code-review

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

Updated Sep 11, 2026
One-click install
npx skills add https://github.com/CYRUS-pinto/pi-bot --skill code-review-cyrus-pinto
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: code-review
Source: https://github.com/CYRUS-pinto/pi-bot/tree/main/.agents/skills/code-review
Command: npx skills add https://github.com/CYRUS-pinto/pi-bot --skill code-review-cyrus-pinto

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Reviewing a branch or PR requires checking two separate things at once: whether the code follows the repo's documented standards, and whether it actually implements what the originating issue or spec asked for. Doing both in one pass lets one axis mask the other, so findings get lost or misranked. ## 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, incorrect implementations) as parallel sub-agents, then reports them side by side. - Fixed-point diffing: Reviews the diff between HEAD and any user-supplied commit, branch, tag, or merge-base, validating the ref and diff before spawning reviewers. - Spec discovery: Locates the originating spec from issue references in commit messages, user-supplied paths, 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 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 a git 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 merge-base comparison. It then runs two parallel sub-agents: one checks documented standards and code smells, the other checks the originating spec.

How does the code review find the originating spec or issue?

It looks for issue references in commit messages first, then a user-supplied path, then spec files under docs/, specs/, or .scratch/ matching the branch or feature. If nothing is found, it asks the user, and the Spec axis reports no spec available.

What happens if the repo has no documented coding standards?

The Standards axis falls back to a fixed baseline of Fowler code smells such as Duplicated Code, Feature Envy, and Shotgun Surgery. These are reported as labelled judgement calls, never hard violations, and documented repo standards always override the baseline.

Can I review work-in-progress changes instead of a finished PR?

Yes. Any fixed point works, including HEAD~5, a tag, or an arbitrary commit, as long as the ref resolves and the diff is non-empty. The skill validates both before spawning the review sub-agents.

Why are standards and spec findings reported separately?

A change can pass one axis and fail the other, such as clean code implementing the wrong thing. Keeping the reports separate under distinct headings prevents one axis from masking or reranking the other's findings.