gsd-review

Orchestrate cross-AI peer reviews of project phase plans via external CLI tools.

1|Updated Apr 4, 2026
One-click install
npx skills add https://github.com/nnexai/git-stacks --skill gsd-review-nnexai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gsd-review
Source: https://github.com/nnexai/git-stacks/tree/main/.codex/skills/gsd-review
Command: npx skills add https://github.com/nnexai/git-stacks --skill gsd-review-nnexai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill addresses the lack of objective validation in AI-generated project plans by orchestrating multi-model peer reviews to identify gaps, risks, and logical inconsistencies before execution.

Core Features & Use Cases

  • Multi-CLI Orchestration: Automatically invokes various AI agents (Gemini, Claude, Codex, Qwen, etc.) to critique phase plans.
  • Structured Feedback: Aggregates diverse AI perspectives into a unified REVIEWS.md file for actionable planning.
  • Use Case: When developing a complex software architecture, use this skill to have multiple specialized AI models review your proposed phase plan to ensure technical feasibility and security compliance.

Quick Start

Invoke the gsd-review skill with the --all flag to trigger a comprehensive peer review of the current phase plan across all available AI models.

Frequently Asked Questions about gsd-review

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

FAQPage Schema
How do I run peer code review on AI-generated phase plans using multiple models?

To run peer code review on AI-generated phase plans, invoke the gsd-review skill with the --all flag, which orchestrates multi-agent execution across various AI CLI tools to validate technical workflows. It automatically aggregates diverse model feedback into a unified report.

What is multi-agent orchestration for collaborative validation of project workflows?

Multi-agent orchestration for collaborative validation involves invoking multiple external AI CLI tools to critique project phase plans. This mechanism aggregates diverse AI perspectives into a structured REVIEWS.md file to identify gaps, risks, and logical inconsistencies before execution.

Can I use multiple AI agents like Gemini and Claude to validate software architecture feasibility?

Yes, you can use multiple AI agents like Gemini and Claude to validate software architecture feasibility. The skill orchestrates cross-AI peer reviews by invoking specialized models to ensure technical feasibility and security compliance for complex phase plans.

Do I need specific AI CLI environments to aggregate feedback from diverse models?

Yes, you need specific AI CLI environments installed to aggregate feedback from diverse models. The multi-CLI orchestration requires integration with these environments and adherence to defined agent-spawning protocols to execute multi-model reviews successfully.

What is the best way to identify logical inconsistencies in technical workflows before execution?

The best way to identify logical inconsistencies in technical workflows before execution is cross-AI peer review. This approach automatically invokes various AI agents to critique phase plans, aggregating objective feedback into a structured REVIEWS.md file for actionable planning.

Why does multi-model code review require defined agent-spawning protocols?

Multi-model code review requires defined agent-spawning protocols to safely facilitate collaborative validation across different external AI CLI tools. These protocols ensure the multi-agent orchestration correctly invokes targets and aggregates structured feedback without execution conflicts.