team-review

Orchestrate parallel subagent code reviews across security, correctness, testing, and architecture.

3|1|Updated Feb 7, 2026
One-click install
npx skills add https://github.com/yon/agentic-dev-os --skill team-review
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: team-review
Source: https://github.com/yon/agentic-dev-os/tree/main/.claude/skills/team-review
Command: npx skills add https://github.com/yon/agentic-dev-os --skill team-review

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill addresses the need for comprehensive and multi-faceted code reviews, especially for large or complex changes, by leveraging specialized subagents to analyze code from various perspectives simultaneously.

Core Features & Use Cases

  • Parallel Review: Spawns multiple specialized review agents (security, code quality, testing, architecture) to work concurrently.
  • Scope Definition: Allows reviews of all uncommitted changes, staged changes, or specific files/directories/commit ranges.
  • Synthesized Reporting: Consolidates findings from all subagents into a single, structured review report with severity ratings.
  • Use Case: When submitting a significant feature impacting multiple modules, use /team-review to get a holistic assessment covering security vulnerabilities, architectural soundness, test coverage, and general code quality before merging.

Quick Start

Use the team-review skill to analyze all uncommitted changes in the current directory.

Frequently Asked Questions about team-review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run a parallel code review across multiple modules?

Run a parallel code review by spawning specialized subagents that concurrently analyze code changes across security, correctness, testing, and architecture dimensions. This orchestrates multiple read-only reviews simultaneously to provide a holistic assessment for large changes.

What is the best way to review large code changes for security and architecture?

The best way to review large code changes is using parallel subagents to analyze security vulnerabilities and architectural soundness concurrently. This multi-dimensional approach synthesizes findings from specialized agents into a single structured report with severity ratings.

Can I scope a code review to specific files or staged changes?

Yes, you can scope code reviews to all uncommitted changes, staged changes, or specific files, directories, and commit ranges. This targets the parallel subagent analysis precisely to the desired code modifications.

How does a multi-agent code review synthesize its findings?

A multi-agent code review synthesizes findings by consolidating read-only reports from specialized subagents into a single, structured review report. The consolidated output includes severity ratings to help prioritize the identified issues.

When should I use parallel subagents for code quality assurance?

Use parallel subagents for code quality assurance when submitting significant features impacting multiple modules or when large changes require in-depth analysis. It is designed for comprehensive reviews spanning multiple perspectives like testing and security.

Does the subagent code review process modify my source code?

No, the subagent code review process does not modify source code. The specialized subagents generate read-only reports that are synthesized into a structured review document, ensuring your codebase remains untouched during analysis.