메뉴
Use when defining features, writing user stories, prioritizing work, or creating acceptance criteria. Covers requirements gathering, user story mapping, prioritization frameworks, sprint planning, and stakeholder communication.
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 managing Laravel Forge servers, sites, deployments, SSL, databases, queue workers, scheduled jobs, security rules, and server provisioning. Covers Forge CLI, API, deployment scripts, Nginx templates, daemon management, and zero-downtime deployments.
Project-specific Ansible operations template — customize with your inventory, playbook catalog, deployment workflows, and host group details
Use when implementing or auditing accessibility features. Covers WCAG 2.1 AA/AAA compliance, ARIA roles and attributes, keyboard navigation, screen reader support, color contrast, focus management, and accessible component patterns.
Use when evaluating AI/LLM systems — benchmark design, automated evaluation pipelines, human evaluation protocols, A/B testing, hallucination detection, factuality checking, bias testing, safety evaluation (red teaming), latency/cost metrics, eval datasets, regression testing for prompts, and model comparison frameworks.
Use when building KPI frameworks, designing dashboards, analyzing marketing performance, setting up attribution models, or creating automated reports. Covers Google Analytics 4, social media analytics, funnel analysis, cohort analysis, A/B test analysis, ROI calculation, competitive benchmarking, and stakeholder reporting.
Use when designing or implementing REST APIs. Covers RESTful conventions, versioning, pagination, filtering, error handling, rate limiting, HATEOAS, OpenAPI documentation, and API security best practices.
| name | product-management |
| description | Use when defining features, writing user stories, prioritizing work, or creating acceptance criteria. Covers requirements gathering, user story mapping, prioritization frameworks, sprint planning, and stakeholder communication. |
| user-invocable | false |
| allowed-tools | ["Read","Write","Grep","Glob"] |
PROBLEM: [Specific, observable problem]
WHO: [Affected user roles and branches]
IMPACT: [Quantified -- time lost, revenue at risk, error rate]
FREQUENCY: [Daily, per transaction, monthly]
EVIDENCE: [Support tickets, analytics, user feedback]
When [situation/trigger],
I want to [motivation/action],
So I can [expected outcome].
Constraints: [time/budget/regulatory limits, integrations, must not break X]
As a [role] in [branch/department],
I want to [specific action],
So that [measurable business value].
Independent, Negotiable, Valuable, Estimable, Small (fits a sprint), Testable.
| Size | Points | Description |
|---|---|---|
| XS | 1 | Config change, label update |
| S | 2 | Single field or simple logic |
| M | 3-5 | New screen or workflow step |
| L | 8 | Multi-screen feature |
| XL | 13+ | Must be split |
- [ ] Given [precondition], When [action], Then [testable result].
Multi-Tenant: User sees only own branch data; cross-branch access returns 403.
Audit Trail: Every CUD logs user, timestamp, table, record ID, old/new values.
Permissions: Users without required permission get 403; read-only users cannot write.
Validation: Invalid input shows field-level errors; missing required fields blocks submit.
Performance: List < 300ms p95; form submit < 500ms p95.
Security: All inputs validated server-side; no sensitive data leaked to unauthorized roles.
ACTIVITY (Epic) -- "Manage Sales Orders"
TASK (Feature) -- "Create Sales Order"
STORY -- "Add line items", "Apply discount", "Submit for approval"
TASK (Feature) -- "Track Sales Order Status"
STORY -- "View timeline", "Receive notification on change"
MVP Slicing: Slice horizontally. MVP = minimum stories for end-to-end core workflow.
Score = (Reach x Impact x Confidence) / Effort
Reach: users/branches per quarter | Impact: 0.25-3 scale | Confidence: 50-100% | Effort: person-weeks
| Category | Description |
|---|---|
| Basic | Expected; absence causes dissatisfaction (login, save, print) |
| Performance | More is better, linear satisfaction (speed, filters, search) |
| Delighter | Unexpected, strong satisfaction (auto-suggestions, smart defaults) |
# Feature: [Name]
## Problem: [What, who, business cost of not solving]
## Scope / Out of Scope
## User Stories (with acceptance criteria)
## Data Model: Entity | Key Fields | Relationships
## API Endpoints: Method | Endpoint | Description | Auth
## UI/UX: Screens, key interactions, user flow
## Permissions: Role x CRUD matrix
## Edge Cases
## Success Metrics
## Dependencies
## Testing Plan: Unit, integration, E2E, multi-tenant isolation
Fibonacci estimation: 1, 2, 3, 5, 8, 13. Split stories > 8 points. Planned capacity = avg velocity (last 3 sprints) x 0.8 buffer.
FEATURE_INVOICE_PDF=true (per-branch)
FEATURE_MULTI_CURRENCY=false (global)
FEATURE_NEW_DASHBOARD=beta (percentage rollout)
RELEASE NOTES -- v[X.Y.Z] ([YYYY-MM-DD])
NEW FEATURES: [Feature]: [One-sentence description]. [Link].
IMPROVEMENTS: [Module]: [What changed and why].
BUG FIXES: [Module]: Fixed [description]. (#ticket)
BREAKING CHANGES: [Description + migration steps].
Procure-to-Pay: PR -> Approval -> PO -> Receipt -> Bill -> Payment
Order-to-Cash: Quotation -> SO -> Delivery -> Invoice -> Payment
Record-to-Report: Journal -> Ledger -> Trial Balance -> Statements -> Period Close
Hire-to-Retire: Requisition -> Hiring -> Onboarding -> Employment -> Payroll -> Exit