메뉴
Prioritization frameworks (RICE, MoSCoW) and capacity planning tools for Sprint structuring. Determines optimal Sprint groupings based on team velocity and dependency constraints.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Use when writing or modifying Express + Prisma backend code in VSmartwatch admin (HealthGuard/backend). Reference patterns for Prisma client singleton, JWT auth, route/controller/service layering, error handling, Postgres patterns, Socket.IO realtime, AWS S3, and Jest testing.
Use when writing or modifying FastAPI backend code in VSmartwatch (health_system/backend, healthguard-model-api, Iot_Simulator_clean/api_server). Reference patterns for router/service/repository layering, Pydantic v2, async DB, internal-secret auth, error handling, sanitized responses, and pytest.
Use when writing or modifying Flutter/Dart code in VSmartwatch mobile app (health_system/lib). Reference patterns for Riverpod state management, dio HTTP, repository pattern, GoRouter navigation, FCM (push only), elderly UX, and widget testing.
Use when about to claim work is complete, fixed, or passing. Requires running verification commands and reading actual output BEFORE making any success claims. Evidence before assertions.
Ultra-compressed Vietnamese mode. ONLY activate when the user types "/caveman" or says "bật caveman", "caveman mode", "ngắn gọn cực", "tiết kiệm token". Off by default. Output stays Vietnamese; only the response style changes.
Five-axis code review framework. Use when reviewing your own changes before merge, or reviewing PR. Evaluates correctness, readability, architecture, security, performance.
| name | product-manager-toolkit |
| description | Prioritization frameworks (RICE, MoSCoW) and capacity planning tools for Sprint structuring. Determines optimal Sprint groupings based on team velocity and dependency constraints. |
Apply structured prioritization frameworks to rank tasks, group them into optimal Sprints, and ensure capacity constraints are respected.
RICE Score = (Reach × Impact × Confidence) / Effort
Reach: Number of users affected per Sprint
Impact:
- Massive = 3x (core product functionality)
- High = 2x (important feature)
- Medium = 1x (useful addition)
- Low = 0.5x (minor improvement)
- Minimal = 0.25x (cosmetic)
Confidence:
- High = 100% (well-defined UC, clear requirements)
- Medium = 80% (some ambiguity)
- Low = 50% (exploratory, unclear scope)
Effort: Story Points
| Category | Description | Action |
|---|---|---|
| Must Have | MVP-critical, system won't work without it | Sprint 1-2 |
| Should Have | Important but system works without it | Sprint 2-3 |
| Could Have | Nice to have, enhances experience | Sprint 3-4 |
| Won't Have | Out of scope for current release | Backlog |
Inputs:
Capacity formula:
Available SP = Team Velocity × 0.8 (buffer)
= 32 × 0.8 = ~26 effective SP
If Sprint has heavy infra tasks: allow up to 42 SP (Sprint 1 pattern)
If Sprint has integration-heavy tasks: cap at 26 SP
Grouping rules:
Sprint allocation table:
| Sprint | Theme | Epics | Total SP | Rationale |
| ------ | --------------- | --------- | -------- | ------------------------------ |
| 5 | Admin Dashboard | EP17-EP19 | ~38 | Dependencies resolved in S1-S4 |