skills.rest
rpelizza
rpelizzaCOMMUNITY
Explore all skills by this author →
GitHub

pelizzai-review

Review code against specifications with blind, evidence-based verification.

Updated Jun 26, 2026
Search Tags:#quality assurance#code review#verification#compliance#software architecture#pelizzai
One-click install
npx skills add https://github.com/rpelizza/PelizzAI --skill pelizzai-review
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pelizzai-review
Source: https://github.com/rpelizza/PelizzAI/tree/main/.agents/skills/pelizzai-review
Command: npx skills add https://github.com/rpelizza/PelizzAI --skill pelizzai-review

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill eliminates superficial code reviews and "rubber-stamping" by enforcing a structured, blind, and evidence-based verification process that catches defects before they propagate into the codebase.

Core Features & Use Cases

  • Asymmetric Blind Review: Implements a split-lens approach where the spec reviewer evaluates code against requirements without seeing the author's narrative, preventing confirmation bias.
  • Fresh Evidence Verification: Mandates that reviewers actually execute tests, linters, or build commands to verify claims, rather than relying on the author's report.
  • Use Case: Use this skill during the execution of a complex feature plan to ensure that every task is independently verified for compliance with the spec and technical quality before integration.

Quick Start

Use the pelizzai-review skill to perform a blind spec review and quality assessment on the current working tree.

Frequently Asked Questions about pelizzai-review

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

FAQPage Schema
What is blind code review and how does it prevent confirmation bias?▼

Fresh evidence verification in code review mandates executing tests, linters, or build commands to validate claims. This prevents rubber-stamping by ensuring reviewers independently confirm code quality and compliance rather than relying on author reports.

How do I perform an evidence-based code review on my working tree?▼

Task-based development cycles require independent verification to ensure every task meets architectural integrity and specification compliance. This structured review process catches defects during execution before they propagate into the codebase through superficial validation.

Can I use this code review process for software architecture and compliance checks?▼

Yes, this code review process enforces multi-lens verification that validates implementation against technical quality standards and software architecture requirements. It applies to task-based development cycles to ensure compliance and architectural integrity during integration.

What are the limitations of asymmetric blind review for complex feature plans?▼

Asymmetric blind review requires strict adherence to the split-lens profile and mandatory fresh evidence verification. This rigorous process may add overhead to simple tasks but is essential for complex feature plans where independent verification prevents defect propagation.

Related Skills

Explore More Software Engineering Skills→
ArvorCoArvorCo
96

constitution

Create or update a project constitution defining coding principles and governance rules.

Community
Advanced
fall-out-bugfall-out-bug
19

hotfix

Create a hotfix branch from main and deploy minimal P0 fixes.

Community
Advanced
wildwasserwildwasser
35

verification-before-completion

Run fresh verification commands and report evidence before declaring work complete.

Community
Intermediate
OneWave-AIOneWave-AI
245

code-review-pro

Review code for security vulnerabilities, performance bottlenecks, and maintainability issues.

Official
Basic