requesting-code-review

Dispatches a code-reviewer subagent to review git diffs against requirements before merging.

1|Updated Feb 18, 2026
One-click install
npx skills add https://github.com/Emmanuel-R8/aikos --skill requesting-code-review-emmanuel-r8
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: requesting-code-review
Source: https://github.com/Emmanuel-R8/aikos/tree/main/.cursor/skills/requesting-code-review
Command: npx skills add https://github.com/Emmanuel-R8/aikos --skill requesting-code-review-emmanuel-r8

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Code changes often get merged without structured review, letting bugs, missing requirements, and architectural issues compound across tasks. This Skill standardizes how you request AI-driven code reviews so issues are caught early. ## Core Features & Use Cases - Structured Review Dispatch: Fills a code-reviewer template with what was implemented, requirements, and git SHAs, then dispatches a review subagent. - Severity-Triage Feedback: Returns issues categorized as Critical, Important, or Minor with file:line references and a merge readiness verdict. - Use Case: After finishing a feature task, capture the base and head commit SHAs, dispatch the reviewer with the task plan, fix Critical and Important issues, then proceed to the next task or merge. ## Quick Start Ask the AI to request a code review of your latest commits against the task requirements before merging.

Frequently Asked Questions about requesting-code-review

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

FAQPage Schema
How do I request a code review before merging?▼

Get the base and head commit SHAs with git rev-parse, then dispatch the code-reviewer subagent with what was implemented, the requirements, and the SHA range. Act on the returned feedback by severity before merging.

When should I request a code review during development?▼

Request review after each task in subagent-driven development, after completing a major feature, and before merging to main. It is also useful when stuck or before refactoring to establish a baseline.

How are code review issues categorized by severity?▼

Issues are split into Critical (bugs, security, data loss), Important (architecture problems, missing features, test gaps), and Minor (style, optimizations). Each issue includes a file:line reference and an explanation of why it matters.

What should I do if the code reviewer is wrong?▼

Push back with technical reasoning rather than accepting incorrect feedback. Show code or tests that prove the implementation works, and request clarification from the reviewer.

Can I skip code review for simple changes?▼

No, skipping review because a change seems simple is explicitly flagged as a red flag. Small changes can still introduce regressions, and early review prevents issues from compounding across tasks.