code-review

Review git diffs against coding standards and spec requirements using parallel sub-agents.

1|Updated Mar 2, 2025
One-click install
npx skills add https://github.com/marjorg/setup --skill code-review-marjorg
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: code-review
Source: https://github.com/marjorg/setup/tree/main/home/.agents/skills/archive/0-matt/code-review
Command: npx skills add https://github.com/marjorg/setup --skill code-review-marjorg

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Code reviews often conflate two separate questions: does the code follow the project's standards, and does it actually implement what was asked for? This Skill separates those axes so one cannot mask the other, and runs both checks in parallel sub-agents to keep their contexts clean. ## Core Features & Use Cases - Two-axis review: Evaluates a diff against documented coding standards (plus a Fowler code-smell baseline) and against the originating issue or spec, reported side by side. - Parallel sub-agents: Spawns independent Standards and Spec sub-agents so findings from one axis never pollute or rerank the other. - Flexible fixed points: Reviews changes since any commit, branch, tag, or merge-base using three-dot git diff semantics. - Use Case: Before merging a feature branch, ask for a review since main and receive separate Standards and Spec reports, each citing the violated rule or spec line. ## Quick Start Ask the assistant to review the changes on this branch since main using the code-review skill.

Frequently Asked Questions about code-review

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

FAQPage Schema
How do I review changes since a specific commit or branch?

Provide any fixed point such as a commit SHA, branch name, tag, or HEAD~5, and the skill diffs it against HEAD using three-dot merge-base semantics. If you do not specify one, it asks before proceeding.

How does this code review check coding standards?

It reads documented standards files like CODING_STANDARDS.md or CONTRIBUTING.md, then adds a fixed baseline of Fowler code smells such as Feature Envy and Shotgun Surgery. Documented repo standards always override the baseline.

What happens if there is no spec or issue for the changes?

The skill searches commit messages for issue references, checks user-provided paths, and looks under docs/, specs/, or .scratch/. If nothing is found and the user confirms no spec exists, the Spec axis is skipped and reported as unavailable.

Why does the review fail before the sub-agents run?

The skill validates the fixed point with git rev-parse and confirms the diff is non-empty before spawning sub-agents. A bad ref or empty diff fails fast at this step rather than inside the parallel agents.

Does the review merge or rank findings across both axes?

No. Standards and Spec findings are reported under separate headings and never merged or reranked, because the two-axis separation exists to prevent one axis from masking failures in the other.