review-pr

# Review PR

Deep code review using 6-7 parallel specialized agents.

## Quick Start

```bash
/review-pr 123
/review-pr feature-branch
```

## Phase 1: Gather PR Information

```bash
# Get PR details
gh pr view $ARGUMENTS --json title,body,files,additions,deletions,commits,author

# View the diff
gh pr diff $ARGUMENTS

# Check CI status
gh pr checks $ARGUMENTS
```

Identify:
- Total files changed
- Lines added/removed
- Affected domains (frontend, backend, AI)

## Phase 2: Skills Auto-Loading (CC 2.1.6)

**CC 2.1.6 auto-discovers skills** - no manual loading needed!

Relevant skills activated automatically:
- `code-review-playbook` - Review patterns, conventional comments
- `security-scanning` - OWASP, secrets, dependencies
- `type-safety-validation` - Zod, TypeScript strict

## Phase 3: Parallel Code Review (6 Agents)

Launch SIX specialized reviewers in ONE message with `run_in_background: true`:

| Agent | Focus Area |
|-------|-----------|
| code-quality-reviewer #1 | Readability, complexity, DRY |
| code-quality-reviewer #2 | Type safety, Zod, Pydantic |
| security-auditor | Security, secrets, injection |
| test-generator | Test coverage, edge cases |
| backend-system-architect | API, async, transactions |
| frontend-ui-developer | React 19, hooks, a11y |

```python
# PARALLEL - All 6 agents in ONE message
Task(subagent_type="code-quality-reviewer", prompt="Review readability...", run_in_background=True)
Task(subagent_type="code-quality-reviewer", prompt="Review type safety...", run_in_background=True)
Task(subagent_type="security-auditor", prompt="Security audit...", run_in_background=True)
Task(subagent_type="test-generator", prompt="Test coverage...", run_in_background=True)
Task(subagent_type="backend-system-architect", prompt="API review...", run_in_background=True)
Task(subagent_type="frontend-ui-developer", prompt="React review...", run_in_background=True)
```

### Optional: AI Code Review

If PR includes AI/ML code, add 7th agent:

```python
Task(subage