# Review

> > **Gemini CLI:** This skill is triggered by description matching. State any arguments in your message. Sub-agent spawning is not supported — the automated review step in `/submit-for-review` must be done manually using the review-agent prompt in a separate session.

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

---


> **Gemini CLI:** This skill is triggered by description matching. State any arguments in your message. Sub-agent spawning is not supported — the automated review step in `/submit-for-review` must be done manually using the review-agent prompt in a separate session.

---

## What `/review` does

`/review` runs a standalone code review on a PR. It wraps `.claude/review-agent-prompt.md`.

---

## Pre-flight

If `ai` is `"off"`, say:

> "Code review is disabled for this project (REVIEW_GATE is set to 'off' in .codecannon.yaml). To enable reviews, set REVIEW_GATE to 'ai' or 'advisory' and re-run CodeCannon/sync.py."

Do not proceed.

---

## Step 1 — Identify the PR

If `$ARGUMENTS` is a number, use it as the PR number.

If `$ARGUMENTS` is empty, detect the current branch's open PR:
```
gh pr view --json number --jq '.number'
```

If no PR is found, abort and say: "No open PR found for the current branch. Pass a PR number explicitly: `/review <number>`"

---

## Step 2 — Run the review

Load `.claude/review-agent-prompt.md` and perform the review for the PR number.

**If sub-agent spawning is supported** (e.g. Claude Code): invoke a dedicated review agent with the prompt and PR number.

**If sub-agent spawning is not supported** (e.g. Codex, Cursor, Gemini): perform the review yourself inline — follow the instructions in the review-agent prompt directly.

The review must:
1. Read the PR diff via `gh pr diff <number>`
2. Read any files needed for full context
3. Post findings as a PR comment via `gh pr comment <number>`

---

## Step 3 — Report verdict

After the review agent completes, relay its verdict to the user:

- **APPROVE** → "Review passed. Run `/submit-for-review` to merge (or it may already be merged if called from `/submit-for-review`)."
- **REQUEST CHANGES** → Surface the CRITICAL findings. Say: "Fix the issues above and run `/review` again before merging."

---

## Important

- This command does not commit, push, or merge anything. It only reviews.
- It may be called manually at any time, not just from `/submit-for-review`.
- The review comment is posted to GitHub for the audit trail.
<!-- generated by CodeCannon/sync.py | skill: review | adapter: gemini | hash: 0efcc370 | DO NOT EDIT — run CodeCannon/sync.py to regenerate -->

