bmad-planning-orchestrator/skills/bmad-prfaq/SKILL.md
Amazon-style Working-Backwards PRFAQ: a future press release plus internal and external FAQs that stress-test a product concept before any building begins. Produces prfaq.md in the configured output folder. Use when the user says: "write a PRFAQ", "working backwards", "press release", "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 criteria. Supports three intents: Create / Update / Validate.
npx skillsauth add aj-geddes/claude-code-bmad-skills bmad-prfaqInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
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:
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, and
decision-log.md.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:
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:
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.
testing
Solutioning-phase UX planning skill (optional; activate when the project has a UI). Produces TWO planning documents: DESIGN.md (the visual system — design tokens, color palette, typography, spacing, component specs, WCAG 2.1 AA contract) and EXPERIENCE.md (user journeys, flow diagrams, screen states, error/empty/loading handling). Use when the user says "design the UX", "create UX planning docs", "define the design system", "map the user flows", "UX for this feature", "wireframe the flows", "what are the user journeys", "accessibility design", "WCAG compliance", "design tokens", "responsive design plan", "mobile-first design", or "create DESIGN.md / EXPERIENCE.md". Runs after architecture is drafted and before stories are created. Supports Create / Update / Validate intents.
testing
Quick Flow lightweight technical specification for small-scope work (1-15 stories). Replaces the full PRD + architecture pair when scope is small and requirements are clear. Produces bmad-output/tech-spec.md as the single planning artifact before story creation. Use when the user says: "write a tech spec", "create a technical specification", "I need a tech spec for this feature", "quick spec", "small project spec", "we don't need a full PRD", "just a tech spec", "spec out this change", "document this feature". QUICK FLOW TRACK ONLY (1-15 stories). If scope grows beyond ~15 stories or involves multiple teams / external integrations at scale, stop and redirect to bmad-prd + bmad-architecture instead — those skills are built for that complexity. Supports three intents: Create (new spec), Update (revise an existing tech-spec.md), Validate (review a draft for completeness against BMAD criteria).
tools
Orchestration handoff bridge: emits and maintains sprint-status.yaml as the project's sequencing system-of-record. Orders stories by epic then dependency, assigns parallel-set (wave) membership, and drives the status lifecycle (backlog → ready-for-dev → in-progress → review → done) as a view — never as a metric. Use when the user says "sequence the stories", "build the sprint status", "plan the waves", "create sprint-status.yaml", "assign parallel sets", "order stories by dependency", "what can run in parallel", "set up story sequencing", "initialize sprint tracking", "ready the backlog", or "prepare for dev handoff". Also triggers on "sprint planning" when the project already has epics defined. SCOPE: SEQUENCING AND ORCHESTRATION ONLY. No velocity, no burndown, no committed points, no coverage metrics. Capacity is expressed as wave width (concurrent story count), not points. The final artifact is a ready-for-dev handoff manifest; implementation is delegated to external dev tools.
development
Distills ANY messy input — brain dump, transcript, long PRD, stakeholder notes, feature request, voice memo — into a tight five-field SPEC.md kernel that any downstream planning skill can consume. The five fields are: Problem, Capabilities, Constraints, Non-Goals, Success Metrics. Use when the user says "create a spec", "write a spec for", "distill this into a spec", "I have a brain dump", "turn this into something structured", "clean up these notes", "make a SPEC from", "I want to define the problem", "help me scope this", "summarize what we're building", "I have a PRD but need a kernel", "what are we actually solving?", or drops raw text/transcript and asks for structure. Also use when starting any new initiative and a clean shared definition is missing.