skills.rest
Maleick
MaleickCOMMUNITY
Explore all skills by this author →
GitHub

peer-review

Orchestrate multi-LLM peer review using Codex and Gemini CLIs.

6|1|Updated Mar 7, 2026
Search Tags:#code review#feedback#brainstorming#codex#llm#gemini#peer review
One-click install
npx skills add https://github.com/Maleick/peer-review --skill peer-review-maleick
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: peer-review
Source: https://github.com/Maleick/peer-review/tree/main/.claude/skills/peer-review
Command: npx skills add https://github.com/Maleick/peer-review --skill peer-review-maleick

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides structured, multi-perspective feedback on plans, ideas, and code by orchestrating reviews from multiple AI models, enabling users to make more informed decisions.

Core Features & Use Cases

  • Multi-LLM Orchestration: Leverages Codex and Gemini for diverse viewpoints.
  • Structured Feedback: Synthesizes critiques into actionable Decision Packets.
  • Multiple Modes: Supports review, idea generation, red-teaming, debate, and more.
  • Use Case: Before committing to a new feature design, use /peer-review review to get implementation-focused feedback from Codex and architectural insights from Gemini, ensuring a robust plan.

Quick Start

Use the peer-review skill to get a structured review of your plan for adding a new caching layer.

Frequently Asked Questions about peer-review

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

FAQPage Schema
How do I get multi-LLM feedback on a code design before implementation?▼

Multi-LLM feedback is generated by dispatching prompts to Codex and Gemini CLIs for structured review. The Skill orchestrates cross-examination between models to synthesize diverse architectural and implementation viewpoints into actionable Decision Packets.

What is the best way to run a premortem or red-teaming analysis on a new feature plan?▼

Running a premortem or red-teaming analysis is supported through dedicated operational modes. You can dispatch your feature plan to the Skill, which prompts the configured LLMs to cross-examine the idea and surface potential failure points or security vulnerabilities.

Do I need Codex and Gemini CLIs installed to use multi-model code review?▼

Codex and Gemini CLIs must be installed and authenticated to perform multi-model code review. The Skill acts as an orchestrator that dispatches prompts directly to these external command-line interfaces to generate diverse feedback.

Can I analyze git diffs for performance and API design using multiple AI models?▼

Git diffs can be analyzed using the dedicated git diff review, performance analysis, and API design modes. These modes dispatch your code changes to Codex and Gemini, synthesizing structured feedback on performance bottlenecks and architectural impacts.

How does cross-examination work in LLM-based peer review?▼

Cross-examination in LLM-based peer review works by dispatching prompts to multiple models and synthesizing their structured feedback. This multi-LLM orchestration ensures diverse viewpoints cross-check each other, producing comprehensive Decision Packets for informed decisions.

Related Skills

Explore More Software Engineering Skills→
Moliboy5000Moliboy5000

ask

Query local Claude, Codex, or Gemini CLIs and persist outputs as reusable artifacts.

Community
Intermediate
OniroHuaverOniroHuaver
30

edit-figma-design

Convert natural language descriptions into Figma designs via API calls.

Community
Advanced
jangtrinhjangtrinh

ck:code-review

Detect security flaws and failure modes in PR diffs and codebases via adversarial red-teaming review.

Community
Advanced
mataaninmataanin
1

multi-review

Coordinate parallel LLM code reviews and compare cross-tool agreements.

Community
Advanced