code-review

Reviews a git diff against coding standards and the originating spec in parallel sub-agents.

Updated May 11, 2026
One-click install
npx skills add https://github.com/cloudofgeorge/AI-hands-Engineer --skill code-review-cloudofgeorge
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: code-review
Source: https://github.com/cloudofgeorge/AI-hands-Engineer/tree/main/skills/engineering/code-review
Command: npx skills add https://github.com/cloudofgeorge/AI-hands-Engineer --skill code-review-cloudofgeorge

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Reviewing a branch or PR requires checking two separate things — whether the code follows the repo's documented standards and whether it actually implements what the issue or spec asked for — and mixing both concerns in one pass lets one axis mask the other. ## Core Features & Use Cases - Two-axis review: Runs a Standards review (documented repo standards plus a fixed Fowler code-smell baseline) and a Spec review (requirements coverage, scope creep, wrong implementations) as parallel sub-agents, then reports them side by side. - Fixed-point diffing: Compares HEAD against any user-supplied commit, branch, tag, or merge-base using a three-dot git diff, with upfront validation that the ref resolves and the diff is non-empty. - Spec discovery: Locates the originating spec from issue references in commit messages, a user-provided path, or spec files under docs/, specs/, or .scratch/. - Use Case: Before merging a feature branch, ask for a review since main and receive separate Standards and Spec reports, each under 400 words, with findings quoted against the diff and spec lines. ## Quick Start Ask the agent to review the changes since main on the current branch 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 a branch against coding standards and its spec?

Provide a fixed point such as a commit SHA, branch, tag, or main, and the skill diffs HEAD against it using a three-dot git diff. It then runs two parallel sub-agents: one checks documented repo standards plus a code-smell baseline, the other checks the diff against the originating issue or spec.

How does the review find the spec for a change?

It looks for issue references in commit messages first, then a path passed by the user, then spec files under docs/, specs/, or .scratch/ matching the branch or feature. If nothing is found it asks the user, and if no spec exists the Spec axis is skipped and noted in the report.

What code smells does the standards review check for?

The baseline covers twelve Fowler smells including Duplicated Code, Feature Envy, Data Clumps, Primitive Obsession, Shotgun Surgery, Divergent Change, and Speculative Generality. Each is reported as a labelled judgement call, and documented repo standards always override the baseline.

What happens if the fixed point or diff is invalid?

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

Does the review merge standards and spec findings into one score?

No. Findings are reported under separate Standards and Spec headings without merging or reranking, because a change can pass one axis and fail the other. The summary gives totals and the worst issue within each axis only.