skills.rest
tinner-deinno
tinner-deinnoCOMMUNITY
Explore all skills by this author →
GitHub

gsd-review

Generate cross-AI peer reviews of phase plans into REVIEWS.md.

1|Updated May 24, 2026
Search Tags:#multi-agent#phase planning#peer review#CLI orchestration#gsd#structured feedback#codebase workflow
One-click install
npx skills add https://github.com/tinner-deinno/innova-skills-lib --skill gsd-review-tinner-deinno
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gsd-review
Source: https://github.com/tinner-deinno/innova-skills-lib/tree/main/core/gsd/gsd-review
Command: npx skills add https://github.com/tinner-deinno/innova-skills-lib --skill gsd-review-tinner-deinno

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It reduces planning blind spots by getting independent cross-AI feedback on phase plans before you execute them.

Core Features & Use Cases

  • Cross-CLI peer review: Prompts multiple external AI CLIs (Gemini, Claude, Codex, OpenCode, Qwen Code, Cursor) to critique the same phase plan.
  • Structured output for reuse: Produces a single REVIEWS.md file containing per-reviewer feedback that you can feed back into planning.
  • Phase-scoped reviews: Targets a specific phase number so reviewers assess the right plan slice without ambiguity.

Use case: you have a multi-phase rollout (e.g., engineering execution plan) and want confidence that each phase is complete, logically ordered, and missing nothing critical before running it.

Quick Start

Ask your agent to run gsd-review for a specific phase number by saying: gsd-review --phase 2 --all.

Frequently Asked Questions about gsd-review

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

FAQPage Schema
How do I get multiple AI models to peer review my software phase plans?▼

Cross-AI peer review of phase plans is done by invoking multiple external AI CLIs to critique the same phase plan, collecting their independent feedback, and writing a structured REVIEWS.md file for reuse.

What is the best way to surface missing risks in a multi-phase engineering execution plan?▼

The best way to surface missing risks is cross-AI peer review, which prompts independent external AI CLIs to evaluate a specific phase plan and identify gaps, inconsistencies, and missing risks before execution.

How do I run a phase-scoped review using multiple external AI CLIs?▼

You run a phase-scoped review by asking your agent to execute a CLI orchestration command targeting a specific phase number, which detects available CLIs, generates reviewer prompts, and invokes each selected CLI for independent feedback.

Does cross-AI peer review work with different external AI CLIs like Gemini and Claude?▼

Yes, cross-AI peer review works with different external AI CLIs including Gemini, Claude, Codex, OpenCode, Qwen Code, and Cursor by detecting available CLIs and generating specific reviewer prompts for each selected tool.

What output format does multi-agent peer review produce for reuse in planning?▼

Multi-agent peer review produces a single structured REVIEWS.md file containing per-reviewer feedback, which you can feed back into your multi-phase planning workflow to improve execution confidence.

When do I need cross-AI feedback on phase plans?▼

You need cross-AI feedback on phase plans when you have a multi-phase rollout and want confidence that each phase is complete, logically ordered, and missing nothing critical before running it.

Related Skills

Explore More Software Engineering Skills→
gesmith0606gesmith0606

gsd-review

Invoke external AI CLIs to review phase plans and write REVIEWS.md.

Community
Intermediate
dobrinz123dobrinz123

gsd-review

Invoke Gemini, Claude, Codex, and OpenCode CLIs to generate per-reviewer feedback and write REVIEWS.md.

Community
Advanced
rjroyrjroy
6

implement

Delegate coding, testing, and review tasks to specialized agents with phased execution.

Community
Advanced
richardcbrichardcb
15

code-review

Audit implemented code against technical plans and AI-specific risks.

Community
Advanced