code-review

Review git diffs against coding standards and originating specs using parallel sub-agents.

Updated Jul 22, 2026
One-click install
npx skills add https://github.com/Chau165/local_skill --skill code-review-chau165
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: code-review
Source: https://github.com/Chau165/local_skill/tree/main/codex/skills/code-review
Command: npx skills add https://github.com/Chau165/local_skill --skill code-review-chau165

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Reviewing a branch or PR requires checking two independent 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 in one pass lets one axis mask failures in the other. ## Core Features & Use Cases - Two-axis review: Runs a Standards review (documented repo standards plus a 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: Reviews the diff between HEAD and any commit, branch, tag, or merge-base the user supplies, validating the ref and diff before spawning agents. - Spec discovery: Locates the originating spec from issue references in commit messages, a user-supplied path, or PRD 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 with cited findings and a per-axis summary. ## Quick Start Ask the assistant 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 all changes since a specific commit or branch?

Provide a fixed point such as a commit SHA, branch name, tag, or HEAD~5, and the skill diffs it against HEAD using a three-dot merge-base comparison. It validates the ref and confirms the diff is non-empty before reviewing.

How does this code review check both style and requirements?

It spawns two parallel sub-agents: one checks the diff against documented repo standards plus a Fowler code-smell baseline, and the other compares the diff against the originating issue or spec. Findings are reported under separate Standards and Spec headings.

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

The skill searches commit messages for issue references, then docs/, specs/, or .scratch/ for matching PRD files. If nothing is found it asks the user, and if no spec exists the Spec axis is skipped and noted in the final report.

Does the review flag code smells even without documented standards?

Yes, a fixed baseline of Fowler code smells such as Duplicated Code, Feature Envy, and Shotgun Surgery always applies. These are reported as judgement calls, and documented repo standards override the baseline where they conflict.

When should I not use this two-axis review approach?

It is less useful for single-commit typo fixes or changes with no reviewable diff, since it requires a non-empty diff against a fixed point. It also depends on an issue tracker configuration at docs/agents/issue-tracker.md for fetching specs.