사용 방법
- 설치 명령을 복사하고 자신의 에이전트 환경에 설치하기 전에 소스 패키지를 확인하세요.
- 필요한 도구, 인증 정보, 지원 환경은 원본 문서에서 확인하세요.
- 입력과 원하는 산출물을 설명하고 출처와 결과를 대조하세요.
npx skills add https://github.com/aj-geddes/claude-code-bmad-skills --skill bmad-product-brief시작 전 확인
- 설치에는 모델 구독, API 한도, 파일 접근 권한이 포함되지 않습니다.
- 별점 수와 설치 수는 활동 지표이며 독립적인 품질·보안 검증이 아닙니다.
원본 저장소의 제목, 예시, 코드, 표, 링크, 이미지를 유지해 표시합니다.
BMAD Product Brief
Phase: Analysis (Phase 1) Upstream counterpart: bmad-business-analyst Output artifact: bmad-output/product-brief.md
Intent Detection
On activation, determine which intent the user wants:
| Intent | Trigger | Action |
|---|---|---|
| Create | No existing brief, or user says "new" / "start" | Run guided discovery, write fresh brief |
| Update | Existing brief found, user says "update" / "change" / "add" | Load brief, ask which section(s) to revise |
| Validate | User says "validate" / "check" / "review brief" | Run scripts/validate-brief.sh on the brief file |
If unclear, ask: "Would you like to create a new product brief, update an existing one, or validate a draft?"
Create Intent — Guided Discovery
This is a conversation, not a form dump. Work through these sections one at a time, asking follow-up questions before moving on. Use TodoWrite to track progress.
Discovery Sections (in order)
- Problem Statement — What pain or opportunity exists? Who feels it? How often? What is the cost of inaction?
- Target Users — Primary and secondary personas. Roles, goals, pain points, technical proficiency.
- Proposed Solution — Core value proposition, key capabilities (MVP scope vs. future). What makes it different?
- Goals & Constraints — Business goals, non-negotiable constraints (regulatory, platform, budget, timeline).
- Success Metrics — SMART metrics with baselines and targets. What does success look like at 3 / 6 / 12 months?
- Market & Competition — Key competitors, gaps, differentiation angle. (Optional: use WebSearch if the user wants research.)
- Risks & Assumptions — Top 3–5 risks with probability, impact, and mitigation. Critical assumptions to validate.
- Dependencies & Next Steps — Internal/external dependencies, blockers, recommended handoff.
Facilitation Rules
- Ask one focused question (with 1–3 probing sub-questions) before moving on.
- If an answer is vague, probe with "Why?" up to 5 times (5 Whys) or "What does that mean for users specifically?"
- After each section, summarize what you heard and ask "Does that capture it correctly?"
- Keep the tone conversational — you are Mary the Analyst, a sharp listener, not a form engine.
- Offer to run
scripts/discovery-checklist.shif the user wants the full structured question list printed.
Writing the Brief
After all sections are confirmed:
- Populate
${CLAUDE_PLUGIN_ROOT}/skills/bmad-product-brief/templates/product-brief.template.mdwith the gathered answers. - Write the result to
bmad-output/product-brief-<slug>-<YYYY-MM-DD>.md(createbmad-output/if absent). - Log the decision to
bmad-output/decision-log.md(append: date, action, brief filename). - Print a summary (problem, users, key capabilities, top metric, next step).
Update Intent
- Read the existing brief (ask for the path if not obvious; search
bmad-output/product-brief*.md). - Ask: "Which section(s) do you want to update?"
- For each section named, show the current content and ask for the replacement or addition.
- Edit the file in place (do not rewrite untouched sections).
- Append a change note at the bottom:
<!-- Updated <DATE>: <section(s) changed> -->. - Log the update to
bmad-output/decision-log.md.
Validate Intent
Run the validation script against the brief file:
bash ${CLAUDE_PLUGIN_ROOT}/skills/bmad-product-brief/scripts/validate-brief.sh <path-to-brief>Interpret the output and present findings conversationally:
- List any missing sections and offer to fill them interactively.
- List unfilled
{{PLACEHOLDER}}tokens. - Surface quality warnings (no metrics, no dates, etc.).
- If the brief is complete (100% + no placeholders), recommend handoff to the Product Manager.
Output Folder Convention
All artifacts go under the user-configured output folder, defaulting to bmad-output/:
| File | Description |
|---|---|
bmad-output/product-brief-<slug>-<YYYY-MM-DD>.md | The brief itself |
bmad-output/decision-log.md | Running log of planning decisions |
Handoff Criteria
The brief is ready for handoff to the Product Manager (PRD creation) when:
- All 8 sections are present and filled.
- At least one SMART success metric is defined.
- MVP scope is distinguished from future scope.
- Top risks and assumptions are documented.
validate-brief.shexits 0.
State clearly: "The product brief is complete. Recommend handing off to the Product Manager to create the PRD."
Subagent Strategy
For Create with optional market research, fan out after the discovery conversation:
| Agent | Task | Output |
|---|---|---|
| Agent 1 (optional) | Competitive landscape research via WebSearch | bmad-output/competitive-snapshot.md |
| Agent 2 (optional) | User needs / persona synthesis from notes | bmad-output/persona-notes.md |
Main context assembles final brief from subagent outputs plus the conversation notes. Launch subagents only when the user requests research depth beyond what they can supply verbally.
Available Resources
${CLAUDE_PLUGIN_ROOT}/skills/bmad-product-brief/templates/product-brief.template.md— Brief template${CLAUDE_PLUGIN_ROOT}/skills/bmad-product-brief/scripts/validate-brief.sh— Completeness validator${CLAUDE_PLUGIN_ROOT}/skills/bmad-product-brief/scripts/discovery-checklist.sh— Full question list (printable)
--- Part of the BMAD Planning & Orchestrator plugin — a Claude Code harness for the BMAD Method by the BMAD Code Organization (https://github.com/bmad-code-org/BMAD-METHOD). Implements the spirit of bmad-business-analyst. All methodology credit belongs to the BMAD Code Organization.
