gsd-review

Execute cross-AI peer reviews of phase plans and collect feedback into REVIEWS.md.

Updated Feb 11, 2026

Search Tags:#workflow automation #ai #phase planning #peer review #prompting #git-based docs #codebase iteration

Ready to run

npx skills add https://github.com/ArtRiv/game-topicos-especiais --skill gsd-review-artriv

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: gsd-review
Source: https://github.com/ArtRiv/game-topicos-especiais/tree/main/.github/skills/gsd-review
Command: npx skills add https://github.com/ArtRiv/game-topicos-especiais --skill gsd-review-artriv

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It reduces the risk of missing issues in phase planning by obtaining independent critiques from multiple external AI CLIs, instead of relying on a single perspective.

Core Features & Use Cases

Cross-AI peer review: Triggers separate reviews from selected CLIs (Gemini, agent/Claude, Codex) for the same phase plan.
Structured output for iteration: Produces a consistent REVIEWS.md containing per-reviewer feedback suitable for follow-up planning.
Flag-driven scope control: Lets you include specific reviewers or use --all to cover available CLIs for a given phase.

Use case: you draft a multi-step phase plan and want independent validation before executing, especially when correctness, completeness, or sequencing is critical.

Quick Start

Run the skill to review phase 3 by calling the appropriate CLI command with the argument --phase 3 and any reviewer flags you want.

Frequently Asked Questions about gsd-review

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

FAQPage Schema

How do I get cross-AI peer review for phase planning?▼

Cross-AI peer review for phase planning is achieved by triggering independent critiques from multiple AI CLIs like Gemini, Claude, or Codex. This reduces oversight risk by collecting independent feedback instead of relying on a single perspective.

What is the best way to validate a multi-step phase plan before execution?▼

Validating a multi-step phase plan is best done by obtaining independent critiques from external AI CLIs. You can trigger separate reviews for the same phase plan to ensure correctness, completeness, and proper sequencing before execution.

How do I run a peer review on a specific phase using external AI CLIs?▼

To run a peer review on a specific phase, execute the configured workflow by calling the CLI command with the argument --phase N. You can include specific reviewer flags or use --all to cover available CLIs.

Can I select specific AI models like Gemini or Codex for my workflow automation?▼

Yes, you can select specific AI models for workflow automation using flag-driven scope control. You can include specific reviewers like Gemini, Claude, or Codex, or use a flag to cover all available CLIs for a given phase.

How does cross-AI peer review output feedback for downstream planning?▼

Cross-AI peer review outputs feedback by collecting responses into a structured REVIEWS.md file. This file contains per-reviewer feedback suitable for follow-up planning and downstream use by phase planning commands.

When do I need independent critiques for codebase iteration cycles?▼

You need independent critiques for codebase iteration cycles when correctness, completeness, or sequencing is critical. Obtaining critiques from multiple AI CLIs improves planning quality and reduces the risk of missing issues across iterations.