Requesting Code Review

Dispatch a code-reviewer subagent to analyze changes against a plan.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/fz42net/superpowers-skills --skill requesting-code-review-fz42net
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Requesting Code Review
Source: https://github.com/fz42net/superpowers-skills/tree/main/skills/collaboration/requesting-code-review
Command: npx skills add https://github.com/fz42net/superpowers-skills --skill requesting-code-review-fz42net

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes assets (resource) components.

What problem does it solve?

Manual code reviews can be slow, inconsistent, and prone to missing issues, especially in fast-paced development. This skill automates the process of requesting and receiving AI-powered code reviews.

Core Features & Use Cases

  • Subagent-Driven Review: Dispatches a specialized code-reviewer subagent to analyze changes.
  • Targeted Feedback: Provides the subagent with specific context (what was implemented, plan/requirements, commit SHAs).
  • Structured Feedback Loop: Guides on acting upon review feedback (Critical, Important, Minor issues).
  • Workflow Integration: Designed for use after tasks, major features, or before merging.
  • Use Case: After completing a task in a subagent-driven development workflow, you use this skill to automatically trigger a code review. The AI reviewer checks your changes against the plan, identifies potential issues, and provides actionable feedback before you proceed.

Quick Start

  1. Get the relevant Git SHAs for the changes you want reviewed: BASE_SHA=$(git rev-parse HEAD~1) HEAD_SHA=$(git rev-parse HEAD)
  2. Dispatch a code-reviewer subagent using your AI environment's Task tool, filling in the template at code-reviewer.md with: WHAT_WAS_IMPLEMENTED: [Your changes] PLAN_OR_REQUIREMENTS: [Relevant plan/requirements] BASE_SHA: [Base commit SHA] HEAD_SHA: [Head commit SHA] DESCRIPTION: [Brief summary]
  3. Act on the subagent's feedback (fix critical/important issues).