background-reviewer

Name: background-reviewer
Availability: InStock
Author: Open330

Orchestrate parallel multi-LLM code reviews with specialized security, architecture, quality, and performance personas.

1|Updated Feb 19, 2026

Search Tags:#architecture #security #developer-tools #code-review #parallel-execution #multi-llm #persona-review

Ready to run

npx skills add https://github.com/Open330/agt --skill background-reviewer

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: background-reviewer
Source: https://github.com/Open330/agt/tree/main/agents/background-reviewer
Command: npx skills add https://github.com/Open330/agt --skill background-reviewer

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Orchestrates multi-LLM parallel code review with specialized agent personas (security, architecture, code quality, and performance).

Core Features & Use Cases

Persona-based reviews: each perspective generates structured findings (security, architecture, quality, performance).
Parallel execution: run all personas simultaneously to reduce review cycle time.
Round-based outputs and merges: save per-round findings and produce a consolidated summary for decision-making.

Quick Start

Run parallel persona reviews to begin multi-perspective code evaluation immediately.

Frequently Asked Questions about background-reviewer

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

FAQPage Schema

How do I run parallel code reviews for pull requests using multiple LLMs?▼

Execute parallel code reviews by orchestrating multiple LLMs to evaluate pull requests, diffs, and staged changes. This method deploys specialized personas for security, architecture, quality, and performance, generating structured findings suitable for merging and audit trails.

What is persona-based code review and how does it work?▼

Persona-based code review assigns specialized evaluation perspectives, such as security, architecture, code quality, and performance, to different LLM agents. Each persona generates structured findings independently, which are then merged into a consolidated summary for decision-making.

Can I review staged changes and diffs across different evaluation perspectives simultaneously?▼

Yes, you can evaluate staged changes and diffs across multiple perspectives simultaneously. The system orchestrates parallel execution of specialized personas, reducing review cycle time while applying security, architecture, quality, and performance evaluations to the provided changes.

Does multi-perspective code review require specific dependencies or external components?▼

No specific dependencies or external components are required to run multi-perspective code reviews. The system orchestrates specialized personas internally to evaluate pull requests and diffs, outputting per-round findings to a structured format without needing additional setup.

What is the best way to consolidate multi-LLM code review findings for audit trails?▼

The best way to consolidate multi-LLM code review findings is by using round-based outputs and merges. The system saves per-round findings from each persona and produces a consolidated summary in a structured format suitable for merging and audit trails.

When should I not use parallel persona reviews for code evaluation?▼

Avoid parallel persona reviews when evaluating trivial changes that do not require diverse evaluation perspectives. The multi-LLM approach is designed for pull requests, diffs, and staged changes needing comprehensive security, architecture, quality, and performance assessments.