standard-review

Review code changes against project conventions and detect logic issues.

Updated Mar 16, 2026
One-click install
npx skills add https://github.com/liminal-ai/code-steward --skill standard-review
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: standard-review
Source: https://github.com/liminal-ai/code-steward/tree/main/.claude/plugins/code-steward-reviews/skills/standard-review
Command: npx skills add https://github.com/liminal-ai/code-steward --skill standard-review

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Performs a standard code review to determine if code does what it claims and is written well, serving as the senior developer's eyes on the code.

Core Features & Use Cases

  • Phase-driven methodology: Context Research, Comparative Analysis, and Issue Assessment.
  • Adheres to project conventions and identifies consistency with existing patterns.
  • Generates structured, actionable feedback for PR reviews and ad-hoc changes.

Quick Start

Begin by applying Phase 1 Context Research, then Phase 2 Comparative Analysis, and finally Phase 3 Issue Assessment to complete the standard review.

Frequently Asked Questions about standard-review

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

FAQPage Schema
How do I perform a senior code review on a pull request?

To perform a senior code review, analyze the PR diff using a phase-driven methodology: research context, compare existing patterns, and assess issues. This generates a structured, prioritized set of findings with actionable recommendations and clear rationale.

What is the best way to detect logic issues and edge cases in code changes?

The best way to detect logic issues and edge cases is through comparative analysis against project conventions. By applying pattern recognition to ad-hoc changes or PR diffs, you can triage quality issues within a senior developer's expectations.

How do I check if new code aligns with existing project conventions?

To check if code aligns with project conventions, apply comparative analysis to identify consistency with existing patterns. This ensures the new changes adhere to established standards during the standard review process.

Can I use an automated code review for ad-hoc changes outside of a pull request?

Yes, you can apply this standard code review to ad-hoc changes outside of a pull request. The review process covers context research and issue assessment to produce structured, actionable feedback regardless of the source.

What steps are needed to generate actionable feedback for a PR review?

Generating actionable feedback requires three steps: Phase 1 Context Research, Phase 2 Comparative Analysis, and Phase 3 Issue Assessment. This methodology produces a structured, prioritized set of findings with clear rationale.