# Review

> Gate the work behind a local reviewer panel.

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

---


# review

The task isn't done until it passes a reviewer panel. Run the gate before declaring done.

## Panel

`$ARGUMENTS` = reviewer count, default 2:

- `1` → fork reviewer only.
- `2` → 1 independent + 1 fork.
- `N` → N−1 independents with distinct lenses (correctness, functionality, simplification, security, tests) + 1 fork.

Reviewer types:

- **Fork** — an agent forked from this session, carrying the full conversation context. Always on the session model.
- **Independent** — fresh context: give it only the task description and the branch diff vs merge-base.

Cross-model: If you are Claude, and have access to Open AI Model (like in Cursor), then prefer cross-model reviewers as long as they're not a weaker model.
For example, Opus 4.8 <-> GPT 5.5

## Gate

1. Run the panel in parallel.
2. Triage findings: fix the real ones; reject with a stated reason (you have context reviewers lack), or escalate to user.
3. One re-review round, of the fixes only.
4. Gate opens. Escalate, contested or rejected findings go in the final summary.