Review

This is the entry point when you want a comprehensive app review but aren't sure which specific reviews you need. It reads your codebase, asks up to four contextual questions about your app type and compliance requirements, then recommends a prioritized plan across eight review categories: design, security, privacy, compliance, resilience, performance, SEO, and GEO. The smart bit is how it triages based on what it finds in your code, like auto-detecting GDPR requirements from cookie implementations or suggesting thorough security reviews when it spots new auth code. Run it before major launches or when onboarding someone who needs to understand your review coverage. It generates a unified report with an overall readiness score and accumulates regression tests over time.

skills.sh installs: 607
GitHub stars: 2
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add shiplightai/agent-skills --skill review --agent claude-code

Installs into .claude/skills of the current project.

Files

Review Orchestrator

The single entry point for application reviews. It triages what matters, then runs one or more domain reviews and merges them into a unified report. Each domain lives in references/<domain>.md and is loaded only when selected.

When to use

User wants a review but isn't sure which kind
Pre-launch readiness assessment
Post-incident review planning
A targeted request for one domain ("check my app's security", "review SEO")

Modes

Triage (default, /review) — ask context questions, recommend a plan, run it.
Full suite (/review --all) — run every applicable domain.
Targeted (/review <domain>) — jump straight into one domain, skipping triage. E.g. /review security, /review seo. Accepts an optional depth flag (--quick / --thorough).