x-agents-cross-review

Coordinate multiple agents to review a scope from diverse perspectives.

1|1|Updated Feb 13, 2026
One-click install
npx skills add https://github.com/laststance/skills --skill x-agents-cross-review
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: x-agents-cross-review
Source: https://github.com/laststance/skills/tree/main/skills/x-agents-cross-review
Command: npx skills add https://github.com/laststance/skills --skill x-agents-cross-review

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Coordinates multiple agents to independently review the same scope from diverse perspectives to uncover blind spots and reduce bias.

Core Features & Use Cases

  • Parallel agents with distinct perspectives review the full scope, producing diverse analyses that are later consolidated.
  • Unified reporting mechanism combines insights into a single consensus document with evidence.
  • Phase-driven workflow from context gathering to progress tracking, enabling deterministic delivery for complex reviews.
  • Use Case: Evaluate a design spec or codebase where cross-review improves reliability and reduces missed edge cases.

Quick Start

Launch a multi-agent cross-review of the current scope to generate a unified assessment.

Frequently Asked Questions about x-agents-cross-review

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

FAQPage Schema
How do I use parallel agents to independently review the same codebase?

Multi-perspective cross-review assigns parallel agents distinct viewpoints to independently analyze the same scope, producing diverse analyses that are later consolidated into a single unified report with evidence and conclusions.

What is the best way to reduce bias when auditing complex requirements?

Cross-review minimizes bias by enforcing phase-based execution and assigning multiple agents independent perspectives from a perspectives library to audit complex requirements, ensuring consensus through a consolidated report.

How does a phase-based workflow work for multi-agent codebase reviews?

A phase-based workflow drives deterministic delivery for multi-agent reviews by progressing sequentially from context gathering to progress tracking, culminating in a single consensus document with evidence.

When do I need multi-perspective review for evaluating a design spec?

You need multi-perspective review when evaluating a design spec where reliability is critical and reducing missed edge cases is essential, allowing parallel agents to uncover blind spots before producing a unified assessment.

Can I use cross-review to generate a unified report with evidence and conclusions?

Yes, cross-review uses a unified reporting mechanism to combine insights from multiple agents into a single consensus document, integrating evidence and conclusions gathered during the independent review phases.

What are the limitations of using parallel agents for independent reviews?

Parallel agent reviews require strict phase-based execution and perspective assignment coordination, meaning the process is limited to scopes where deterministic delivery and consensus consolidation are structurally feasible.