bmad-forge-idea Skill for Claude Code: Pressure-Test an Idea

BMad Method skill that questions a half-formed idea, with different personas probing its weak points, until you can act on it or drop it.

Installs: 12.6K; on skills.sh
Stars: 54.9K; on GitHub
Files: 4; besides SKILL.md
Updated: Nov 2026; last repo commit

Tell it an idea and what you want from the session: understand it, test it or improve it. It asks one question at a time, presses on vague claims and uses two voices per turn, one from a persona pool and one it invents. You can say "attack this", "defend this" or "switch roles" at any time.

It ends as Hardened, Killed or Clearer, and always renders a forge-report.html. It only works in a project where BMad is set up, because its SKILL.md runs scripts from the project's _bmad folder through uv. The folder has 5 files including SKILL.md, with one Python helper and its tests.

Good for

Founders with an idea they have not examined yet
Product managers who want assumptions challenged before planning
Anyone who wants to think an idea through, kill it early or sharpen it

Install bmad-forge-idea

Claude Code

Copy this prompt.

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

/plugin marketplace add bmad-code-org/bmad-plugins

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.

bmad-forge-idea needs BMad set up in your project: its SKILL.md runs a script from the project's _bmad folder and tells the agent to run the bmad skill's setup when that script is missing. Pick one route, not both. The marketplace manifest lists this skill's folder under the bmad-toolbox plugin, so install bmad-toolbox after you add the marketplace, plus the plugin that holds the bmad skill (the bmad-plugins README names bmad-method and bmad-toolbox). Then ask the bmad skill to run bmad setup. Skills CLI route: it asks which coding tools to install to, so choose Claude Code, then ask the bmad skill to run bmad setup. BMad needs uv for its setup and Python scripts. The README calls v7 a preview alpha with breaking changes between updates.

From the project README. Source.

What's in the skill

When it loads

Test a half-formed idea in a questioning conversation, with different personas probing its weak points, until the user can act on it or drop it with confidence. Optionally writes a short brief for planning skills to build on. Use when the user says 'forge an idea', 'pressure-test this idea', 'stress-test my thinking', or 'harden this idea'

Sections in SKILL.md

Overview
Conventions
On Activation
Open the session
Discover intent
Steering the conversation
Set up the session
The forge
The personas
Exits

Key facts

Author: BMad Code (owner of the bmad-code-org/bmad-method repo)
License: README and the plugin marketplace manifest say MIT; GitHub reports no detected license
Installs on skills.sh: 12,609 as of 2026-11-02
GitHub stars: 54,859 for the whole bmad-code-org/bmad-method repo, 2026-11-02
Last repo commit: 2026-11-01
Files: 5 files including SKILL.md (1 Python helper and its tests, 2 config files)
Needs: uv, and BMad set up in the project (SKILL.md)

What it includes

Confirms the idea, your goal and whether it changes an existing project.
Read · Open the session
Say these at any time to change how the idea is argued.
Read · Attack, defend, switch roles
Mixes one persona from an installed or custom pool with one invented outside voice.
resolve_personas.py lists installed agents, custom personas and saved parties.
Runs code · Personas
Records each decision, assumption, crack, kill and lock to a session log on disk.
Lets the session resume after an interruption.
Runs code · Memlog capture
Distills the locked decisions into a very short forged idea file.
Write · Exit: Hardened
States plainly that the idea does not hold up and records why.
Write · Exit: Killed
Leaves the log as the record when no idea is ready to hand off.
Write · Exit: Clearer
Always renders a self-contained report with the outcome stamp.
Write · forge-report.html

From the official docs

Permissions

Low risk

It writes a session log and a report file into your project and can read project files to check your claims. Look at the workspace folder it names before you commit.

What it can do

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

Watch out for

It writes session files into your project
The session keeps a memlog on disk and always renders forge-report.html in the workspace. Check the folder it names before you commit your project. github.com
For existing projects it reads your files
SKILL.md tells the agent to treat an existing project's files as the source of truth and check your claims against them. github.com
This is a preview release
The BMAD-METHOD README calls v7 a preview alpha with breaking changes between updates. github.com

Technical details

Scopes	Runs uv run on _bmad/scripts in your project (resolve_customization.py, resolve_config.py, memlog.py) Runs scripts/resolve_personas.py, which calls other resolver scripts and reads TOML override files Writes a forge workspace with a memlog, an optional forged idea and forge-report.html

Questions

What does bmad-forge-idea do?

It pressure-tests a half-formed idea in a questioning conversation. Different personas probe its weak points until you can act on the idea or drop it.

How do I install it?

Use the install box at the top of this page. After installing, ask the bmad skill to run bmad setup, because this skill needs BMad set up in the project.

Does it work in the Claude app or claude.ai?

This page documents no install for the Claude app. The skill needs uv and a project folder with BMad set up, so the box lists Claude Code, Codex and the skills CLI.

Is it safe?

It writes a session log and an HTML report into your project, and for an existing project it reads your files to check your claims. Our advice: check the workspace folder it names before you commit.

Will it just agree with me?

No. SKILL.md says not to use agreement or praise to smooth the conversation, and in attack mode the assistant never agrees with the idea until you end the mode.

Does it have to produce a document?

No. SKILL.md says the goal is better thinking, not an artifact. Strengthening, rejecting or clarifying an idea are all complete outcomes, and the forged idea file is optional.

bmad-forge-idea vs bmad-prfaq?

Forge-idea is for an idea not yet tested. The bmad-prfaq skill is a structured challenge for a concept with a customer and problem, and it points you to forge-idea when you cannot name them.

Information

updated Nov 2, 2026

Repository: bmad-code-org/bmad-method
Folder: skills/bmad-forge-idea

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

Sources

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

Show all 5

README.md · github.com
README.md · github.com
marketplace.json · github.com
SKILL.md · github.com
resolve_personas.py · github.com