sdd-review

Automate Spec-Driven Development reviews with parallel code, security, architecture, and performance checks.

1|Updated Apr 25, 2026

Search Tags:#code review #software quality #review #spec-driven development #review automation

Ready to run

npx skills add https://github.com/dariomazzitellireplik-coder/sdd-skills --skill sdd-review-dariomazzitellireplik-coder

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: sdd-review
Source: https://github.com/dariomazzitellireplik-coder/sdd-skills/tree/main/skills/sdd-review
Command: npx skills add https://github.com/dariomazzitellireplik-coder/sdd-skills --skill sdd-review-dariomazzitellireplik-coder

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

The sdd-review Skill automates the review phase of Spec-Driven Development, allowing developers to validate the implementation of code and documentation before shipping.

Core Features & Use Cases

Automated Checks: Executes tests, linters, formatters, and builds to ensure code quality.
Parallel Reviews: Invokes multiple subagents to perform code reviews, security audits, architecture checks, and performance evaluations.
Confidence Scoring: Applies a confidence score to review findings to help decide whether issues are blocking, need user input, or can be ignored.

Quick Start

After completing the 'sdd-execute' phase, use the command /sdd-review to automatically run reviews and get feedback.

Frequently Asked Questions about sdd-review

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

FAQPage Schema

How do I automate code review for Spec-Driven Development?▼

Automated review for Spec-Driven Development runs tests, linters, and builds while invoking parallel subagents for security, architecture, and performance checks to validate implementation quality.

What is the best way to ensure architecture adherence before shipping code?▼

Architecture adherence is ensured by invoking parallel reviews from an architect-reviewer and code-reviewer, applying confidence scores to findings to determine blocking issues before shipping.

Can I run security audits and performance evaluations in parallel during a code review?▼

Yes, security audits and performance evaluations run in parallel by invoking security-auditor and performance-engineer subagents alongside automated checks to provide comprehensive review feedback.

How does confidence scoring work for code review findings?▼

Confidence scoring applies to code review findings to help developers decide whether issues are blocking, require manual user input for edge cases, or can be safely ignored.

When do I need manual review for edge cases in review automation?▼

Manual review for edge cases is needed when automated checks and parallel subagent reviews identify low-confidence findings that require user input to validate against predefined standards.