gsd-code-review

Automate phase-based code-change reviews and generate severity-classified REVIEW.md findings.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Review source files changed during a phase for bugs, security vulnerabilities, and code quality problems, producing a concise assessment that helps teams ship safer code.

Core Features & Use Cases

  • Automated phase reviews: Analyze changes introduced in a phase to surface defects, security issues, and quality gaps.
  • Depth control: Support quick, standard, and deep analysis to balance speed and thoroughness.
  • Artifact generation: Produce a REVIEW.md in the phase directory with severity-classified findings for traceability.
  • Scoped analysis: Optionally limit the review to specific files via a --files list for targeted checks.

Quick Start

Run phase 2 code review with standard depth to generate the phase 2 artifact.

Frequently Asked Questions about gsd-code-review

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

FAQPage Schema
How do I automate code review for a Git diff to detect security vulnerabilities?

Automated code review analyzes your Git diff to detect security vulnerabilities, bugs, and quality issues. It performs a phase-based assessment of changed source files and produces a structured REVIEW.md artifact with severity-classified findings for traceability.

What is the best way to scope a code quality analysis to specific files?

Scoping code quality analysis to specific files is supported via an optional file list input. This targets the review checks toward selected changed files rather than the entire phase, allowing for faster and more focused automated security and quality assessments.

How do I control the depth of an automated code review to balance speed and thoroughness?

You can control code review depth using quick, standard, or deep analysis modes. Depth control allows you to balance the speed of the automated review against the thoroughness of bug, security vulnerability, and quality issue detection for your phase changes.

Does automated phase-based code review require a specific project structure?

Automated phase-based code review applies to workflows where a Git diff or phase artifacts are available. It requires a phase-number input to identify the changes and generates a REVIEW.md artifact directly in the corresponding phase directory for traceability.

Why generate a REVIEW.md artifact for code changes instead of inline comments?

Generating a REVIEW.md artifact for code changes provides a persistent, structured assessment with severity-classified findings. This ensures traceability of detected bugs, security vulnerabilities, and quality issues within the phase directory, unlike transient inline comments.

Can I run a code review on phase artifacts without a direct Git diff?

Yes, automated code review supports phase-based work where phase artifacts are available even without a direct Git diff. It analyzes these artifacts to surface defects, security issues, and quality gaps, outputting a structured REVIEW.md with classified findings.