code-review-and-quality

Reviews code changes across correctness, readability, architecture, security, and performance before merge.

Updated Jul 9, 2026
One-click install
npx skills add https://github.com/assafmanor/waypoint --skill code-review-and-quality-assafmanor
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: code-review-and-quality
Source: https://github.com/assafmanor/waypoint/tree/main/.claude/skills/code-review-and-quality
Command: npx skills add https://github.com/assafmanor/waypoint --skill code-review-and-quality-assafmanor

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Code merged without structured review accumulates defects, security vulnerabilities, and architectural debt. This Skill enforces a consistent multi-axis review process so every change is evaluated against the same quality gates before entering the main branch. ## Core Features & Use Cases - Five-Axis Review: Evaluates every change for correctness, readability, architecture, security, and performance with concrete checklists per axis. - Severity-Labeled Feedback: Categorizes findings as Critical, Required, Nit, Optional, or FYI so authors know exactly what must be addressed before merge. - Change Sizing and Splitting Guidance: Defines thresholds for reviewable change sizes and provides stacking, horizontal, and vertical splitting strategies for oversized PRs. - Use Case: Before merging a pull request that adds a new API endpoint, run the review checklist to verify tests cover edge cases, inputs are validated at boundaries, no N+1 queries exist, and the change description stands alone in version control history. ## Quick Start Review this pull request across correctness, readability, architecture, security, and performance, and label each finding by severity.

Frequently Asked Questions about code-review-and-quality

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

FAQPage Schema
What are the limitations of automated or AI-assisted code review?▼

Passing tests and plausible-looking AI-generated code do not guarantee correctness, security, or architectural fit. Reviewers must still verify edge cases, check for relocated rather than reduced complexity, and avoid rubber-stamping with unexamined approvals.