roast

Review code files or repositories against a criteria-driven rubric for defects and debt.

Updated Feb 20, 2026
One-click install
npx skills add https://github.com/ChrisSteinbach/claude-skills --skill roast-chrissteinbach
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: roast
Source: https://github.com/ChrisSteinbach/claude-skills/tree/main/roast
Command: npx skills add https://github.com/ChrisSteinbach/claude-skills --skill roast-chrissteinbach

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Quickly revealing hidden flaws and quality gaps in code through an adversarial, zero-tolerance review approach, preventing shipping brittle implementations.

Core Features & Use Cases

  • Rigorous code quality assessment: Identify security issues, architectural weaknesses, and maintainability concerns with concrete, actionable feedback.
  • Debt discovery: Surfacing TODOs, hacks, and anti-patterns that slow future changes.
  • Guided remediation: Provides clear next steps and tradeoffs to fix prioritized issues on target code.

Quick Start

Provide the target code path or snippet and the skill will perform a ruthless, technically grounded review.

Frequently Asked Questions about roast

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

FAQPage Schema
How do I perform an adversarial code review to find critical defects?

An adversarial code review relentlessly critiques code using a criteria-driven rubric to surface critical defects, architectural debt, and hidden flaws, providing prioritized fixes and remediation steps.

What is the best way to identify technical debt and anti-patterns in a repository?

Identify technical debt by applying a zero-tolerance risk identification process across the repository to surface TODOs, hacks, and anti-patterns that slow future changes.

Can I use a static analysis rubric for production-readiness assessment across different languages?

Production-readiness assessment applies to single files or entire repositories across languages using a structured YAML frontmatter and detailed rubric for deterministic, repeatable reviews.

How does a criteria-driven rubric ensure repeatable quality assessments?

A criteria-driven rubric ensures repeatable quality assessments by requiring structured YAML frontmatter in the target SKILL.md and a detailed rubric in the body to guide deterministic, repeatable reviews.

What do I need to start a ruthless code critique on my source files?

To start a ruthless code critique, provide the target code path or snippet; the review requires a structured YAML frontmatter including name and description in the target SKILL.md to execute.