mcpbeat Sign in

Bmad Product Brief Skill for Claude

| Lean facilitator for creating, updating, and validating a product brief — the Analysis-phase foundation of the BMAD Method. Captures problem statement, target users, core features, goals, constraints, and success metrics. "let's do discovery", "help me define my product", "what problem are we solving", "capture our product vision", "update the product brief", "validate the brief", "check if the brief is complete", "run discovery", "start a product brief", "brainstorm the product", or "I want to plan a product". Output is a planning artifact only — no code is written or run.

8k tokens
context cost
the whole folder, loaded on every use
4
files
ships runnable scripts
0
copies elsewhere
how many repositories repackaged it
471
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/aj-geddes/claude-code-bmad-skills --skill bmad-product-brief

The instruction itself

12 sections, as written by the author

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.sh if 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.md with the gathered answers.
  • Write the result to bmad-output/product-brief-<slug>-<YYYY-MM-DD>.md (create bmad-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.sh exits 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.

Other skills for the same job

different authors, same section of the catalogue
Startup Analyst
by ComeOnOliver
×2

Expert startup business analyst specializing in market sizing, financial modeling, competitive analysis, and strategic planning for early-stage companies. Use PROACTIVELY when the user asks about market opportunity, TAM/SAM/SOM, financial projections, unit economics, competitive landscape, team planning, startup metrics, or business strategy for pre-seed through Series A startups.

5k tokens
Team Composition Analysis
by ComeOnOliver
×2

This skill should be used when the user asks to "plan team structure", "determine hiring needs", "design org chart", "calculate compensation", "plan equity allocation", or requests organizational design and headcount planning for a startup.

5k tokens
Bulk Rnaseq
by K-Dense-AI
×1

End-to-end bulk RNA-seq orchestrator — takes raw FASTQ reads through QC and trimming (FastQC, fastp/Trim Galore), alignment and quantification (STAR, Salmon, featureCounts), assembles a gene-level counts matrix, then hands off to differential expression (pydeseq2), pathway/GSEA enrichment (pathway-enrichment), and publication figures (scientific-visualization). Use whenever the user has bulk RNA-seq reads or quant output and wants a complete, reproducible differential-expression workflow — e.g. "analyze my RNA-seq", "FASTQ to DESeq2", "run nf-core/rnaseq", "STAR/Salmon quantification", "build a counts matrix for DESeq2", or "go from reads to differentially expressed genes and enriched pathways". Routes between an nf-core/rnaseq (Nextflow) path and a standalone STAR/Salmon path, and covers experimental design, strandedness, and QC gates. For single-cell RNA-seq use the scanpy skill instead.

13k tokens scripts
Generate Status Report
by openai
vendor ×1

Generate project status reports from Jira issues and publish to Confluence. When an agent needs to: (1) Create a status report for a project, (2) Summarize project progress or updates, (3) Generate weekly/daily reports from Jira, (4) Publish status summaries to Confluence, or (5) Analyze project blockers and completion. Queries Jira issues, categorizes by status/priority, and creates formatted reports for delivery managers and executives.

6k tokens scripts
Us Market Bubble Detector
by nicepkg
×1

Evaluates market bubble risk through quantitative data-driven analysis using the revised Minsky/Kindleberger framework v2.1. Prioritizes objective metrics (Put/Call, VIX, margin debt, breadth, IPO data) over subjective impressions. Features strict qualitative adjustment criteria with confirmation bias prevention. Supports practical investment decisions with mandatory data collection and mechanical scoring. Use when user asks about bubble risk, valuation concerns, or profit-taking timing.

22k tokens scripts
Gws Workflow Standup Report
by googleworkspace
vendor

Google Workflow: Today's meetings + open tasks as a standup summary.

278 tokens
Recipe Create Events From Sheet
by googleworkspace
vendor

Read event data from a Google Sheets spreadsheet and create Google Calendar entries for each row.

223 tokens
Baoyu Diagram
by JimLiu

Create professional, dark-themed SVG diagrams of any type — architecture diagrams, flowcharts, sequence diagrams, structural diagrams, mind maps, timelines, illustrative/conceptual diagrams, and more. Use this skill whenever the user asks for any kind of technical or conceptual diagram, visualization of a system, process flow, data flow, component relationship, network topology, decision tree, org chart, state machine, or any visual representation of structure/logic/process. Also trigger when the user says "画个图" "画一个架构图" "diagram" "flowchart" "sequence diagram" "draw me a ..." or uploads content and asks to visualize it. Output is always a standalone .svg file.

7k tokens scripts

How to use it

Copy the folder

Take aj-geddes/bmad-product-brief from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.