multi-review-aggregation
Multi-Review Aggregation
Dispatch N independent code reviews and aggregate findings. Each reviewer catches different bugs -- union preserves the long tail that single-shot misses.
Research basis: SWR-Bench (arXiv 2509.01494) -- N independent reviews: 43.67% F1 improvement, 118.83% recall improvement. Diminishing returns past N=5; N=3 captures most improvement.
Core principle: Independence via separate Task dispatches -- same base prompt, no shared context.
N Selection by Tier
| Tier | N Reviews | Rationale |
|---|---|---|
| max-20x | 3 | Quality priority -- full aggregation |
| max-5x | 3 | Balanced -- same recall benefit |
| pro/api | 1 | Budget priority -- single review |
When N=1, skip this skill -- use standard single code review.
Parallel Dispatch Pattern
More from schlenks/superpowers-bd
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
10writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
9dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
9brainstorming
Use when starting any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
8epic-verifier
Use when all implementation tasks in an epic are closed, before calling finishing-a-development-branch
8rule-of-five-tests
Use when writing 50+ lines of test code, adding test suites, or before claiming test work complete - apply 5 focused passes (Draft, Coverage, Independence, Speed, Maintainability) to catch issues single-shot generation misses
8