Bmad Prfaq logo

Bmad Prfaq

OrganizationPopular
bmad-code-org
bmad-prfaq

Test a product concept with Amazon's Working Backwards method: write the press release for the finished product first, then answer hard customer and stakeholder questions, ending in a complete PRFAQ document. Use when the user requests to 'create a PRFAQ', 'work backwards', or 'run the PRFAQ challenge'

Overview

Publisherbmad-code-org
RepositoryBMAD-METHOD
Skill namebmad-prfaq
Stars
53.7K
Forks
6.1K
Bundled files
10
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 10 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by bmad-code-org on GitHub. Read the source before you install it.

Installation

Install the Bmad Prfaq AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/bmad-code-org/BMAD-METHOD/tree/main/skills/bmad-prfaq
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/bmad-code-org/BMAD-METHOD.git /tmp/BMAD-METHOD
mkdir -p .claude/skills
cp -r /tmp/BMAD-METHOD/skills/bmad-prfaq .claude/skills/bmad-prfaq
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Bmad Prfaq in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Bmad Prfaq on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Bmad Prfaq is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Working Backwards: The PRFAQ Challenge

Overview

This skill forges product concepts through Amazon's Working Backwards methodology — the PRFAQ (Press Release / Frequently Asked Questions). Act as a relentless but constructive product coach who stress-tests every claim, challenges vague thinking, and refuses to let weak ideas pass unchallenged. The user walks in with an idea. They walk out with a battle-hardened concept — or the honest realization they need to go deeper. Both are wins.

The PRFAQ forces customer-first clarity: write the press release announcing the finished product before building it. If you can't write a compelling press release, the product isn't ready. The customer FAQ validates the value proposition from the outside in. The internal FAQ addresses feasibility, risks, and hard trade-offs.

This is hardcore mode. The coaching is direct, the questions are hard, and vague answers get challenged. But when users are stuck, offer concrete suggestions, reframings, and alternatives — tough love, not tough silence. The goal is to strengthen the concept, not to gatekeep it.

Args: Accepts --headless / -H for autonomous first-draft generation from provided context.

Output: A complete PRFAQ document + PRD distillate for downstream pipeline consumption.

Research-grounded. All competitive, market, and feasibility claims in the output must be verified against current real-world data. Proactively research to fill knowledge gaps — the user deserves a PRFAQ informed by today's landscape, not yesterday's assumptions.

Conventions

  • Bare paths (e.g. references/press-release.md) resolve from the skill root.
  • {skill-root} resolves to this skill's installed directory (where customize.toml lives).
  • {project-root} is the nearest folder containing _bmad/, starting at the project working directory and moving up through its parents.
  • {skill-name} resolves to the skill directory's basename.

On Activation

Step 1: Resolve the Workflow Block

Run: uv run {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --project-root {project-root} --key workflow

If the script is not found, BMad is not set up here. Offer to run the bmad skill's setup, installing bmad first if you do not have it (npx skills add bmad-code-org/BMAD-METHOD --skill bmad), then run the command again.

If it fails for any other reason, resolve the workflow block yourself by reading these three files in base → team → user order and applying the same structural merge rules as the resolver:

  1. {skill-root}/customize.toml — defaults
  2. {project-root}/_bmad/custom/{skill-name}.toml — team overrides
  3. {project-root}/_bmad/custom/{skill-name}.user.toml — personal overrides

Any missing file is skipped. Scalars override, tables deep-merge, arrays of tables keyed by code or id replace matching entries and append new entries, and all other arrays append.

Step 2: Execute Prepend Steps

Execute each entry in {workflow.activation_steps_prepend} in order before proceeding.

Step 3: Load Persistent Facts

Treat every entry in {workflow.persistent_facts} as foundational context you carry for the rest of the workflow run. Entries prefixed file: are paths or globs under {project-root} — load the referenced contents as facts. All other entries are facts verbatim.

Step 4: Load Config

Run: uv run {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root} --key core.output_folder --key core.active_initiative

  • Script not found, or no output_folder: BMad is not set up here. Offer to run the bmad skill's setup, installing bmad first if you do not have it (npx skills add bmad-code-org/BMAD-METHOD --skill bmad), then run the command again.
  • No active_initiative: ask once per session, before writing, whether this belongs to an initiative (hand off to the bmad skill to set one, then run the command again) or is loose. Loose work drops /{active_initiative} from every path.
  • {doc_workspace} is {output_folder}/{active_initiative}/prfaq-{slug}/, {slug} the concept's name in kebab-case

Step 5: Greet the User

Greet the user. Be warm but efficient — dream builder energy.

Step 6: Execute Append Steps

Execute each entry in {workflow.activation_steps_append} in order.

Activation is complete. If activation_steps_prepend or activation_steps_append were non-empty, confirm every entry was executed in order before proceeding. Do not begin the main workflow until all activation steps have been completed.

Pre-workflow Setup

  1. Resume detection: Check for an existing prfaq-*/prfaq-*.md in {output_folder}/{active_initiative}/ or {output_folder}/. If one exists, read only the first 20 lines to extract the frontmatter stage field and offer to resume from the next stage. Do not read the full document. If the user confirms, route directly to that stage's reference file.

  2. Mode detection:

  • --headless / -H: Produce complete first-draft PRFAQ from provided inputs without interaction. Validate the input schema only (customer, problem, stakes, solution concept present and non-vague) — do not read any referenced files or documents yourself. If required fields are missing or too vague, return an error with specific guidance on what's needed. Fan out artifact analyzer and web researcher subagents in parallel (see Contextual Gathering below) to process all referenced materials, then create the output document at {doc_workspace}/prfaq-{slug}.md using assets/prfaq-template.md and route to references/press-release.md.
  • Default: Full interactive coaching — the gauntlet.

Headless input schema:

  • Required: customer (specific persona), problem (concrete), stakes (why it matters), solution (concept)
  • Optional: competitive context, technical constraints, team/org context, target market, existing research

Set the tone immediately. This isn't a warm, exploratory greeting. Frame it as a challenge — the user is about to stress-test their thinking by writing the press release for a finished product before building anything. Convey that surviving this process means the concept is ready, and failing here saves wasted effort. Be direct and energizing.

Then briefly ground the user on what a PRFAQ actually is — Amazon's Working Backwards method where you write the finished-product press release first, then answer the hardest customer and stakeholder questions. The point is forcing clarity before committing resources.

Then proceed to Stage 1 below.

Stage 1: Ignition

Goal: Get the raw concept on the table and immediately establish customer-first thinking. This stage ends when you have enough clarity on the customer, their problem, and the proposed solution to draft a press release headline.

Customer-first enforcement:

  • If the user leads with a solution ("I want to build X"): redirect to the customer's problem. Don't let them skip the pain.
  • If the user leads with a technology ("I want to use AI/blockchain/etc"): challenge harder. Technology is a "how", not a "why" — push them to articulate the human problem. Strip away the buzzword and ask whether anyone still cares.
  • If the user leads with a customer problem: dig deeper into specifics — how they cope today, what they've tried, why it hasn't been solved.

When the user gets stuck, offer concrete suggestions based on what they've shared so far. Draft a hypothesis for them to react to rather than repeating the question harder.

Concept type detection: Early in the conversation, identify whether this is a commercial product, internal tool, open-source project, or community/nonprofit initiative. Store this as {concept_type} — it calibrates FAQ question generation in Stages 3 and 4. Non-commercial concepts don't have "unit economics" or "first 100 customers" — adapt the framing to stakeholder value, adoption paths, and sustainability instead.

Essentials to capture before progressing:

  • Who is the customer/user? (specific persona, not "everyone")
  • What is their problem? (concrete and felt, not abstract)
  • Why does this matter to them? (stakes and consequences)
  • What's the initial concept for a solution? (even rough)

Fast-track: If the user provides all four essentials in their opening message (or via structured input), acknowledge and confirm understanding, then move directly to document creation and Stage 2 without extended discovery.

Graceful redirect: If after 2-3 exchanges the user can't articulate a customer or problem, don't force it. Point them upstream: bmad-brainstorming if they need to generate options, or bmad-forge-idea if they hold an idea that hasn't been pressure-tested into something sound yet.

Contextual Gathering: Once you understand the concept, gather external context before drafting begins.

  1. Ask about inputs: Ask the user whether they have existing documents, research, brainstorming, or other materials to inform the PRFAQ. Collect paths for subagent scanning — do not read user-provided files yourself; that's the Artifact Analyzer's job.
  2. Fan out subagents in parallel:
    • Artifact Analyzer (agents/artifact-analyzer.md) — Scans {output_folder}/{active_initiative}/, then {output_folder}/, for relevant documents, plus any user-provided paths. Receives the product intent summary so it knows what's relevant.
    • Web Researcher (agents/web-researcher.md) — Searches for competitive landscape, market context, and current industry data relevant to the concept. Receives the product intent summary.
  3. Graceful degradation: If subagents are unavailable, scan the most relevant 1-2 documents inline and do targeted web searches directly. Never block the workflow.
  4. Merge findings with what the user shared. Surface anything surprising that enriches or challenges their assumptions before proceeding.

Create the output document at {doc_workspace}/prfaq-{slug}.md using assets/prfaq-template.md. Write the frontmatter (populate inputs with any source documents used) and any initial content captured during Ignition. This document is the working artifact — update it progressively through all stages.

Coaching Notes Capture: Before moving on, append a <!-- coaching-notes-stage-1 --> block to the output document: concept type and rationale, initial assumptions challenged, why this direction over alternatives discussed, key subagent findings that shaped the concept framing, and any user context captured that doesn't fit the PRFAQ itself.

When you have enough to draft a press release headline, route to references/press-release.md.

Stages

#StagePurposeLocation
1IgnitionRaw concept, enforce customer-first thinkingSKILL.md (above)
2The Press ReleaseIterative drafting with hard coachingreferences/press-release.md
3Customer FAQDevil's advocate customer questionsreferences/customer-faq.md
4Internal FAQSkeptical stakeholder questionsreferences/internal-faq.md
5The VerdictSynthesis, strength assessment, final outputreferences/verdict.md

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Bmad Prfaq AI skill do?

Test a product concept with Amazon's Working Backwards method: write the press release for the finished product first, then answer hard customer and stakeholder questions, ending in a complete PRFAQ document. Use when the user requests to 'create a PRFAQ', 'work backwards', or 'run the PRFAQ challenge'

Why use Bmad Prfaq on TypingMind?

Because you install it once and use it with any model. Bmad Prfaq is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Bmad Prfaq in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/bmad-code-org/BMAD-METHOD/tree/main/skills/bmad-prfaq. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Bmad Prfaq?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Bmad Prfaq?

As many as you like. As long as a model supports skills, you can use Bmad Prfaq with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Bmad Prfaq AI skill free?

It is published on GitHub by bmad-code-org. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇