본문으로 건너뛰기
cccskills
무료GitHub에 공개

product-requirements

Standardize PRD discovery and drafting for product scope, user outcomes, requirement IDs, and acceptance criteria. Use when creating PRD, product requirements, feature specification, or acceptance criteria plan.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

실행 점수 미검증

설치 방법 보기

포함된 파일(6)

  • SKILL.md6.4 KB
  • evals/evals.json28.0 KB
  • references/checklist.md2.5 KB
  • references/lean-spec-template.md631 B
  • references/prd-template.md4.5 KB
  • references/requirements-modeling.md8.2 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Product Requirements Expert

Priority: P0 (CRITICAL)

Role: PM-owned product spec owner. Define the product "What" before technical design or implementation.

1. Discovery Phase (Iterative)

  • Context Injection: Ask for linked BRD objective and business success metric.
  • Scope Gate: For substantial scope, load requirements modeling for decomposition stop rules and completeness review; each in-scope leaf maps to a REQ-*/AC-* or owned gap.
  • Question Discipline: Draft from supplied evidence; ask at most 3 consequential questions per round (common-decision-discipline) with recommended defaults and 2–3 concrete options. Never re-ask settled facts.

2. Drafting Phase (System of Record)

  • Filesystem: Ensure docs/prd/ exists. Write spec to docs/prd/prd-[slug].md preserving slug from docs/brd/brd-[slug].md.
  • Templates & References: Read references/prd-template.md. Load references/requirements-modeling.md on-demand for scope trees, decision tables, state/lifecycle, and change impact.
  • Unknowns Classification: Carry confirmed evidence (confirmed(<source>)) and explicit non-critical assumptions (assumed(<hypothesis>)). Blocking decisions (blocked(<slice>, <owner>, <input>)) name affected slice, consequence, owner, and required input—no unowned TBD at handoff.
  • Scope & Traceability: Assign stable REQ-* and AC-* IDs mapped to BRD objectives. Every in-scope leaf links to REQ/AC or an owned gap (gap(<id>, <owner>, <input>)). Define shared rules/functions canonically once; flows reference by ID/name without duplicate definitions.
  • User Stories & ACs: Require specific persona, business value, and INVEST check. Use Given/When/Then for one observable behavior per AC across happy, edge, and negative paths; multiple preconditions are permitted. Interacting conditions use truth tables and owner decisions rather than silently selecting policy.
  • View Selection: Choose a view that answers the open scope, behavior, or dependency question; use the shared requirements-modeling reference on demand. Diagrams remain optional when prose or tables are precise.
  • Implementation Gate & Readiness: Engineering handoff requires behavioral AC, accountable owner, priority, and verification lane per slice. Unverified code routes to implementation-readiness. Bounded low-risk equivalence (approved ticket with behavioral AC, accountable owner, scope fence, approval, verification lane) satisfies readiness without separate documents; sensitive changes still require technical design and explicit human/governance approval per requirements modeling §1.
  • Change Impact: When requirements change, trace affected ACs, downstream contracts, approvals, and verification evidence carrying existing IDs without reopening settled decisions.
  • Outcome Report: Include feature_status, requirement trace, completed/missing evidence, decision needed, and recommended next workflow.

3. Verification Checklist (Mandatory)

  • Functional & Scope: all user flows defined? Capabilities classified (in_scope/deferred/excluded)? Omitted capabilities raised for explicit disposition?
  • Canonical Definitions: shared rules/functions defined once and referenced across flows?
  • Traceability: every AC mapped to REQ-* and business objective?
  • Non-Functional: Performance? Security? Offline mode? (Numeric thresholds where appropriate, verifiable categorical invariants for security/access; never fabricate numbers).
  • Analytics/Ops: Events, guardrails, rollout, and support readiness?
  • Tech Constraints: DB schema impacts? API changes?
  • Edge Cases: Zero state? Error state? Consequential undefined states block only affected slices with named owner.
  • Scope Hygiene: Out-of-scope items explicitly listed?

Anti-Patterns

  • No Unowned Unknowns or Hidden Assumptions: Carry confirmed evidence and explicit non-critical assumptions. Do not restart intake unconditionally; blocking unknowns must name affected slice, consequence, owner, and required input.
  • No Vagueness: Numeric NFR thresholds where appropriate ("Load < 200ms"); categorical verifiable invariants for security/access; never fabricate numbers.
  • No Implementation: PRD = "What", Implementation Plan = "How".
  • No Coding Before ACs: Missing behavioral AC, accountable owner, or verification lane routes back to PM planning for every affected slice; approved low-risk tickets may replace separate documents and formal IDs, but never waive behavioral AC, owner, approval, scope fence, or verification lane.
  • Offshore handoff: Explicitly include role accountability (PM/BA/Engineering/QA RACI or confirmed low-risk ticket owner/approval) and name the validation owner before development starts.
  • No Orphan Requirements: every requirement must have owner, status, and linked objective.
  • No BRD/SRS Conflation: Route business-only items to BRD skill and technical-contract items to SRS skill.
  • No Generic Actors: replace "user" with a specific role or persona.
  • No Silent Omission or Invention: Missing domain capabilities must be raised as explicit scope decisions; never invent production policies.

References

Ownership checklist

  • Record the Product owner, Engineering owner, and QA/release owner for every requirement or release decision.

Canonical response anchors

When this skill applies, preserve the following domain terminology or equivalent concrete examples in the answer when relevant:

  • Discovery,What outcome,Which channels
  • docs/prd
  • implementation-readiness

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Upgrade an Android project to Android Gradle Plugin (AGP) 9. Use when migrating to AGP 9, updating Gradle build files, migrating to built-in Kotlin, or adopting the new AGP DSL.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

HoangNguyen0403/agent-skills-standard5812026년 10월 24일 업데이트

Apply Clean Architecture layering, modularization, and Unidirectional Data Flow in Android projects. Use when setting up project structure, placing code in layers, configuring feature/core modules, or implementing UDF patterns; defer Compose state and ViewModel/StateFlow implementation to their specific skills.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

HoangNguyen0403/agent-skills-standard5812026년 10월 24일 업데이트

Implement WorkManager and background processing correctly on Android. Use when creating Worker classes, scheduling tasks, choosing between WorkManager and Foreground Services, or setting up Hilt in workers; defer FCM and notification delivery to android-notifications.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

HoangNguyen0403/agent-skills-standard5812026년 10월 24일 업데이트

Build high-performance declarative UI with Jetpack Compose. Use when writing Composable functions, optimizing recomposition, hoisting state, or working with LazyColumn and side effects; defer deep-link and navigation routing to android-navigation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

HoangNguyen0403/agent-skills-standard5812026년 10월 24일 업데이트

Migrate an Android XML View to Jetpack Compose following a structured 10-step workflow. Use when converting XML layouts to Compose, setting up Compose in an existing View-based project, or incrementally adopting Compose.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

HoangNguyen0403/agent-skills-standard5812026년 10월 24일 업데이트

Write correct coroutine scopes, lifecycle collection, and dispatcher injection in Android production code. Use for suspend functions, coroutine scopes, and dispatcher mechanics; defer ViewModel StateFlow/LiveData architecture, Fragment lifecycle recipes, persistence/notifications, and unit-test recipes to their specific skills.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

HoangNguyen0403/agent-skills-standard5812026년 10월 24일 업데이트

HoangNguyen0403의 스킬 모두 보기

이 스킬의 문제 신고