| external FAQs that stress-test a product concept before any building begins. Produces prfaq.md in the configured output folder. "future press release", "stress-test the concept", "validate the idea before building", "internal FAQ", "external FAQ", "Amazon-style product brief", or "PRFAQ for [product/feature]". Also use when someone wants to clarify or update an existing PRFAQ, or validate a draft against the Working-Backwards
npx skills add https://github.com/aj-geddes/claude-code-bmad-skills --skill bmad-prfaq
Role: Pre-Phase Analysis — Working-Backwards stress-test
Function: Guide the user through the Amazon Working-Backwards method to
produce a PRFAQ document (prfaq.md) that crystallises the product vision,
validates the concept, and surfaces hard questions *before* a PRD, architecture,
or a single line of code is written.
Use when you need to:
product brief for Working-Backwards teams)
Working-Backwards starts from the *desired customer outcome* and reasons
backward to the product. The PRFAQ has two parts:
| Part | Purpose |
|------|---------|
| Press Release | Articulate the customer value as if the product already shipped |
| Internal FAQ | Surface hard business and technical questions the team must answer |
| External FAQ | Anticipate questions a curious customer or press contact would ask |
The process forces concrete answers to the hardest questions *now*, not after
months of building.
This skill supports three modes. Identify intent from context:
| Intent | Trigger | Output |
|--------|---------|--------|
| Create | No existing PRFAQ; new concept | Full prfaq.md from scratch |
| Update | Existing PRFAQ; requirements changed | Revised prfaq.md with decision log entry |
| Validate | Draft PRFAQ exists; needs critique | Critique report; annotated checklist |
prfaq.md, project-context.md, anddecision-log.md.
produce a critique; stop — do not rewrite unless the user asks.
Ask the minimum questions needed to fill the template. Stop after each cluster
and confirm before moving on. Suggested clusters:
Cluster A — Customer & Problem
Cluster B — Product & Value
Cluster C — Differentiation & Availability
Cluster D — Hard Questions (Internal)
Cluster E — Customer Questions (External)
Use the template at ${CLAUDE_PLUGIN_ROOT}/skills/bmad-prfaq/templates/prfaq.template.md.
Fill in order:
Keep the press release under 600 words. If you cannot keep it short, the
concept is not clear enough — ask more questions.
10-15 questions that the leadership team, investors, or a skeptical engineer
would ask. Required question categories:
Answers must be specific. "We will figure it out" is not acceptable.
5-10 questions that a customer, journalist, or analyst would ask at launch.
Cover: pricing/access, privacy/security, compatibility, support, roadmap.
Assemble the three sections into prfaq.md in the output folder.
File path: {outputFolder}/prfaq.md
Append a concise entry to {outputFolder}/decision-log.md:
Suggest the appropriate BMAD track and next skill:
product-manager for a tech spec.
product-manager for a PRD, then system-architect.
creative-intelligence research before proceeding.
When intent is Validate (or as a self-check before finalising):
A complete PRFAQ must:
Pattern: Sequential gather, parallel draft
For large or complex products where multiple customer segments exist, fan out
FAQ drafting across segments:
| Agent | Task | Output |
|-------|------|--------|
| Agent 1 | Draft Internal FAQ (business/market/risk questions) | {outputFolder}/prfaq-internal-faq-draft.md |
| Agent 2 | Draft External FAQ (customer/press questions) | {outputFolder}/prfaq-external-faq-draft.md |
Coordination:
{outputFolder}/prfaq-inputs.md.prfaq.md.Example subagent prompt (Internal FAQ agent):
Task: Draft the Internal FAQ section of a PRFAQ document.
Context: Read {outputFolder}/prfaq-inputs.md for the product concept, customer
segments, risks, and success metrics gathered from the user.
Objective: Produce 10-15 internal FAQ questions and specific answers covering
market opportunity, customer validation, business model, technical
risk, success metrics, alternatives considered, and dependencies.
Output: Write draft to {outputFolder}/prfaq-internal-faq-draft.md.
Constraints:
- Answers must be specific, not aspirational placeholders.
- Include at least one "what are the top ways this fails?" question.
- Include success metrics at 30, 90, and 180 days.
- Do not include implementation code or technical architecture decisions.
Receives input from:
Provides output to:
before drafting (cite sources in the internal FAQ).
use past-tense achievements, not future promises.
person say this?" test.
> 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-prfaq. All methodology credit belongs to the BMAD Code Organization.
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.
Generates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.). Saves hours of brainstorming and manual checking.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.
Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Take aj-geddes/bmad-prfaq from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
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.