# Review

> Use when asked for an opinionated review of the codebase - architecture/backend findings, UI findings against the project's own design docs, or both - severity-ranked with evidence, written to docs/capstone/review.md. Bare "review" does both sides; "review backend" or "review frontend" does one. Opt-in judgment; never edits code.

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

---


# Capstone: review

From this skill's base directory, read `../core/references/core.md`
and `../core/references/core-authoring.md`, then execute
`../core/references/protocols/review.md`
exactly (review is core.md's sole judgment exception). No argument
runs both sides; `backend`/`be` or `frontend`/`fe` runs one.