deep-review

Orchestrate parallel security, performance, architecture, and code-quality reviews of git diffs.

1|Updated Aug 18, 2025
One-click install
npx skills add https://github.com/abhinav8888/dot-files --skill deep-review-abhinav8888
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deep-review
Source: https://github.com/abhinav8888/dot-files/tree/main/claude/.claude/skills/deep-review
Command: npx skills add https://github.com/abhinav8888/dot-files --skill deep-review-abhinav8888

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates expert-level reviews of code changes or plans by coordinating four specialized reviewers in parallel, reducing cycle time and improving review quality.

Core Features & Use Cases

  • Parallel expert reviews: Security, Performance, Architecture, and Code Quality analyses run simultaneously.
  • Diff and plan agnostic: Accepts git diff, staged changes, or a textual plan description; passes relevant data to all agents.
  • Deterministic orchestration: Ensures consistent reviewer inputs and passes full file content for thorough assessment.

Quick Start

Provide the diff or plan to initiate the four-agent review workflow and obtain multi-faceted feedback.

Frequently Asked Questions about deep-review

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

FAQPage Schema
How do I automate a code review for a git diff?

Automate a code review for a git diff by passing the changeset to a parallel orchestration workflow. Specialized agents analyze the full diff and changed file list simultaneously to produce staff-engineer-grade feedback.

What is the best way to analyze staged changes for security and performance issues?

To analyze staged changes for security and performance issues, use a parallel review workflow that routes the diff to specialized agents, yielding simultaneous expert assessments across multiple architectural dimensions.

Can I review a textual implementation plan instead of a code diff?

Yes, you can review a textual implementation plan. The orchestration workflow accepts plan text as input, passing the description to specialized agents for architecture and security analysis.

How does parallel code review work for a changeset?

Parallel code review works by coordinating four specialized agents that run simultaneously using the opus model. Each agent receives the full file content and diff to independently assess security, performance, architecture, and code quality.

What are the limitations of automated parallel code reviews?

Automated parallel code reviews require passing the full diff and changed files to the agents, which may consume significant processing resources for large changesets. Reviews are limited to security, performance, architecture, and code quality dimensions.