Run any Skill in Manus with one click

bmad-prd

Stars467

Forks73

UpdatedJune 20, 2026 at 01:58

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.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

aj-geddes

aj-geddes/claude-code-bmad-skills

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Project Management SpecialistsBusiness and Financial Operations Occupations·SOC 13-1082

File Explorer

6 files

SKILL.md

readonly

name	bmad-prd
description	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.
allowed-tools	Read, Write, Edit, Bash, Glob, Grep, WebSearch, WebFetch, TodoWrite

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

Load context — read project-context.md, product brief, and decision-log.md. Note constraints already decided.
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.
Gather requirements — elicit functional needs, then non-functional constraints. Push back on vague terms ("user-friendly" → measurable). Capture assumptions/dependencies.
Organize — assign IDs (FR-001, NFR-001), categorize NFRs by quality attribute, apply MoSCoW. For contested ordering, run RICE (see below).
Outline epics & stories — group FRs into epics; sketch user stories ("As a… I want… so that…") with Given/When/Then acceptance criteria. Epics here are an outline — detailed story files are produced later by the sprint/story skills.
Write traceability — map each requirement → business goal → epic → story.
Emit — fill ${CLAUDE_PLUGIN_ROOT}/skills/bmad-prd/templates/prd.template.md → prd.md. Park overflow in addendum.md via ${CLAUDE_PLUGIN_ROOT}/skills/bmad-prd/templates/addendum.template.md. Append decisions to decision-log.md.
Validate — run the validator (below).

UPDATE

Read the existing prd.md and decision-log.md.
Make the change surgically with Edit — add/modify FRs/NFRs/epics, re-prioritize, adjust scope. Keep IDs stable; never renumber existing requirements (append new ones).
If the change reflects a real decision (scope cut, priority flip, new NFR), append a dated entry to decision-log.md with the rationale.
Move superseded or deferred material to addendum.md rather than deleting it.
Re-run the validator.

VALIDATE

Run bash ${CLAUDE_PLUGIN_ROOT}/skills/bmad-prd/scripts/validate-prd.sh bmad-output/prd.md.
Read the output and the PRD. Report: missing sections, requirements lacking IDs/priority/acceptance criteria, vague/untestable language, broken traceability, priority inflation (everything "MUST").
Recommend fixes. Do not silently edit during a pure validation pass — report, then offer to fix.

Requirements at a Glance

FR-### — what the system does. Format: FR-001: MUST — <capability> plus 3-5 testable acceptance criteria. Describe WHAT/WHY, never HOW.
NFR-### — quality attributes: Performance, Security, Scalability, Reliability, Usability, Maintainability (+ Compliance/Operability for Enterprise). Must be measurable (e.g. "p95 < 200ms", not "fast").
See REFERENCE.md for the full FR/NFR taxonomy and requirement-quality rules.

Prioritization

MoSCoW (default) — Must / Should / Could / Won't. Won't is explicit out-of-scope; keep it visible. If everything is Must, nothing is — push back.
RICE (for contested or large feature sets) — (Reach × Impact × Confidence) / Effort. Run the helper:
```
python3 ${CLAUDE_PLUGIN_ROOT}/skills/bmad-prd/scripts/prioritize.py              # interactive
python3 ${CLAUDE_PLUGIN_ROOT}/skills/bmad-prd/scripts/prioritize.py -b feats.csv # batch (name,reach,impact,confidence,effort)
```
RICE produces a ranked list; you translate the ranking into MoSCoW buckets and log the rationale in decision-log.md. RICE/MoSCoW are planning math, not estimation — do NOT assign story points, velocity, or burndown. Story sizing ("small enough for one agent session, ~2-8h") happens in the sprint/story skills; delivery is count-based.

Validation Checklist

Every requirement has a unique ID and a MoSCoW priority
Every FR has testable acceptance criteria; every NFR is measurable
Epics group related FRs; user stories use "As a… I want… so that…"
Out-of-scope (Won't) list is explicit
Traceability: requirement → goal → epic → story
Decisions captured in decision-log.md

Handoff

The PRD feeds the architecture skill (system design) and the sprint/story skills (which compile ready-for-dev story files). State the recommended next step when done. The PRD is the last word on what; implementation is owned by external dev tools.

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-prd. All methodology credit belongs to the BMAD Code Organization.

More from this repository

same repository

bmad-builder

aj-geddes/claude-code-bmad-skills

Meta-skill for scaffolding and validating custom PLANNING/ORCHESTRATION skills within the BMAD Planning & Orchestrator plugin. Produces the full skill directory: SKILL.md, scripts, and templates — all pre-targeted at this plugin's path conventions. Includes a scope-violation checker so newly created skills never drift into dev/lint/build/coverage territory. Use when the user says "create a skill", "scaffold a skill", "build a new planning skill", "add a skill to the orchestrator", "extend BMAD planning", "custom orchestration skill", "validate this skill", "check this skill for scope violations", "new skill for the planner", or "bmad-builder". Supports three intents: Create (new skill skeleton), Validate (check an existing SKILL.md), Scaffold (directory structure only). This skill plans and scaffolds only — it NEVER writes application code, runs tests, lints, or builds.

2026-06-20467

bmad-architecture

aj-geddes/claude-code-bmad-skills

Solutioning skill (Winston, the Architect). Produces architecture.md with ADRs and systematic NFR coverage, mapping every FR/NFR from the PRD to a concrete design decision. ONE architecture forces all future parallel dev agents to share the same API style, data model, state management, naming conventions, and security approach — catching alignment here is 10x cheaper than during implementation. Use when the user says "design the architecture", "create architecture", "/architecture", "solutioning", "tech stack", "system design", "ADR", "architecture decision record", "data model", "API design", "NFR coverage", "non-functional requirements", or after a PRD is done and they ask "what's next" / "ready for solutioning". Supports Create (new architecture.md), Update (revise against PRD changes), and Validate (check coverage + ADR completeness). PLANS only — never writes application code, runs tests, lints, or builds.

2026-06-20467

bmad-brainstorm

aj-geddes/claude-code-bmad-skills

Facilitates structured ideation sessions using proven brainstorming techniques (SCAMPER, SWOT, 5 Whys, Mind Mapping, Six Thinking Hats, Reverse Brainstorming, Starbursting, Brainwriting). Produces a brainstorming-report.md of organized ideas and actionable insights. Operates in three intents: Create (new session), Update (add techniques or deepen coverage), Validate (confirm insights align with project goals). Use when the user says: "brainstorm", "ideate", "generate ideas", "explore options", "SCAMPER", "SWOT analysis", "mind map", "Six Thinking Hats", "5 Whys", "creative session", "what if we", "let's explore", "think through possibilities", "find alternatives", or "problem-solve". This skill PLANS only — it never writes application code or runs tests.

2026-06-20467

bmad-correct-course

aj-geddes/claude-code-bmad-skills

CROSS-PHASE mid-stream scope correction. Re-enters planning when requirements, features, architecture, or constraints change after planning has started. Re-shards affected epics/stories, re-sequences sprint-status.yaml, appends rationale to decision-log.md. Routes to bmad-epics-and-stories, bmad-sprint-planning, or bmad-parallel-plan as needed. Changes the PLAN, never code. Use when: "we need to change course", "scope has changed", "new requirement came in", "we're dropping feature X", "we need to pivot", "re-plan after the change", "requirements changed mid-sprint", "correct course", "architecture changed", "re-scope the backlog", "update epics after feedback", "cancel story X", "add epic for Y", "change the plan", "we got new constraints", or when stories are split/merged/reordered due to a decision not in the original plan. Produces: updated epics.md (affected only), revised/new story files, updated sprint-status.yaml, new decision-log.md entry. NEVER writes code or runs tests.

2026-06-20467

bmad-document-project

aj-geddes/claude-code-bmad-skills

BROWNFIELD planning input. Scans an existing codebase READ-ONLY and writes project-documentation.md — ground truth for stack, structure, key flows, conventions, and integration points — so downstream BMAD planning skills start from reality. Does NOT modify code; produces only the doc artifact. Use when the user says: "document this codebase", "document the project", "document my app", "scan the existing code", "brownfield planning", "we have existing code, start planning", "map what's already built", "document current state", "capture the current architecture", "understand the existing system before planning", "write project-documentation.md", or before a PRD or architecture doc when the user already has code written. Three intents: Create (initial scan), Update (re-scan changed areas), Validate (check completeness). Plans only — reads code but never writes it, runs no tests, no linters, no build tools, no application code.

2026-06-20467

bmad-epics-and-stories

aj-geddes/claude-code-bmad-skills

Solutioning flagship — shards a PRD + architecture into epics.md and individual {epic}.{story}.{slug}.story.md context objects, the LAST planning artifact before external dev handoff. Each story is a self-contained ~8K-token compiled context object: Dev Notes with SOURCE CITATIONS back to prd.md/architecture.md, Acceptance Criteria, Tasks/Subtasks mapped to ACs, Testing strategy, Dependency Maps, an explicit Owned File/Module Scope list (the lever for parallel-conflict-free scheduling), and Learnings from Previous Stories. Sized to one dev-day; split if larger; NO story points. Use when the user says "shard the PRD", "create epics", "break the PRD into epics", "break this epic into stories", "create stories", "create a story", "draft story files", "generate the story for X", "prepare stories for dev", "mark the story ready for dev", "validate this story", or "what stories are in this epic". Three intents: Create new epics/stories, Update an existing story, or Validate a draft against the contract.

2026-06-20467

name	bmad-prd
description	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.
allowed-tools	Read, Write, Edit, Bash, Glob, Grep, WebSearch, WebFetch, TodoWrite

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)

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

Load context — read project-context.md, product brief, and decision-log.md. Note constraints already decided.
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.
Gather requirements — elicit functional needs, then non-functional constraints. Push back on vague terms ("user-friendly" → measurable). Capture assumptions/dependencies.
Organize — assign IDs (FR-001, NFR-001), categorize NFRs by quality attribute, apply MoSCoW. For contested ordering, run RICE (see below).
Outline epics & stories — group FRs into epics; sketch user stories ("As a… I want… so that…") with Given/When/Then acceptance criteria. Epics here are an outline — detailed story files are produced later by the sprint/story skills.
Write traceability — map each requirement → business goal → epic → story.
Emit — fill ${CLAUDE_PLUGIN_ROOT}/skills/bmad-prd/templates/prd.template.md → prd.md. Park overflow in addendum.md via ${CLAUDE_PLUGIN_ROOT}/skills/bmad-prd/templates/addendum.template.md. Append decisions to decision-log.md.
Validate — run the validator (below).

UPDATE

Read the existing prd.md and decision-log.md.
Make the change surgically with Edit — add/modify FRs/NFRs/epics, re-prioritize, adjust scope. Keep IDs stable; never renumber existing requirements (append new ones).
If the change reflects a real decision (scope cut, priority flip, new NFR), append a dated entry to decision-log.md with the rationale.
Move superseded or deferred material to addendum.md rather than deleting it.
Re-run the validator.

VALIDATE

Run bash ${CLAUDE_PLUGIN_ROOT}/skills/bmad-prd/scripts/validate-prd.sh bmad-output/prd.md.
Read the output and the PRD. Report: missing sections, requirements lacking IDs/priority/acceptance criteria, vague/untestable language, broken traceability, priority inflation (everything "MUST").
Recommend fixes. Do not silently edit during a pure validation pass — report, then offer to fix.

Requirements at a Glance

FR-### — what the system does. Format: FR-001: MUST — <capability> plus 3-5 testable acceptance criteria. Describe WHAT/WHY, never HOW.
NFR-### — quality attributes: Performance, Security, Scalability, Reliability, Usability, Maintainability (+ Compliance/Operability for Enterprise). Must be measurable (e.g. "p95 < 200ms", not "fast").
See REFERENCE.md for the full FR/NFR taxonomy and requirement-quality rules.

Prioritization

MoSCoW (default) — Must / Should / Could / Won't. Won't is explicit out-of-scope; keep it visible. If everything is Must, nothing is — push back.
RICE (for contested or large feature sets) — (Reach × Impact × Confidence) / Effort. Run the helper:
```
python3 ${CLAUDE_PLUGIN_ROOT}/skills/bmad-prd/scripts/prioritize.py              # interactive
python3 ${CLAUDE_PLUGIN_ROOT}/skills/bmad-prd/scripts/prioritize.py -b feats.csv # batch (name,reach,impact,confidence,effort)
```
RICE produces a ranked list; you translate the ranking into MoSCoW buckets and log the rationale in decision-log.md. RICE/MoSCoW are planning math, not estimation — do NOT assign story points, velocity, or burndown. Story sizing ("small enough for one agent session, ~2-8h") happens in the sprint/story skills; delivery is count-based.

Validation Checklist

Every requirement has a unique ID and a MoSCoW priority
Every FR has testable acceptance criteria; every NFR is measurable
Epics group related FRs; user stories use "As a… I want… so that…"
Out-of-scope (Won't) list is explicit
Traceability: requirement → goal → epic → story
Decisions captured in decision-log.md

Handoff

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-prd. All methodology credit belongs to the BMAD Code Organization.