code-review

Compare git diffs against repository standards and project specifications.

Updated Dec 17, 2025
One-click install
npx skills add https://github.com/Frantss/oxform --skill code-review-frantss
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: code-review
Source: https://github.com/Frantss/oxform/tree/main/.agents/skills/code-review
Command: npx skills add https://github.com/Frantss/oxform --skill code-review-frantss

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill solves the challenge of maintaining both high technical standards and functional alignment with project requirements during code reviews, preventing the common issue where code is technically sound but fails to meet the original business intent.

Core Features & Use Cases

  • Parallel Review Axes: Simultaneously evaluates code against documented standards and the originating specification.
  • Smell Baseline: Automatically applies a set of Fowler-inspired code smells to identify design issues like Feature Envy or Shotgun Surgery.
  • Use Case: Use this when reviewing a complex pull request to ensure the implementation is both clean, maintainable, and strictly adheres to the requirements defined in the associated issue or PRD.

Quick Start

Ask the agent to perform a code review on the current branch by comparing it against the main branch.

Frequently Asked Questions about code-review

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

FAQPage Schema
How do I automate code review to check both pull request quality and spec compliance?

Automated code review for pull requests can evaluate both technical quality and spec compliance by comparing git diffs against repository standards and originating project specifications. This dual-axis approach uses parallel sub-agents to analyze implementation correctness and code health simultaneously.

What is a dual-axis code review and how does it work with git diffs?

Dual-axis code review works by analyzing git diffs against two parallel tracks: documented architectural standards for code health, and originating project specifications for functional completeness. This ensures the implementation is both clean and strictly adheres to business requirements.

How do I perform a code review on my current branch against the main branch?

To perform a code review on your current branch, ask the agent to compare your current branch against the main branch. The review will automatically apply Fowler-inspired code smells to identify design issues like Feature Envy or Shotgun Surgery in the diff.

Can code review detect code smells like Feature Envy or Shotgun Surgery automatically?

Yes, automated code review can detect code smells by applying a Fowler-inspired smell baseline. It automatically identifies design issues like Feature Envy or Shotgun Surgery to flag areas needing refactoring and ensure architectural adherence.

Does automated static analysis ensure my code matches the requirements in my issue tracker?

Automated static analysis ensures code matches requirements by checking functional completeness relative to issue trackers or PRDs. It orchestrates parallel sub-agent analysis to verify that technically sound code does not fail to meet the original business intent.