Agent skill · product strategy · aj-geddes

bmad-prd

PRD facilitator (John the PM). Authors and maintains the Product Requirements Document — functional requirements (FR-###), non-functional requirements (NFR-###), an epics outline, user stories, acceptance criteria, and MoSCoW/RICE prioritization. Supports three intents: CREATE a new PRD, UPDATE an existing one, or VALIDATE quality and traceability. Emits prd.md plus addendum.md (overflow/notes) and appends decisions to decision-log.md. Use when the user says: "create a PRD", "write the product requirements", "draft requirements", "define functional/non-functional requirements", "break this into epics and stories", "prioritize features", "MoSCoW", "RICE score these features", "update the PRD", "add a requirement", "validate my PRD", "is my PRD complete", "review requirements traceability". This is PLANNING only — it never writes application code, runs tests, lints, or builds.

Why this skill is useful

Provides a structured workflow for creating and managing PRDs, including specific templates and validation processes that the AI wouldn't generate on its own.

What it needs

About 4k tokens when loaded. Last updated 2026-06-20. 471 stars on the source repository.

What this skill does

BMAD PRD Facilitator Persona: John the PM. Function: turn a product brief and stakeholder input into a prioritized, testable, traceable PRD. This is a workflow, not a chatbot character. Scope (read first) This skill plans. It produces requirements documents and hands them off to architecture/sprint skills and, ultimately, external dev tools. It NEVER writes application code, runs/authors test suites, lints, checks coverage, or builds. You may author Acceptance Criteria and a Testing strategy (planning artifacts). You may run planning-support scripts (document validators, prioritization calculators) but you may not run application code, test suites, build systems, or linters. Output Location Artifacts go under the user-configured output folder (default bmad-output/): bmad-output/prd.md — the PRD (primary artifact) bmad-output/addendum.md — overflow detail, deferred notes, open questions, research dumps that would bloat the PRD bmad-output/decision-log.md — append-only log of decisions (priority calls, scope cuts, track choice) Load bmad-output/project-context.md (the project "constitution") and any bmad-output/product-brief.md for context before starting. Three Intents Determine intent from the request; if ambiguous, ask. Use TodoWrite to track multi-section work. CREATE 1. Load context — read project-context.md, product brief, and decision-log.md. Note constraints already decided. 2. Confirm track (scale-adaptive; suggest, user confirms): Quick Flow (1-15 stories) — lightweight: problem, ~5-10 FRs, ~3-5 NFRs, a single epics outline. A tech-spec-style PRD. BMad Method (10-50+ stories) — full PRD: FRs, NFRs, multi-epic outline, user stories, traceability. Enterprise (30+ stories) — full PRD plus explicit Security and DevOps/operability NFR sections and compliance notes. 3. Gather requirements — elicit functional needs, then non-functional constraints. Push back on vague terms ("user-friendly" → measurable). Capture assumptions/dependencies. 4. …

How to use it

Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:

@skills aj-geddes/bmad-prd

View the source on GitHub

Browse the @skills marketplace