XiNian-dada/Fuck_My_Shit_Mountain

An evidence-based AI code audit skill. Professional output. Zero emotional bullshit.

What it solves

This project provides a specialized set of instructions and rubrics (a "skill") for AI coding agents like Codex, Claude Code, Copilot, and Gemini. It solves the problem of "hidden" technical debt and risks in a codebase that might run but contains underlying issues in security, stability, or maintainability that are difficult for a human to audit manually across a large project.

How it works

It functions as a plugin or skill for an AI agent. Once installed in the agent's skill directory, the AI uses the provided prompts, templates, and rubrics to perform a systematic audit. The process involves:

  1. Project Profiling: The AI analyzes the language, frameworks, dependencies, and CI/CD configuration.
  2. Dimension-based Auditing: The AI audits the code based on 25 different dimensions (e.g., security, performance, AI safety, data integrity). The user can request a full audit or specific modes like security or maintainability.
  3. Evidence-based Reporting: The AI generates a report (in Markdown or HTML) containing severity levels, confidence scores, evidence from the code, and specific repair suggestions.

Who it’s for

Developers and engineers who use AI coding agents and want a structured, evidence-based audit of their codebase to identify risks and prioritize repairs before release or during maintenance.

Highlights

  • 25 Audit Dimensions: Covers everything from architecture and security to AI-specific safety (prompt injection, RAG leaks) and accessibility.
  • Structured Reporting: Produces reports with scoring panels, coverage matrices, and prioritized repair plans.
  • Agent Agnostic: Compatible with various AI IDEs and agents including Codex, Claude Code, Copilot, and Gemini.
  • Evidence-Driven: Distinguishes between confirmed issues and potential risks, providing evidence for every finding.

Related

  • Project
    cloudflare/security-audit-skill

    A coding-agent skill that orchestrates multiple parallel agents through a six-phase pipeline to find and verify exploitable security vulnerabilities in codebases.

  • Project
    mattpocock/skills

    A collection of composable AI agent skills that apply software engineering fundamentals like TDD and domain modeling to prevent common AI coding failures.

  • Project
    KKKKhazix/khazix-skills

    A collection of standardized AI agent skills (instruction sets) for goal definition, disk cleanup, deep research, and project documentation maintenance.

  • Project
    Aaronontheweb/dotnet-skills

    A library of 30 skills and 5 specialized agents for AI coding assistants to ensure professional, production-grade .NET development patterns.

  • Project
    alirezarezvani/claude-skills

    A massive open‑source library (364 skills, 120 commands) that adds domain‑specific expertise to Claude Code, Codex, Gemini CLI, Cursor, and 9 other AI coding agents. Each skill bundles a structured markdown guide, pure‑Python CLI helpers, and reference assets. The repo includes personas, an orchestration protocol, and a built‑in security auditor, making it a turnkey way to turn any LLM‑coding assistant into a full‑stack engineering, product, marketing, compliance, or C‑suite advisor.