requesting-code-review

Triggers Git-based code review using BASE_SHA and HEAD_SHA ranges.

6|Updated Mar 21, 2026
One-click install
npx skills add https://github.com/caitengwei/my-skills --skill requesting-code-review-caitengwei
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: requesting-code-review
Source: https://github.com/caitengwei/my-skills/tree/main/superpowers/skills/requesting-code-review
Command: npx skills add https://github.com/caitengwei/my-skills --skill requesting-code-review-caitengwei

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Code changes often miss critical problems until later, causing rework, regressions, and delays.

Core Features & Use Cases

  • Early, focused review dispatch: Sends your change context to a dedicated reviewer subagent designed to evaluate only the work product.
  • Clear review trigger points: Enforces review after each subagent task, after major features, and before merging to main.
  • Actionable feedback workflow: Guides you to fix critical issues immediately, address important issues before continuing, and treat minor issues as backlog items.
  • Git range-based evaluation: Uses BASE_SHA and HEAD_SHA so the reviewer can examine the exact diff you produced.

Quick Start

After you finish a task, dispatch the code-reviewer subagent by providing WHAT_WAS_IMPLEMENTED, PLAN_OR_REQUIREMENTS, BASE_SHA, HEAD_SHA, and DESCRIPTION so it can assess production readiness and issue severity.

Frequently Asked Questions about requesting-code-review

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

FAQPage Schema
What is a git diff range code review and when do I need it?

A git diff range code review evaluates changes between a BASE_SHA and HEAD_SHA to catch defects early. You need it after implementing tasks, major features, or before merging to main to prevent regressions.

How do I request a targeted code review before merging to main?

To request a targeted code review, dispatch a reviewer subagent with WHAT_WAS_IMPLEMENTED, PLAN_OR_REQUIREMENTS, BASE_SHA, HEAD_SHA, and DESCRIPTION. This provides the exact diff range for assessing production readiness.

How does severity-categorized feedback work for issue triage?

Severity-categorized feedback separates issues into critical, important, and minor. You fix critical issues immediately, address important issues before continuing, and treat minor issues as backlog items for structured issue triage.

When should I enforce code review in a subagent workflow?

You should enforce code review after each subagent task, after completing major features, and before merging to main. This prevents defects from spreading during iterative plan execution and subagent-driven development.

Does this code review approach work with iterative plan execution?

Yes, this approach applies to iterative plan execution and subagent-driven development. It uses BASE_SHA and HEAD_SHA to define the diff range, ensuring each iteration's changes are verified for release readiness before proceeding.