review-code

Evaluates code quality and correctness for pull requests, commits, and branches.

113|15|Updated Mar 3, 2026
One-click install
npx skills add https://github.com/avibebuilder/claude-prime --skill review-code-avibebuilder
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: review-code
Source: https://github.com/avibebuilder/claude-prime/tree/main/.claude/skills/review-code
Command: npx skills add https://github.com/avibebuilder/claude-prime --skill review-code-avibebuilder

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides an objective, structured evaluation of existing code to surface correctness issues, quality concerns, and alignment with project intent when the user requests a review rather than implementation or debugging.

Core Features & Use Cases

  • Targeted reviews: Apply to pull requests, branch diffs, commits, staged changes, or one or more files to evaluate existing work.
  • Depth-matched analysis: Choose Quick, Standard, or Deep review depth depending on risk, scope, and potential impact.
  • Structured reporting: Produce a clear verdict plus categorized findings (Critical Issues, Suggestions, Questions) with file paths and line references and a concise Summary.
  • Team isolation workflow: Support spawning an isolated reviewer teammate to avoid bias from the author and to preserve a repeatable review process.

Quick Start

Ask the reviewer to evaluate the provided diff or files for correctness, readability, and project fit.

Frequently Asked Questions about review-code

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

FAQPage Schema
How do I get a structured code review for a pull request?

To get a structured code review for a pull request, provide the diff, commit, or staged changes. The review produces a report with a verdict, inferred intent, critical issues, suggestions, and a summary with file paths and line references.

Can I adjust the depth of a code review to match project risk?

Yes, you can adjust code review depth to match project risk. Choose Quick, Standard, or Deep review depths to evaluate correctness, readability, and project fit based on the potential impact and scope of the changes.

What is the best way to avoid bias when reviewing my own code commits?

The best way to avoid bias when reviewing your own code commits is to spawn an isolated reviewer teammate. This team isolation workflow preserves a repeatable review process and provides objective, bias-free evaluation of your work.

Does this code review tool work with individual files or only branch diffs?

This code review tool works with both individual files and branch diffs. You can apply targeted evaluations to pull requests, commits, staged changes, or specific files when you request an assessment rather than implementation.

What categories are included in a code quality evaluation report?

A code quality evaluation report includes categories for Critical Issues, Suggestions, and Questions. It also provides a clear Verdict, Inferred Intent, and a concise Summary with specific file paths and line references.

When should I use a deep code review instead of a quick scan?

You should use a deep code review instead of a quick scan when the scope, risk, and potential impact of the changes are high. Depth-matched analysis ensures the review effort aligns with the project's correctness and quality concerns.