gsd-review

Invoke Gemini, Claude, Codex, and OpenCode CLIs to review phase plans and write REVIEWS.md.

8|Updated Apr 9, 2026
One-click install
npx skills add https://github.com/D0NMEGA/donnyclaude --skill gsd-review-d0nmega
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gsd-review
Source: https://github.com/D0NMEGA/donnyclaude/tree/main/packages/skills/gsd-review
Command: npx skills add https://github.com/D0NMEGA/donnyclaude --skill gsd-review-d0nmega

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Reviews phase plans by invoking multiple external AI CLIs to generate independent, structured feedback.

Core Features & Use Cases

  • Automatically invoke external AI CLIs (Gemini, Claude, Codex, OpenCode) to review phase plans.
  • Produce a structured REVIEWS.md with per-reviewer feedback that can be fed back into planning via /gsd-plan-phase --reviews.
  • Suitable for software-project planning tasks that require multi-CLI validation and actionable feedback.

Quick Start

Provide the phase number and optional CLI flags to generate cross-CLI reviews for the current phase plan.

Frequently Asked Questions about gsd-review

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

FAQPage Schema
How do I get peer review feedback on software phase plans using multiple AI CLIs?

To get peer review feedback on phase plans using multiple AI CLIs, this Skill automatically invokes external tools like Gemini, Claude, Codex, and OpenCode. It generates independent, structured feedback for software-project planning validation.

What is the best way to validate phase plans across different AI models?

Validating phase plans across different AI models is best achieved by invoking multiple external AI CLIs independently. This approach detects available tools, prompts each for review, and collects structured actionable feedback into a unified document.

How does multi-CLI validation work for software-project planning tasks?

Multi-CLI validation works by detecting available AI CLIs on your system, invoking each with a specific review prompt for your phase plan, and collecting their independent responses. It follows a defined workflow to ensure comprehensive actionable feedback.

Can I use Gemini, Claude, Codex, and OpenCode together to review phase plans?

Yes, you can use Gemini, Claude, Codex, and OpenCode together to review phase plans. The Skill detects these available external AI CLIs, invokes each individually, and aggregates their independent structured feedback.

Do I need to manually format AI CLI responses for phase plan reviews?

You do not need to manually format AI CLI responses for phase plan reviews. The Skill automatically collects responses from each invoked CLI and writes a structured REVIEWS.md file containing all per-reviewer feedback.

How do I feed multi-CLI review feedback back into the planning workflow?

To feed multi-CLI review feedback back into the planning workflow, use the generated REVIEWS.md file. This structured document can be passed directly into your planning command via the --reviews flag to refine phase plans.