross-language idiom leakage.
Use Case: Run this audit on a pull request generated by an AI coding assistant to strip away unnecessary complexity and verify that the code is grounded in your project's actual framework and API contracts.

Quick Start

Invoke the anti-slop skill to perform a full codebase audit and report on any detected code quality issues.

Frequently Asked Questions about anti-slop

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

FAQPage Schema

How do I detect AI-generated code smells and hallucinated APIs in my codebase?▼

AI-generated code smells and hallucinated APIs are detected using static analysis and structural pattern matching to flag issues like over-abstraction and redundant boilerplate, ensuring your codebase remains human-readable and maintainable.

Can I run static analysis audits on both application code and Infrastructure as Code?▼

Yes, static analysis audits support both application code and Infrastructure as Code. The audit targets TypeScript, Python, Rust, and Shell, alongside IaC formats including Terraform, Ansible, and Helm.

What's the best way to check an AI-generated pull request for defensive programming overkill?▼

The best way to check for defensive programming overkill is to run an audit that distinguishes between valid defensive programming and machine-generated slop, automatically flagging defensive overkill and generic naming.

Do I need linters like eslint and ruff installed to audit my codebase?▼

Yes, linters and static analysis tools like eslint, ruff, mypy, shellcheck, tflint, ansible-lint, and kubeconform are required dependencies to perform the multi-language codebase audit and enforce quality standards.

Why does static analysis flag cross-language idiom leakage in my Python and Rust files?▼

Static analysis flags cross-language idiom leakage because it detects AI-native smells where code patterns from one language are incorrectly applied to another, ensuring your code adheres to specific language frameworks and API contracts.