full-code-review

Official

Coordinate code reviews with parallel subagents.

Authorliminal-ai
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Orchestrate a comprehensive multi-pass code review by coordinating six specialized reviewers to surface diverse findings and deliver a single verified report.

Core Features & Use Cases

  • Orchestrates six specialized review types (standard, security, performance, architecture, test-coverage, silent-failure) in parallel and synthesizes results into a unified report.
  • Supports all scope modes: PRs, uncommitted changes, branch-vs-branch comparisons, and ad-hoc file or directory reviews.
  • Use Case: Review a feature branch against main to surface issues across multiple domains and deliver a consolidated report.
  • Explicitly delegates code review to subagents; it coordinates the workflow and delivers a comprehensive result.

Quick Start

Launch a full-code-review to orchestrate all six reviewers and generate the final report.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: full-code-review
Download link: https://github.com/liminal-ai/code-steward/archive/main.zip#full-code-review

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.