review
Installation
SKILL.md
Team Review
Team-based collaborative code review using Agent Teams.
Why teams > parallel subagents
Current /dm-work:review spawns 3 isolated subagents that report back independently. Findings may conflict, duplicate, or miss connections between concerns. With Agent Teams, reviewers can:
- Challenge each other ("I flagged this as security, but arch says the pattern is intentional")
- Cross-pollinate ("the perf issue I found is caused by the architecture pattern you identified")
- Converge on unified severity ratings instead of potentially conflicting ones
When to use
- Complex PRs touching multiple domains
- Security-sensitive changes where arch context matters
- When previous reviews produced conflicting findings
- For dm-work:review's use cases, see tiered-delegation — simple reviews are fine with subagents