bmm-skills

Routes requests to the BMad Method (v6.12.4) agile framework: persona agents, planning skills (brief, PRFAQ, PRD, UX, spec, architecture, epics, sprint planning), shipping skills (build, code review,

SKILL.md

GitHub

Attribution: The skills in this folder are sourced from bmad-code-org/BMAD-METHOD v6.12.4 by BMad Code, LLC, licensed MIT. BMad and BMad Method are trademarks of BMad Code, LLC; this collection is not affiliated with or endorsed by it. This router was written for this collection.

BMad Method router

This file holds no workflow logic. It routes a request to the one sub-skill that handles it. The folder mirrors upstream's layout:

agents/   persona agents (Mary, John, Sally, Winston, Amelia)
plan/     brief, PRFAQ, PRD, UX, spec, architecture, epics and stories, sprint planning, project context
ship/     build, unattended build loop, code review, walkthrough, QA tests, correct course, retrospective
core/     brainstorming, idea forging, research, review lenses, elicitation, party mode, help, customize

module.yaml (method) and core/module.yaml hold the shared settings and the agent roster. module-help.csv and core/module-help.csv list every skill with its menu code, phase, and what usually comes before and after it.

Before first use

The sub-skills call helper scripts that the BMad installer puts in the project: {project-root}/_bmad/scripts/ (render_skill.py, resolve_customization.py, resolve_config.py, memlog.py), run with uv and Python 3.11 or later. Set a project up once with:

npx bmad-method install

Most skills fall back to their own customize.toml defaults when a script is missing. bmad-build and bmad-build-auto do not: they stop and report the error. If _bmad/ is absent and the user wants Build, tell them to run the installer first.

Routing

  1. The user names an agent? Load that persona skill and let it take over.
  2. The user names an artifact or action? Match it in the tables below.
  3. Unsure where to start, or asks what to do next? Load core/bmad-help/SKILL.md; it reads the project state and recommends the next skill.
  4. Just a code change? ship/bmad-build/SKILL.md is the standard implementation flow at any size.

Read only the sub-skill that matches. Each one resolves its own customization when it starts.

Agents

Agent Role Skill
Mary 📊 Business analyst: market research, competitive analysis, requirements agents/bmad-agent-analyst/SKILL.md
John 📋 Product manager: PRDs and requirements discovery agents/bmad-agent-pm/SKILL.md
Sally 🎨 UX designer and UI specialist agents/bmad-agent-ux-designer/SKILL.md
Winston 🏗️ System architect: technical design agents/bmad-agent-architect/SKILL.md
Amelia 💻 Senior engineer: implements stories and code changes agents/bmad-agent-dev/SKILL.md

Plan

Request Skill
Capture a product idea in a brief plan/bmad-product-brief/SKILL.md
Stress-test a concept with Working Backwards (press release plus FAQ) plan/bmad-prfaq/SKILL.md
Create, update, or validate a PRD plan/bmad-prd/SKILL.md
Condense any input into a short SPEC.md, or split a spec into stories plan/bmad-spec/SKILL.md
UX design: DESIGN.md and EXPERIENCE.md plan/bmad-ux/SKILL.md
Architecture decisions document plan/bmad-architecture/SKILL.md
Break requirements into epics and stories plan/bmad-create-epics-and-stories/SKILL.md
Readiness check and sprint status file; sprint progress summary plan/bmad-sprint-planning/SKILL.md
Set up or refresh the repo's AGENTS.md block for agents plan/bmad-project-context/SKILL.md

Ship

Request Skill
Implement a feature, story, bug fix, or change ship/bmad-build/SKILL.md
One iteration of an unattended build loop (only when invoked by name) ship/bmad-build-auto/SKILL.md
Review code changes with parallel reviewers ship/bmad-code-review/SKILL.md
Walk a human reviewer through a change ship/bmad-walkthrough/SKILL.md
Generate API and end-to-end tests for built features ship/bmad-qa-generate-e2e-tests/SKILL.md
Assess a significant mid-sprint change ship/bmad-correct-course/SKILL.md
Retrospective on a finished epic ship/bmad-retrospective/SKILL.md

Core

Request Skill
Brainstorm or ideate core/bmad-brainstorming/SKILL.md
Test a half-formed idea through probing personas core/bmad-forge-idea/SKILL.md
Research to support a decision (market, domain, technical) core/bmad-deep-recon/SKILL.md
Review a diff, PR, or document with review lenses core/bmad-review/SKILL.md
Push a draft further (pre-mortem, first principles, red team) core/bmad-advanced-elicitation/SKILL.md
Several agents discuss a topic together core/bmad-party-mode/SKILL.md
What to do next, or questions about BMad core/bmad-help/SKILL.md
Change how an installed BMad skill behaves core/bmad-customize/SKILL.md

Usual chain

brief or PRFAQ → PRD (plus UX when there is a UI) → architecture → epics and stories → sprint planning → build → code review → retrospective. A spec can stand in for the brief and PRD on small work. Run correct course when a change mid-sprint invalidates the plan.

Names from earlier v6 releases

Older BMad guides use names that upstream has since merged or retired. Route them like this:

Old name Now
bmad-quick-dev, bmad-create-story, bmad-dev-story ship/bmad-build
bmad-dev-auto ship/bmad-build-auto
bmad-create-prd, bmad-edit-prd, bmad-validate-prd plan/bmad-prd
bmad-create-architecture plan/bmad-architecture
bmad-create-ux-design plan/bmad-ux
bmad-check-implementation-readiness, bmad-sprint-status plan/bmad-sprint-planning
bmad-checkpoint-preview ship/bmad-walkthrough
bmad-domain-research, bmad-market-research, bmad-technical-research core/bmad-deep-recon
bmad-document-project, bmad-generate-project-context plan/bmad-project-context
bmad-agent-tech-writer (Paige) retired upstream with no replacement yet; core/bmad-review covers editorial review