se-code-review

Orchestrate multi-agent code reviews and generate structured findings reports.

Updated May 7, 2026

Search Tags:#multi-agent #code-review #ai-agents #diff-analysis #pr-workflow #plan-verification

Ready to run

npx skills add https://github.com/simonwjackson/pi-software-engineering --skill se-code-review

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: se-code-review
Source: https://github.com/simonwjackson/pi-software-engineering/tree/main/skills/se-code-review
Command: npx skills add https://github.com/simonwjackson/pi-software-engineering --skill se-code-review

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires bash, git, gh, jq, awk, sed, grep, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Organizes and automates complex code-review workflows by spawning multiple reviewer personas, consolidating findings, and providing a structured report for PR decisions.

Core Features & Use Cases

Automated, multi-agent code reviews that cover correctness, testing, maintainability, standards, security, and more.
Supports PR-based reviews, standalone current-branch reviews, and branch-based reviews with base resolution.
Generates a single, deduplicated report with evidence and suggested fixes, ready for ticketing or merging.

Quick Start

Provide a patch or PR link to trigger the review workflow and receive a structured results report.

Frequently Asked Questions about se-code-review

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

FAQPage Schema

How do I automate multi-agent code review for pull requests?▼

Multi-agent code review automates PR analysis by spawning reviewer subagents to evaluate correctness, testing, maintainability, and security. It uses git, gh, and jq to compute diffs and assemble a structured, deduplicated report with suggested fixes.

Can I review a standalone git branch without creating a pull request?▼

Yes, standalone current-branch reviews are supported without a pull request. The workflow computes branch diffs using fork-safe base resolution, enabling direct code analysis and structured findings generation.

What dependencies do I need to run AI-assisted PR workflow analysis?▼

AI-assisted PR workflow analysis requires bash, git, gh, jq, awk, sed, and grep installed. These command-line tools fetch PR metadata, compute diffs, parse JSON, and assemble the final review report artifacts.

Does multi-agent diff analysis cover security and maintainability standards?▼

Multi-agent diff analysis covers correctness, testing, maintainability, standards, and security. Multiple reviewer personas evaluate the patch concurrently, consolidating findings into a single deduplicated report with evidence and suggested fixes.

What is the best way to consolidate findings from multiple AI code reviewers?▼

The best way to consolidate AI reviewer findings is to orchestrate subagents that return structured, deduplicated reports. This workflow assembles evidence and suggested fixes into a single artifact ready for PR decisions.

How does fork-safe base resolution work for branch-based code reviews?▼

Fork-safe base resolution for branch-based code reviews automatically identifies the correct base commit in forked repositories. It relies on git and gh to fetch metadata and compute accurate diffs across fork boundaries.