skills.rest
compozy
compozyOFFICIAL
Explore all skills by this author →
Website𝕏@compozyaiGitHub

spec-peer-review

Facilitate cross-LLM peer reviews of code specifications with a specified model.

96|8|Updated Apr 9, 2026
Search Tags:#code review#LLM integration#specification analysis#peer review#compliance validation
One-click install
npx skills add https://github.com/compozy/kb --skill spec-peer-review
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: spec-peer-review
Source: https://github.com/compozy/kb/tree/main/.agents/skills/spec-peer-review
Command: npx skills add https://github.com/compozy/kb --skill spec-peer-review

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires comozy, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides a cross-LLM peer review mechanism for specs, ensuring comprehensive and unbiased feedback on code designs.

Core Features & Use Cases

  • Cross-LLM Peer Review: Facilitates reviews by different LLMs for a more thorough analysis.
  • Customizable Reviewer Runtime: Allows selection of different LLMs and models for reviews.
  • Project-Agnostic: Operates across any project, automatically discovering rule files.
  • Use Case: Before finalizing a new feature's design document, use this Skill to get an external review from a configured LLM, ensuring all aspects are covered and no critical issues are overlooked.

Quick Start

Run the spec-peer-review skill with the specific spec file and provide additional context if necessary: spec-peer-review [spec-path] --context file1.md,notebook.txt

Frequently Asked Questions about spec-peer-review

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

FAQPage Schema
How does cross-LLM peer review work for code specifications?▼

Cross-LLM peer review works by routing your code specifications to a specified LLM and model for independent analysis, generating a structured findings artifact that highlights compliance validation issues and design flaws.

How do I automate code review for my design documents before finalizing a feature?▼

You automate code review by running the spec-peer-review command with your target spec file path and optional context files, which triggers an external LLM to analyze the specification and output structured feedback.

Do I need Comozy installed to run specification analysis?▼

Yes, you need Comozy installed because this skill requires the Comozy runtime to execute the review process and run validation scripts that verify the integrity of the generated findings artifact.

Can I customize the LLM model used for specification analysis and peer review?▼

Yes, you can customize the reviewer runtime by selecting different LLMs and models during the peer review process, allowing you to leverage specific models for thorough specification analysis and compliance validation.

Does cross-LLM peer review require project-specific rule files to function?▼

No, the peer review mechanism is project-agnostic and automatically discovers relevant rule files within your project directory, ensuring the specification analysis adapts to your existing project standards.

What are the limitations of using LLM integration for specification analysis?▼

A key limitation is the strict dependency on validation scripts and the Comozy runtime; without these components, the system cannot execute the cross-LLM review or verify the integrity of the resulting findings artifact.

Related Skills

Explore More Software Engineering Skills→
CloudSenCloudSen

eliteforge-sonar-pmd-generator

Parse specification documents to generate governance artifacts and a configurable PMD rule set.

Community
Advanced
Cuki2910Cuki2910
1

brainstorming

Guide structured brainstorming and design validation with stakeholder feedback.

Community
Advanced
basilisk-labsbasilisk-labs
72

agentplane-local-dev-operator

Analyze changed files and run task-scoped validation for AgentPlane projects.

Official
Advanced
rysweetrysweet

debate-workflow

Facilitate structured multi-perspective debates for architectural decisions.

Community
Advanced