bmad-product-brief Skill: Write, Update or Check a Product Brief With Claude

Coaches you through writing, updating or validating a short product brief, and saves it as a file with a decision log.

Installs: 13.1K; on skills.sh
Stars: 54.9K; on GitHub
Files: 3; besides SKILL.md
Updated: Nov 2026; last repo commit

bmad-product-brief is a BMad Method skill that makes Claude act as a product analyst coach. You bring an idea, an existing brief or one to test, and it works in three modes: create, update or validate. In create mode it asks for a brain dump first, then offers a fast path (batched questions, [ASSUMPTION] tags) or a coaching path (section by section, with pushback on thin answers).

It needs the BMad setup. The skill runs uv run scripts from the project's _bmad/scripts folder, which the bmad skill puts there, and saves the brief under your output folder as brief-{slug}/brief-{slug}.md with a .memlog.md decision log. It aims for 1 to 2 pages.

Good for

Founders and product people turning a rough idea into a brief
Teams that want a brief pressure-tested before it feeds a PRD
Developers using the BMad Method who start planning with a brief
Anyone pitching soon who wants a fast draft with assumptions flagged

Install bmad-product-brief

Claude Code

Copy this prompt.

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

npx skills add bmad-code-org/BMAD-METHOD --skill bmad --skill bmod-method --skill bmad-product-brief

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 Node.js, Git, uv.

bmad-product-brief belongs to the bmod-method module and needs the bmad skill, which sets up the _bmad folder in your project. The README needs uv for BMad setup and Python scripts. These are the v7 preview alpha skills from the main branch, which the README says change often. There is no Claude app upload route, because the skill runs uv scripts inside a project folder. The plugin marketplace repo lists the plugins as bmad-method and bmad-toolbox, while the main README calls the second one bmad-core-tools. The plugin tree holds skills only, with no hooks or MCP files.

Built from the package data we hold. Not yet tested by us.

What's in the skill

When it loads

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

Sections in SKILL.md

On Activation
Intent Operating Modes
Headless Mode
Discovery
Constraints
Finalize

Key facts

Author: BMad Code (bmad-code-org)
Repository: bmad-code-org/bmad-method
Installs on skills.sh: 13,064 as of 2026-11-02
GitHub stars: 54,859 for the whole repo, 2026-11-02
Last commit to the repo: 2026-11-01
Files: 4 files including SKILL.md (assets/brief-template.md, bmod.toml, customize.toml)
License: MIT per the repo LICENSE file and README (GitHub license detection reports NOASSERTION)
Module: Part of bmod-method; needs the bmad skill and uv
Status: README calls these v7 skills a preview alpha
Saves to: {output_folder}/{active_initiative}/brief-{slug}/brief-{slug}.md plus .memlog.md and an optional addendum.md

What it includes

Builds a new brief from a brain dump, then fast or coaching path
Starts with discovery before any drafting, then creates a run folder with the brief, a draft status and a seeded decision log. The default template has Executive Summary, The Problem, The Solution, What Makes This Different, Who This Serves, Success Criteria, Scope and Vision, and Claude adapts it to your product.
Try: “Help me create a product brief for a habit-tracking app.”
Runs code · Create
Reconciles an existing brief with a change before editing it
Reads the brief, addendum, decision log and original inputs first, and surfaces conflicts with earlier decisions before changing anything.
Write · Update
Critiques a brief against its own purpose and cites specific lines
Returns the critique inline with no separate file unless asked, then offers to roll the findings into an update.
Read · Validate
Brain dump, source material, stakes, optional web-research subagents
Claude asks for the full picture and any memo, deck or transcript you have. During the dump it spawns web-research subagents to ground the picture and suggests bmad-deep-recon for deeper market work.
Network · Discovery
Runs without questions and ends with a JSON status block
When invoked headless it does not ask. It finishes with JSON listing status, intent and artifact paths, or a blocked status if the intent is unclear.
Headless mode
Memlog audit, polish pass, external handoffs, ready message
Accounts for each decision-log entry, applies document standards (by default a bmad-review structure and prose pass), runs any configured handoffs and tells you where the files are.
Write · Finalize
uv run resolve_customization.py, resolve_config.py and memlog.py from _bmad/scripts
These are installed by the bmad skill, not bundled in this folder. The decision log is only written through memlog.py.
Runs code · scripts it calls

From the official docs

Permissions

Low risk

The skill runs setup scripts from your project and writes brief files to your output folder. Check what you put in external handoffs before enabling them.

What it can do

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

Watch out for

It runs scripts from your project
The skill calls uv run on scripts in _bmad/scripts, put there by the bmad skill. Read them if you did not install BMad yourself. github.com
External handoffs can send files out
customize.toml has an external_handoffs list, empty by default. If your team fills it, Finalize runs those tools, such as a Confluence upload. github.com
It does web research for you
SKILL.md has Claude spawn web-research subagents during the brain dump. Check your coding tool's search settings if your idea is confidential. github.com

Technical details

Scopes	Runs uv run scripts from the project's _bmad/scripts folder Writes brief-{slug}.md, .memlog.md and an optional addendum.md under the output folder Spawns web-research subagents during discovery

Questions

What does bmad-product-brief do?

It coaches you through creating, updating or validating a product brief and saves it as a markdown file with a decision log.

How do I install bmad-product-brief in Claude Code or Codex?

Use the install box at the top of this page. It installs the skill with the bmad hub skill and its module record. Then ask bmad to run bmad setup in your project.

Does it need anything besides the skill?

Yes. It needs the bmad skill and its setup in your project, and uv to run the Python scripts. Without setup, the skill offers to run it.

Does it need an API key?

No key is named in SKILL.md. It can spawn web-research subagents during discovery, so it uses whatever web search your coding tool provides.

Is it safe?

It writes a brief, a decision log and an optional addendum into your output folder, and runs uv scripts from your project. Configured external handoffs, empty by default, can post files to tools such as Confluence, so review any you add.

Which other BMad skills does it use?

SKILL.md mentions bmad-party-mode and bmad-advanced-elicitation as optional extras, and bmad-deep-recon for deep market work. Its default polish step calls bmad-review, which is in the full BMad set.

Does it work in the Claude app?

The install box leaves out a Claude app upload route, because the skill runs uv scripts inside your project folder. Use Claude Code, Codex or another coding tool that supports skills.

Information

updated Nov 2, 2026

Repository: bmad-code-org/bmad-method
Folder: skills/bmad-product-brief

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

Sources

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

Show all 6

BMAD-METHOD README · github.com
bmad-plugins README · github.com
bmad-plugins marketplace.json · github.com
bmad-product-brief SKILL.md · github.com
brief-template.md · github.com
customize.toml · github.com