requesting-code-review

Dispatches a subagent to review code against plan, quality, and architecture criteria.

Updated Jun 20, 2026

Search Tags:#qa #code-quality #subagent #software-development #code-review #requesting-code-review

Ready to run

npx skills add https://github.com/lowmason/agent-skills --skill requesting-code-review-lowmason

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: requesting-code-review
Source: https://github.com/lowmason/agent-skills/tree/main/requesting-code-review
Command: npx skills add https://github.com/lowmason/agent-skills --skill requesting-code-review-lowmason

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Dispatch a code reviewer subagent to catch issues before they cascade. The reviewer gets precisely crafted context for evaluation — never your session's history. This keeps the reviewer focused on the work product, not your thought process, and preserves your own context for continued work.

Core Features & Use Cases

Dispatch a general-purpose subagent, filling the template at code-reviewer.md to standardize feedback.
Enforce review moments across the workflow: after each task, after major feature completion, and before merging to main, with optional checks for sticking points, refactoring, and bug fixes.
Use a clear placeholders system for describing the build, plan, and commit range to ensure consistent, actionable feedback.

Quick Start

Instruct the workflow by dispatching a general-purpose code-review subagent with the template above and fill in the placeholders for DESCRIPTION, PLAN_OR_REQUIREMENTS, BASE_SHA, and HEAD_SHA.

Frequently Asked Questions about requesting-code-review

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

FAQPage Schema

How do I automate pre-merge code review for a subagent-driven workflow?▼

Dispatch a dedicated reviewer subagent using a templated prompt to automate pre-merge code review. This routes your commit range to an isolated evaluator to validate architecture and production readiness before merging to main.

What is the best way to keep a code reviewer focused on the actual code changes?▼

Keep a code reviewer focused by dispatching a subagent with precisely crafted context containing only the build description, plan, and commit SHAs. This isolates the evaluation from your session's thought process history.

How do I structure feedback for a code quality check after feature implementation?▼

Structure code quality feedback by filling placeholders for description, plan, base SHA, and head SHA in a review template. This enforces consistent evaluation of plan alignment, architecture, and testing after feature implementation.

When should I request a code review during task-driven software development?▼

Request a code review during task-driven software development after each task completion, after major feature implementation, and before merging to main. Optional checks can also be triggered for refactoring and bug fixes.

Does dispatching a code reviewer subagent preserve my main session context?▼

Dispatching a code reviewer subagent preserves your main session context by routing the evaluation to an isolated process. The subagent receives only the work product details, keeping your context window clear for continued development.