review

Automate evidence-based reviews of code, documents, or architecture.

18|3|Updated Mar 28, 2026
One-click install
npx skills add https://github.com/ondrej-svec/heart-of-gold-toolkit --skill review-ondrej-svec
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: review
Source: https://github.com/ondrej-svec/heart-of-gold-toolkit/tree/main/plugins/deep-thought/skills/review
Command: npx skills add https://github.com/ondrej-svec/heart-of-gold-toolkit --skill review-ondrej-svec

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

In software development, this skill streamlines rigorous, evidence-based reviews of code, documents, or architectures, helping teams surface issues before they become defects.

Core Features & Use Cases

  • Auto-detects review type (code diff, document, or architecture) and guides a structured evaluation.
  • Delivers evidence-backed findings and clear verdicts to support decision-making.
  • Keeps user autonomy by presenting recommendations without applying any changes directly.

Quick Start

Ask the AI to review the latest commit or document and return a structured findings report.

Frequently Asked Questions about review

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

FAQPage Schema
How do I get an automated code review with evidence for my commit?

An evidence-based code review evaluates your commit diff or document automatically. It detects the review type, delivers structured findings with clear justifications, and provides actionable next steps for decision-making.

What is the best way to review architecture plans before implementation?

The best way to review architecture plans is through a structured evaluation workflow that provides evidence-backed verdicts. It assesses your architecture documents, highlights potential issues, and outputs actionable recommendations without applying changes.

Can I use this to review documentation quality automatically?

Yes, you can automatically review documentation quality by submitting your documents. The system detects the document format, evaluates the content, and returns a structured findings report with evidence-backed verdicts and recommendations.

Does the review process apply changes to my code directly?

No, the review process does not apply changes to your code directly. It strictly preserves user autonomy by presenting evidence-backed findings, clear verdicts, and actionable recommendations without modifying your files.

How do I start a structured code or architecture evaluation?

To start a structured code or architecture evaluation, simply ask the AI to review your latest commit, code diff, or document. The system auto-detects the input type and generates a structured findings report with actionable next steps.