bmad-advanced-elicitation Skill: Pressure-Test Claude's Last Answer With Named Methods

Offers a menu of named critique methods, such as pre-mortem, first principles and red team, to improve Claude's most recent output.

Installs: 12.9K; on skills.sh
Stars: 54.9K; on GitHub
Files: 5; besides SKILL.md
Updated: Nov 2026; last repo commit

bmad-advanced-elicitation is a BMad Method skill that pushes Claude to reconsider and refine something it just produced. You can call it on any recent output, or other BMad skills call it at natural pauses. It offers five methods picked from a catalog, you choose one or several, Claude runs them and shows proposed changes, and nothing is applied until you accept.

The catalog is a CSV with 71 methods in 12 categories, served by a Python script so the whole list never loads into context. It needs the BMad setup, because it runs uv run scripts from _bmad/scripts.

Good for

Anyone who wants Claude to challenge its own draft, plan or decision
Teams stress-testing a plan with a pre-mortem or red team
BMad users whose other skills hand work to this one for a deeper pass
Writers who want a reframing, such as first principles or the 5 whys

Install bmad-advanced-elicitation

Claude Code

Copy this prompt.

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

npx skills add bmad-code-org/BMAD-METHOD --skill bmad --skill bmod-core-tools --skill bmad-advanced-elicitation

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-advanced-elicitation belongs to the bmod-core-tools 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

Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team

Sections in SKILL.md

Conventions
On Activation
Serving the Catalog
The Menu
Running a Method

Key facts

Author: BMad Code (bmad-code-org)
Repository: bmad-code-org/bmad-method
Installs on skills.sh: 12,891 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: 6 files including SKILL.md (assets/methods.csv, scripts/pick_methods.py with a test, bmod.toml, customize.toml)
License: MIT per the repo LICENSE file and README (GitHub license detection reports NOASSERTION)
Module: Part of bmod-core-tools; needs the bmad skill and uv
Status: README calls these v7 skills a preview alpha
Catalog: 71 methods in 12 categories (counted from methods.csv)

What it includes

Five methods plus Reshuffle, List all and Proceed
Claude picks 2 to 4 fitting categories, hand-picks five methods and waits for your choice. Reshuffle draws five new ones, List all shows the catalog, Proceed hands the improved version back.
Try: “Run a pre-mortem on this plan.”
Menu
Applies a method to the target and shows proposed changes
Each method works on the current enhanced version, so refinements build up. You can apply or reject a proposal, and nothing changes unless you accept.
Running a method
Serves the catalog: categories, list, show, random
Run through uv run on the CSV. It has the commands categories, list, show and random so the full catalog never enters context.
Runs code · scripts/pick_methods.py
71 methods such as Tree of Thoughts, Red Team vs Blue Team, 5 Whys
Categories include collaboration, core, creative, advanced, risk, technical, framing, research, competitive, learning, philosophical and retrospective.
Read · assets/methods.csv
Round tables and panels reuse party members or installed agents
When a method needs personas, Claude reuses bmad-party-mode members if a party is active, otherwise resolves installed agents with roster.py, otherwise invents viewpoints.
Runs code · Persona methods
preferences, additional_methods and methods_file settings
customize.toml lets a team hold standing preferences and add methods to the catalog.
Customization

From the official docs

Permissions

Low risk

The skill runs uv scripts from your project and only changes your text after you accept a proposal.

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 resolve_customization.py and its own pick_methods.py, and may call roster.py for persona methods. github.com

Technical details

Scopes	Runs uv run scripts from the project's _bmad/scripts folder Runs scripts/pick_methods.py on the methods CSV Applies edits to your text only when you accept a proposal

Questions

What does bmad-advanced-elicitation do?

It offers named critique and reframing methods and applies the ones you pick to Claude's latest output, then hands back an improved version.

How do I install bmad-advanced-elicitation 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 change my work without asking?

No. SKILL.md says it never changes the work unless you accept the proposal, and a rejected proposal is dropped entirely.

Which methods are in it?

The catalog has 71, including Socratic Questioning, First Principles Analysis, Pre-mortem Analysis, Red Team vs Blue Team, Six Thinking Hats and Stakeholder Round Table.

Is it safe?

It reads a CSV catalog through a bundled Python script and changes your text only after you accept a proposal. It runs uv scripts from your project, so install it from a source you trust.

How does it differ from bmad-party-mode?

Party mode runs a group discussion between personas. Advanced elicitation runs one method at a time against a piece of work, and can borrow party members for persona-based methods.

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-advanced-elicitation

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-plugins marketplace.json · github.com
bmad-advanced-elicitation SKILL.md · github.com
customize.toml · github.com
methods.csv · github.com
pick_methods.py · github.com