bmad-prd

Create, update, and validate product requirement documents through guided discovery and reviewer gates.

1|Updated Sep 18, 2026
One-click install
npx skills add https://github.com/PastaSus/egg-defender --skill bmad-prd-pastasus
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: bmad-prd
Source: https://github.com/PastaSus/egg-defender/tree/main/.agents/skills/bmad-prd
Command: npx skills add https://github.com/PastaSus/egg-defender --skill bmad-prd-pastasus

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and assets (resource) components.

What problem does it solve? Writing a PRD that is decision-ready, scoped honestly, and usable by downstream UX, architecture, and story workflows is hard; this Skill guides the process with structured discovery, templates, and multi-reviewer validation instead of producing a hollow document. ## Core Features & Use Cases - Three intent modes: Create a new PRD from a brain dump, Update an existing PRD against a change signal, or Validate a PRD with a seven-dimension quality rubric without modifying it. - Adaptive PRD structure: An Essential Spine template plus an Adapt-In Menu of section clusters (compliance, monetization, API contracts, hardware constraints) selected based on the product's actual concerns and stakes. - Reviewer gate and synthesis: Parallel reviewer subagents write findings to per-reviewer files, then a synthesis pass renders a consolidated HTML and Markdown validation report with severity-tiered findings. - Use Case: A product manager with rough notes and customer research invokes the skill, chooses the coaching path, narrates user journeys, and ends with a finalized PRD, an addendum of deferred depth, and an auditable decision memlog. ## Quick Start Ask the assistant to help you create a PRD for your product idea and answer its discovery questions about vision, users, and scope.

Frequently Asked Questions about bmad-prd

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a PRD with an AI assistant?

Invoke the skill with your product idea and it runs a discovery sequence: brain dump, stakes calibration, and a choice between a fast drafting path or a coaching path. It then drafts the PRD with tagged assumptions and walks a finalize sequence including reviewer passes.

How do I validate an existing PRD for quality?

Use the Validate intent, which critiques the PRD without changing it. A rubric-walker subagent scores seven dimensions such as decision-readiness and done-ness clarity, and the results are synthesized into HTML and Markdown validation reports.

What PRD template structure does it use?

It uses an Essential Spine covering vision, target users, glossary, features with numbered functional requirements, non-goals, MVP scope, success metrics, and assumptions. Additional section clusters like compliance, monetization, or API contracts are pulled in only when the product's concerns warrant them.

Can it run headless without interactive prompts?

Yes. When invoked headless with an intent and inputs, it completes the run without asking questions and returns a JSON status payload with artifact paths, assumptions, and open questions. Ambiguous intent results in a blocked status with a reason.

What are the limitations of the fast path drafting mode?

Fast path batches remaining gaps into one or two questions and drafts the full PRD with [ASSUMPTION] tags where values were inferred. Initial quality depends heavily on how much context you provide upfront, and assumptions must be confirmed during finalization.