# Review

> Bug-focused PetSwipe review workflow emphasizing regressions, deployment risk, missing validation, and stale docs.

- Skill: `hoangsonww/review-2` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add hoangsonww/review-2`
- Raw SKILL.md: https://api.skillmd.com/api/skills/hoangsonww/review-2/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Productivity
- Author: hoangsonww (https://skillmd.com/u/hoangsonww)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/hoangsonww/review-2

---


Use this skill when the user asks for a review or when a high-risk change needs structured scrutiny.

## Workflow

1. Review for correctness and regression risk first.
2. Check deployment, validation, and doc-sync impact second.
3. Prefer concrete findings over broad commentary.
4. If there are no findings, say so explicitly and mention residual uncertainty.

## Output Standard

- Findings first
- Highest severity first
- File references whenever possible
- Brief open questions or residual risks after findings

Use the `petswipe-reviewer` subagent when you want isolated review context.

@references/review-checklist.md