brutal-project-review

Automate subsystem-by-subsystem code reviews with resumable state tracking.

2|Updated Feb 9, 2026
One-click install
npx skills add https://github.com/sssemil/SKILLS --skill brutal-project-review
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: brutal-project-review
Source: https://github.com/sssemil/SKILLS/tree/main/brutal-project-review
Command: npx skills add https://github.com/sssemil/SKILLS --skill brutal-project-review

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Systematically review large codebases subsystem by subsystem, preserving resumable state to avoid rework and ensure traceable audits.

Core Features & Use Cases

  • Subsystem discovery and phased review plan
  • Resumable state tracking across sessions
  • Automatic generation of workspace tasks for critical/major findings
  • Context-rich reviews with per-subsystem task creation

Quick Start

Start a brutal project review from the repository root to discover subsystems and begin generating tasks for high-severity issues.

Frequently Asked Questions about brutal-project-review

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

FAQPage Schema
How do I automate subsystem-by-subsystem code reviews for a large codebase?

Automate subsystem-by-subsystem code reviews by dynamically discovering subsystems, building context, and generating actionable findings for critical issues. This systematic approach applies phased review plans to large codebases without manual partitioning.

What is resumable state tracking for code reviews and when do I need it?

Resumable state tracking preserves code review progress across sessions using manifest-driven tracking, ensuring traceable audits and avoiding rework. You need this when systematically reviewing large codebases that require multiple sessions to complete.

How do I automatically generate tasks for critical code review findings?

Generate tasks for critical code review findings automatically through multi-perspective, context-rich reviews. The review process identifies high-severity issues and creates actionable workspace tasks for major findings within each subsystem.

Can I perform a risk analysis review on my codebase without losing progress between sessions?

Yes, you can perform risk analysis reviews with manifest-driven progress tracking that preserves state across sessions. This ensures traceable audits and avoids rework when reviewing large codebases subsystem by subsystem.

What's the best way to systematically review large codebases without missing critical issues?

Systematically review large codebases using dynamic subsystem discovery and phased review plans. This method builds rich context per subsystem and applies multi-perspective analysis to ensure critical issues generate actionable tasks.

Does subsystem discovery work for any repository structure?

Subsystem discovery works from the repository root to dynamically identify and partition codebases for phased reviews. It builds context per subsystem, ensuring comprehensive coverage regardless of the underlying project structure.