AntiVibe skill

A skill that explains and audits code, telling you what it does and why instead of just accepting it

  • 1,134 ★ on the repository
  • Last commit
  • MIT
Skill

Extended access

Why this level

  • Reads project code and change history via git diff
All reasons and checks

mohi-devhub/antivibe

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/antivibe

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • Reads project code and change history via git diff

This is third-party code. Review the repository files before installing.

What it does

The skill breaks down any code, be it new, legacy or AI-generated, and produces either a learning explanation or an architectural audit. It shows what the code does, why it was written this way, when such patterns fit and what alternatives exist. Depth and detail are set right in the request, from a beginner walkthrough with definitions and analogies to a senior mode that surfaces only the trade-offs. It can analyze recent changes from git diff, explain a single file or directory, and switch to a dedicated agent for audits.

Who it is for. For developers who want to understand other people's or generated code rather than accept it blindly.

Good fit when

  • You need to understand what code does and why
  • You need to onboard someone into an unfamiliar or legacy codebase
  • You want an architectural audit focused on trade-offs

Not a fit when

  • You need to write code quickly rather than analyze existing code
  • You need a formal linter or tests rather than an explanation

Example request

Do a deep dive on the src/auth directory and explain why the code is built this way

Limitations

The skill gives explanations and audits but does not fix code or replace tests and linters. Analysis depth depends on the agent's model. It installs manually by copying into the Claude Code skills directory.

How to disable. Remove the antivibe folder from the ~/.claude/skills directory.

FAQ

How does explanation differ from audit?

Explanation walks the code at the chosen level; a trade-off audit is routed to a dedicated auditor agent.

How do I set the explanation level?

Right in the request, for example a junior walkthrough with definitions or a senior mode with trade-offs only.

Discussion

No questions or reviews yet.

Skills

A Codex skill for reviewing AI-written code: explains blocks, names files and lines, checks goals against evidence.

SkillExtended access133Repository stars

A skill that finds AI slop in code: duplicate helpers, empty abstractions, weak tests. It cleans one pattern per commit.

SkillExtended access95Repository stars

A skill that runs a full refactor so agents read code more easily: it finds hidden links and needless dependencies.

SkillExtended access1.1KRepository stars

A code review skill across many languages and frameworks: architecture, performance, security, anti-patterns and common bugs

SkillMinimal access2.3KRepository stars12Installs via CLI and agents

An evidence-first development skill: the agent wraps code in a spec and a gauntlet of checks so line-by-line review becomes optional

SkillExtended access759Repository stars

A cleanup skill for agent-written code: finds surplus tests, self-checks and fallbacks and deletes them, keeping behavior

SkillExtended access140Repository stars

README in short

The README describes a code-learning and audit framework installed by copying the folder into ~/.claude/skills. It is triggered with /antivibe or phrases like deep dive and walk me through, with depth set inline from junior to senior. The skill analyzes recent changes from git diff, individual files and whole codebases, and uses a dedicated agent for audits. MIT licensed.

README badge

Original SKILL.md

---
name: antivibe
description: Code learning and audit framework. Analyze any codebase — new, legacy, or AI-generated — and produce educational explanations or architectural audits. Use when the user wants to understand WHAT and WHY behind any code, not just accept it.
triggers:
  - phrase: "/antivibe"
  - phrase: "deep dive"
  - phrase: "anti-vibecode"
  - phrase: "why did AI write"
  - phrase: "learn from this code"
  - phrase: "understand what AI wrote"
  - phrase: "explain this file"
  - phrase: "audit this"
---

# AntiVibe - Code Learning & Audit Framework

## Purpose

AntiVibe generates learning-focused explanations or architectural audits of any code — AI-generated, legacy, or otherwise.

Report a problem