code-review

Reviews git diffs against standards, spec, and code contracts using parallel sub-agents.

9|Updated Jul 17, 2026
One-click install
npx skills add https://github.com/Yassimba/loom --skill code-review-yassimba
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: code-review
Source: https://github.com/Yassimba/loom/tree/main/skills/code-review
Command: npx skills add https://github.com/Yassimba/loom --skill code-review-yassimba

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Code reviews often conflate different concerns—style, correctness against the spec, and contract compliance—so one axis can mask failures in another. This Skill separates a change into independent review axes and runs them in parallel sub-agents so findings stay distinct and nothing gets lost. ## Core Features & Use Cases - Standards Axis: Checks the diff against documented repo standards plus a built-in baseline of Fowler code smells (Duplicated Code, Feature Envy, Shotgun Surgery, and more). - Spec Axis: Compares the diff against the originating issue or spec to find missing requirements, scope creep, and incorrect implementations. - Code Contracts Axis: When the repo defines @cc or CONTRACTS obligations, verifies the change complies with them. - Use Case: Before merging a feature branch, ask for a review since main. The Skill pins the fixed point, locates the spec and standards files, spawns parallel review sub-agents, and reports findings side by side under separate headings. ## Quick Start Use the code-review skill to review all changes on this branch since main against our coding standards and the originating spec.

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 a fixed point such as a commit SHA, tag, branch name, or HEAD~5, and the Skill diffs it against HEAD using a three-dot git diff. If you don't specify one, it asks before proceeding and fails early on bad refs or empty diffs.

How does this code review check compliance with a spec?

The Spec axis locates the originating spec from issue references in commit messages, a user-provided path, or spec files under ai-docs/, specs/, or .scratch/. A sub-agent then reports missing requirements, scope creep, and incorrect implementations with quoted spec lines.

What coding standards does the review check against?

It uses any documented repo standards such as CODING_STANDARDS.md or CONTRIBUTING.md, plus a built-in baseline of Fowler code smells like Duplicated Code and Feature Envy. Documented repo standards always override the baseline, and smells are reported as judgement calls.

Does the review support code contracts or invariants?

Yes, when the repository contains production @cc declarations or CONTRACTS files, a Code Contracts axis is enabled. A dedicated sub-agent runs the code-contracts verify procedure against the diff and reports violations with contract IDs and evidence.

Why are review findings split into separate sections?

Standards, Spec, and Code Contracts answer different questions, so a change can pass one axis and fail another. Keeping reports separate prevents one axis from masking failures in another, and findings are never merged or reranked across axes.