Run any Skill in Manus with one click

multi-review

Stars2

Forks1

UpdatedJanuary 14, 2026 at 12:03

Full project code review using multiple AI CLIs (Claude, Gemini, Codex). Use when user wants comprehensive multi-perspective code review.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

ThrownLemon

ThrownLemon/claude-code-plugins

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software Quality Assurance Analysts and TestersComputer and Mathematical Occupations·SOC 15-1253

SKILL.md

readonly

name	multi-review
description	Full project code review using multiple AI CLIs (Claude, Gemini, Codex). Use when user wants comprehensive multi-perspective code review.
triggers	["multi ai review","multi-ai review","review with multiple ais","compare ai reviews","get opinions from multiple ais","run parallel review","claude gemini codex review","consensus review","multi-perspective review","cross-check my code","what do different ais think","full project review","comprehensive code review","review with all ais","ai consensus on code"]

Multi-AI Code Review Skill

When the user wants a comprehensive code review using multiple AI perspectives, delegate to the review-coordinator subagent.

When to Use

Use this skill when the user:

Asks for a "multi-AI" or "multi-perspective" review
Wants to compare what different AI tools think about their code
Asks for "consensus" or "cross-checking"
Mentions Claude + Gemini + Codex reviewing together
Wants a "comprehensive" or "full project" review
Asks what different AIs think about their code

Default Behavior

CLIs: All three (claude, gemini, codex)
Focus: Comprehensive (all categories)
Timeout: 10 minutes per CLI

What the Subagent Does

The review-coordinator subagent will:

Validate Prerequisites
- Check which CLIs are installed
- Report any missing CLIs with install instructions
- Continue with available CLIs
Execute Parallel Reviews
- Run all available CLIs simultaneously
- Monitor for completion or timeout
- Handle failures gracefully
Aggregate Results
- Parse findings from each CLI
- Match similar issues using fuzzy matching
- Categorize by agreement level
Present Comparison Report
- Consensus findings (all agree) - highest confidence
- Majority findings (2+ agree) - likely valid
- Unique findings (1 found) - needs human judgment

Example User Requests

"Run a multi-AI review of this codebase"
"What do Claude, Gemini, and Codex think about my code?"
"Get a consensus review of my project"
"Compare AI opinions on this code"
"Do a comprehensive code review"
"Cross-check my code with multiple AIs"

Use the review-coordinator subagent to handle the review workflow.

More from this repository

same repository

fork-terminal

ThrownLemon/claude-code-plugins

Fork terminal sessions to spawn parallel AI agents or CLI commands in new terminal windows. Supports git worktrees for isolated parallel development.

2026-06-132

cr-local

ThrownLemon/claude-code-plugins

Local code review using CodeRabbit CLI. Use when user wants to review changes before committing or pushing.

2026-06-132

ui-ux-pro-max

ThrownLemon/claude-code-plugins

UI/UX design intelligence. 57 styles, 96 palettes, 50 font pairings, 25 charts, 11 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Search and apply design best practices.

2026-06-132

consult-second-opinion

ThrownLemon/claude-code-plugins

Use when the user asks for a "second opinion", "third opinion", "what does GLM/Gemini think", or wants another model to weigh in on code, design, or review. Routes to the consult plugin's CLI which calls z.ai (GLM-5.2) or Gemini directly via API.

2026-06-132

bambu-printer

ThrownLemon/claude-code-plugins

Automatically assist with Bambu Lab X1Plus 3D printer operations via the bambu CLI. Covers status checks, file transfer, print control, calibration, filament management, camera analysis, diagnostics, and SSH commands.

2026-05-152

unifi-network

ThrownLemon/claude-code-plugins

Auto-triggered skill for managing UniFi network devices, clients, sites, and diagnostics via the unifi CLI.

2026-05-152

Multi-AI Code Review Skill

When the user wants a comprehensive code review using multiple AI perspectives, delegate to the review-coordinator subagent.

When to Use

Use this skill when the user:

Asks for a "multi-AI" or "multi-perspective" review

Wants to compare what different AI tools think about their code

Asks for "consensus" or "cross-checking"

Mentions Claude + Gemini + Codex reviewing together

Wants a "comprehensive" or "full project" review

Asks what different AIs think about their code

Default Behavior

CLIs: All three (claude, gemini, codex)

Focus: Comprehensive (all categories)

Timeout: 10 minutes per CLI

What the Subagent Does

The review-coordinator subagent will:

Validate Prerequisites

Check which CLIs are installed
Report any missing CLIs with install instructions
Continue with available CLIs

Execute Parallel Reviews

Run all available CLIs simultaneously
Monitor for completion or timeout
Handle failures gracefully

Aggregate Results

Parse findings from each CLI
Match similar issues using fuzzy matching
Categorize by agreement level

Present Comparison Report

Consensus findings (all agree) - highest confidence
Majority findings (2+ agree) - likely valid
Unique findings (1 found) - needs human judgment

Example User Requests

"Run a multi-AI review of this codebase"

"What do Claude, Gemini, and Codex think about my code?"

"Get a consensus review of my project"

"Compare AI opinions on this code"

"Do a comprehensive code review"

"Cross-check my code with multiple AIs"

Use the review-coordinator subagent to handle the review workflow.