agentic-review

Reviews local Git changes with parallel specialized agents for prioritized, actionable findings.

11|1|Updated Mar 3, 2026
One-click install
npx skills add https://github.com/SZoloth/skill-pack --skill agentic-review
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agentic-review
Source: https://github.com/SZoloth/skill-pack/tree/main/skills/agentic-review
Command: npx skills add https://github.com/SZoloth/skill-pack --skill agentic-review

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Deep multi-agent code review for personal repos. Analyzes changes, prioritizes files, spawns specialized review agents in parallel, and synthesizes actionable findings.

Core Features & Use Cases

  • Spawns parallel specialized agents (security, performance, patterns, architecture) to analyze changes
  • Produces prioritized, actionable findings with clear remediation steps
  • Useful for review before committing, pushing, or comparing branches

Quick Start

Run skill agentic-review to perform a comprehensive, parallelized review of your local changes across staged, unstaged, or branch differences.

Frequently Asked Questions about agentic-review

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

FAQPage Schema
How do I run a multi-agent code review on local git changes?

Multi-agent code review of local git changes is performed by running the skill, which analyzes staged, unstaged, or branch differences. It spawns parallel specialized agents for security, performance, and architecture to synthesize actionable findings.

What is multi-agent code review and how does it identify architectural issues?

Multi-agent code review is an analysis process that spawns parallel specialized agents to examine code changes. It identifies architectural issues by deploying dedicated agents to evaluate structural patterns and synthesize prioritized findings for remediation.

Can I review specific commits or branch diffs without pushing to a remote repository?

Yes, you can review specific commits or branch diffs without pushing. The code review operates entirely on local git context, requiring no remote access to analyze differences and generate structured, actionable remediation steps.

How does multi-agent code review prioritize findings for security and performance issues?

Multi-agent code review prioritizes security and performance findings by running dedicated agents in parallel across changed files. It synthesizes outputs into a structured format, ranking issues to provide clear, actionable remediation steps.

What is the best way to analyze code for security and performance issues before committing changes?

The best way to analyze code for security and performance issues before committing is using a multi-agent code review skill. It evaluates local staged and unstaged changes in parallel, outputting structured, prioritized findings for immediate remediation.