gsd-review

Coordinate cross-AI peer reviews of phase plans from external AI CLIs.

1|Updated Apr 7, 2026
One-click install
npx skills add https://github.com/TruCol270/salty-pickle --skill gsd-review-trucol270
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gsd-review
Source: https://github.com/TruCol270/salty-pickle/tree/main/.claude-skills/gsd-review
Command: npx skills add https://github.com/TruCol270/salty-pickle --skill gsd-review-trucol270

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Cross-AI peer review of phase plans to improve quality and reduce bias by aggregating independent feedback from external AI CLIs.

Core Features & Use Cases

  • Multi-CLI reviews: Gather insights from Gemini, Claude, Codex, and OpenCode to assess phase plans.
  • Structured REVIEWS.md: Produce per-reviewer feedback compiled into a single document for quick integration.
  • Feedback integration: Feed reviews back into planning via /gsd-plan-phase --reviews for iterative improvement.

Quick Start

Run the gsd-review workflow for a specific phase by specifying --phase N and optional CLI flags.

Frequently Asked Questions about gsd-review

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

FAQPage Schema
What is cross-AI peer review for phase plans?

Cross-AI peer review for phase plans aggregates independent feedback from multiple AI CLIs, like Gemini and Claude, to improve plan quality and reduce single-model bias.

How do I aggregate peer reviews from multiple AI CLIs into one document?

Aggregate peer reviews by running an automated workflow that invokes each AI CLI, gathers independent responses, and compiles per-reviewer notes into a single structured REVIEWS.md file.

Can I gather feedback from Gemini, Claude, Codex, and OpenCode simultaneously?

Yes, you can gather feedback from Gemini, Claude, Codex, and OpenCode by using a workflow that detects external AI CLIs, builds review prompts, and invokes each one to assess your phase plans.

How do I integrate cross-AI feedback back into phase planning?

Integrate cross-AI feedback by feeding the compiled REVIEWS.md document back into your planning workflow using iterative improvement commands to refine the phase plan.

What's the best way to automate AI peer reviews for software engineering phase plans?

The best way to automate AI peer reviews is using a CLI workflow that specifies the phase number, builds prompts, invokes multiple AI CLIs, and writes aggregated feedback directly to a markdown file.

Do I need to manually copy prompts between AI CLIs to get independent phase plan reviews?

No, you do not need to manually copy prompts because the workflow automatically detects available AI CLIs, constructs review prompts, and invokes each CLI independently to gather feedback.