BMad PRD Skill for Claude: Create, Update and Validate a PRD

Coaches you through writing, editing or checking a product requirements document, or drafts one fast with assumptions marked.

Installs: 13.2K; on skills.sh
Stars: 54.9K; on GitHub
Files: 8; besides SKILL.md
Updated: Nov 2026; last repo commit

bmad-prd makes Claude act as a facilitator and coach for a PRD. By default it pulls the thinking out of you with open questions instead of writing for you. On the Fast path it batches its gaps into one or two questions, drafts the full PRD and tags what it assumed.

Ask it to produce, edit or validate a PRD and it triggers. It runs web research during discovery, keeps a .memlog.md of decisions, and sends detail that does not fit into an addendum.md. It runs uv scripts from your project's _bmad folder, so you need the rest of the BMad set installed and bmad setup done.

Good for

Founders and product managers who want help writing a PRD without losing their own thinking
Developers who need requirements written down before they build
Teams who want an existing PRD reviewed against a quality rubric

Install bmad-prd

Claude Code

Copy this prompt.

Install the bmad-prd skill in Claude Code. Run this command:

/plugin marketplace add bmad-code-org/bmad-plugins
/plugin install bmad-method@bmad
/plugin install bmad-toolbox@bmad

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Requires uv.

Install the whole BMad set, not just this skill: it calls scripts and sibling skills that the set provides. After installing, open your coding tool in the project and ask the bmad skill to run bmad setup. Every route needs uv (the README says both routes need it for setup and Python scripts). This is the v7 preview alpha, so expect breaking changes between updates. Plugin names differ between sources: the BMAD-METHOD README says to install bmad-method and bmad-core-tools, but the bmad-plugins README and its marketplace manifest list bmad-method and bmad-toolbox, and the bmad skill sits in the toolbox plugin's skills folder. Use the names that /plugin shows after you add the marketplace. Pick one route, not both.

From the project README. Source.

What's in the skill

When it loads

Create, update, or validate a PRD. Use when the user wants help producing, editing, or validating a PRD

Sections in SKILL.md

Conventions
On Activation
Intent Modes
Discovery
PRD Discipline
Reviewer Gate
Finalize

Key facts

Author: bmad-code-org (BMad Code); the plugin marketplace lists Brian (BMad) Madison as owner
License: GitHub detects none for the repo (NOASSERTION); the README and plugin marketplace say MIT
Installs on skills.sh: 13,159 as of 2026-11-02
GitHub stars: 54,859 for the whole BMAD-METHOD repo
Last commit to the repo: 2026-11-01
Files in the skill: 9 files including SKILL.md: bmod.toml, customize.toml, assets/headless-schemas.md, assets/prd-template.md, assets/prd-validation-checklist.md, assets/validation-report-template.html, references/headless.md, references/validate.md
Needs: uv (README), plus the bmad setup skill so the _bmad/scripts folder exists
skills.sh audits: Gen Agent Trust Hub warn, Socket pass, Snyk pass

What it includes

Starts a new PRD in a prd-<slug> folder and seeds a .memlog.md.
Runs Discovery, then Finalize. The PRD gets YAML frontmatter with status draft until it is finalized.
Try: “Help me write a PRD for a booking app.”
Write · Create
Reconciles an existing PRD with a change you describe.
Checks the PRD, addendum and memlog, surfaces conflicts with earlier decisions before applying the change, then runs Finalize.
Write · Update
Critiques a PRD without changing it and builds an HTML report.
Runs a rubric reviewer against the quality checklist plus any extra reviewers, then folds the results into one HTML and markdown report.
Write · Validate
Brain dump, stakes check, then a working-mode choice.
You give context and any existing documents. It asks whether the work is a hobby, internal or a launch, then offers the Fast path or the Coaching path.
Read · Discovery
Spawns web-research subagents to see what exists in the space.
Subagents search and hand the main session a digest of how comparables position themselves.
Network · Research subagents
Vision + Features, or Journey-led.
Vision + Features is capability-first, for enterprise, developer products and internal tools. Journey-led is user-first, for consumer, UX-heavy or multi-stakeholder products.
Read · Coaching entry points
Holds detail that belongs downstream or does not fit the PRD.
Rejected-alternative rationale, options matrices, technical how, in-depth personas and sizing data go here instead of the PRD.
Write · addendum.md
Audits the memlog, reconciles inputs, reviews, triages, polishes and closes.
The close sets status to final and logs "PRD finalized". Common next steps are asking Sofia to write the initiative's requirements, or running bmad-ux or bmad-architecture.
Write · Finalize (8 steps)
Runs without a user, following references/headless.md.
Used when no interactive user is present. references/headless.md sets the rules and ends the run with a JSON response; assets/headless-schemas.md has an example of each payload.
Write · Headless mode

From the official docs

Permissions

Medium risk

It writes files into your project, runs uv scripts, runs web research and starts reviewer subagents. Commit or back up first, and do not paste secrets into the documents you hand it.

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

It writes files into your project
It creates a prd-<slug> folder under your output folder holding the PRD, .memlog.md, an addendum.md and review files, and a validate run builds an HTML report. Commit or back up first and check what it wrote. github.com
It runs web research by default
SKILL.md says to spawn web-research subagents during discovery to see what exists in the space. A configured external_sources list can add internal tools such as knowledge bases or MCP tools. Do not paste secrets into the prompts you give it. github.com
It reads documents you point it at
You can give it briefs, research, transcripts and drafts, and subagents extract from them. Treat anything you hand over as visible to those subagents. github.com
It runs uv scripts from your project
SKILL.md has Claude run resolve_customization.py, resolve_config.py and memlog.py with uv from a _bmad/scripts folder in your project. Those scripts come from the bmad skill, not from this folder, so read them there if you want to know what they do. github.com
Project override files steer Claude
Claude reads customize.toml plus optional team and personal override files, runs their activation steps and external handoffs, and loads their persistent facts. Anyone who can edit those files in your repo can change what the skill does, so review them in pull requests. github.com

Technical details

Sign-in and keys	SKILL.md names no sign-in or API key.
Scopes	Runs uv scripts (resolve_customization.py, resolve_config.py, memlog.py) Writes a prd-<slug> folder with the PRD, .memlog.md, addendum.md and reviews Web research subagents

Questions

What does the bmad-prd skill do?

It helps you create, edit or check a PRD. It coaches you with open questions by default, or drafts the whole document quickly with [ASSUMPTION] tags, then runs reviewers over it.

How do I install bmad-prd?

Use the install box above and install the whole BMad set. The skill needs the scripts and sibling skills in it, so installing it alone does not work. Then ask the bmad skill to run bmad setup.

Does it need an API key?

SKILL.md names no API key. It needs uv, which the README lists as required for BMad setup and its Python scripts.

Is bmad-prd safe to run?

It writes a folder of files into your project, runs uv scripts, runs web research and starts reviewer subagents. Commit or back up first, and do not paste secrets into the documents you hand it. The Permissions section lists the details.

What if I only need a one-pager or a quick build?

SKILL.md says to suggest other skills when the first message points elsewhere: bmad-build for an express build, bmad-product-brief for a one-pager, and bmad-prfaq to vet a product idea.

bmad-prd vs bmad-agent-pm?

bmad-prd is the workflow that writes, edits or validates the PRD. bmad-agent-pm is the John persona whose PRD menu item calls it. You can invoke bmad-prd directly.

Information

updated Nov 2, 2026

Repository: bmad-code-org/bmad-method
Folder: skills/bmad-prd

bmad-code-org/bmad-method skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 7

BMAD-METHOD README · github.com
bmad-plugins README · github.com
bmad-prd SKILL.md · github.com
validate.md · github.com
bmad-agent-pm customize.toml · github.com
customize.toml · github.com
bmad skill memlog.py · github.com