code-review

Automate evidence-based code review workflows with SHA verification gates.

2|Updated Jan 9, 2026
One-click install
npx skills add https://github.com/NammDev/Goads-Krea --skill code-review-nammdev
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: code-review
Source: https://github.com/NammDev/Goads-Krea/tree/main/.claude/skills/code-review
Command: npx skills add https://github.com/NammDev/Goads-Krea --skill code-review-nammdev

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Code teams waste cycles on low-signal reviews and unverified claims. This Skill automates rigorous, evidence-based review workflows to ensure changes are verified before being claimed or merged.

Core Features & Use Cases

  • Scout edge cases before review to surface hidden issues and dependencies.
  • Gate verification such that no completion claims are made without fresh verification evidence.
  • Structured interaction flows: requesting code review, handling feedback, and completing verification with traceable SHAs.
  • For use before PR merges, after implementing features, and when claiming task completion.

Quick Start

Begin by scouting edge cases for your changes, then dispatch a code-reviewer with BASE_SHA and HEAD_SHA to evaluate your implementation.

Frequently Asked Questions about code-review

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

FAQPage Schema
How do I automate evidence-based code review before a pull request?

Evidence-based code review automates pre-PR verification by scouting edge cases, extracting BASE_SHA and HEAD_SHA, and dispatching a code-reviewer subagent. It gates merges behind fresh verification evidence to eliminate unverified claims.

What is edge-case scouting in a code review workflow?

Edge-case scouting is a formal pre-review step that surfaces hidden issues and dependencies before evaluation begins. Targeting boundary conditions early ensures subsequent code review focuses on high-risk areas and prevents low-signal review cycles.

How do I prevent unverified task completion claims in software engineering?

Verification gates prevent unverified completion claims by requiring fresh verification evidence before any status is asserted. The workflow extracts traceable SHAs and mandates formal verification steps, ensuring no merge or completion claim bypasses evidence checks.

Can I use code review automation after implementing a feature?

Code review automation applies after implementing features to validate changes before claiming completion. It dispatches a code-reviewer subagent with relevant commit SHAs to evaluate the implementation and enforce verification gates.

What is the best way to structure a pull request review workflow?

The best way to structure a pull request review workflow is to enforce formal steps: scout edge cases, extract BASE_SHA and HEAD_SHA, dispatch a code-reviewer subagent, and require fresh verification evidence before status claims. This eliminates low-signal reviews.

Why does my code review workflow produce low-signal feedback?

Low-signal feedback occurs when reviews lack structured edge-case scouting and verification gates. Implementing an evidence-based workflow with traceable SHAs and a dispatched code-reviewer subagent ensures feedback is grounded in fresh verification evidence.