skills.rest
Iron-Ham
Iron-HamCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

deep-review

Run parallel multi-agent code quality reviews and output prioritized reports.

31|1|Updated Feb 5, 2026
Search Tags:#architecture#concurrency#CLAUDE.md#code-review#PR-analysis#deep-review
One-click install
npx skills add https://github.com/Iron-Ham/claude-deep-review --skill deep-review-iron-ham
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: deep-review
Source: https://github.com/Iron-Ham/claude-deep-review/tree/main
Command: npx skills add https://github.com/Iron-Ham/claude-deep-review --skill deep-review-iron-ham

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Claude Deep Review consolidates architecture analysis, code review, error handling audit, type design analysis, comment verification, test coverage analysis, concurrency analysis, and code simplification into a single command, enabling teams to surface and prioritize issues efficiently.

Core Features & Use Cases

  • 14 specialized review agents run in parallel for thorough analysis
  • Flexible scope detection: review PR changes, uncommitted work, or specific paths
  • Modular aspects: run all agents or select specific review types
  • Prioritized output: Critical, Important, or Suggestions
  • Architecture health assessment and actionable reports
  • Standalone tool with no dependencies on other plugins
  • Suitable for pre-merge PR reviews, feature completion checks, and ongoing code health audits

Quick Start

Run the deep-review tool on the current branch or a specific path, e.g. /deep-review, with flags to tailor scope and aspects.

Frequently Asked Questions about deep-review

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

FAQPage Schema
How do I run a deep code review on uncommitted changes or a specific path?▼

You can run a deep code review by executing the tool on your current branch or a specific path, using flexible scope detection to analyze uncommitted work, PR changes, or targeted directories.

What is parallel multi-agent code quality analysis and how does it work?▼

Parallel multi-agent code quality analysis orchestrates 14 specialized review agents to concurrently assess architecture, error handling, type design, test coverage, and concurrency, synthesizing results into a single prioritized report.

Can I select specific review aspects like architecture and concurrency instead of running all agents?▼

Yes, you can select specific modular aspects like architecture, concurrency, or test coverage analysis to run individually, rather than executing all 14 agents for your code review.

Do I need external plugins or dependencies to analyze PR changes for architecture health?▼

No, you do not need external plugins or dependencies to analyze PR changes for architecture health, as this is a standalone tool requiring no additional plugin installations.

How are code review issues classified and prioritized in the final report?▼

Code review issues are classified into NEW versus PRE-EXISTING categories and prioritized as Critical, Important, or Suggestions, helping teams surface and resolve the most impactful problems efficiently.

Related Skills

Explore More Software Engineering Skills→
kfolkeskfolkes
2

pr-reference

Generate structured XML documents of commit history and diffs between branches.

Community
Intermediate
J-PsterJ-Pster
291

receiving-code-review

Prioritize and resolve critical code-review findings before commits.

Community
Intermediate
yocxy2yocxy2

land-and-deploy

Merge pull requests and verify production deployment health with canary checks.

Community
Advanced
atxinskyatxinsky
4

dispatching-parallel-agents

Dispatch parallel agents to investigate independent test failures concurrently.

Community
Basic