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, walkthrough, QA tests, retrospective), and core helpers (brainstorming, research, review, party mode). Use when the user mentions BMad or BMM, names a BMad agent such as Mary, John, Sally, Winston, or Amelia, or wants a structured flow from idea through PRD and architecture to built, reviewed code.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
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.
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.
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.
core/bmad-help/SKILL.md; it reads the
project state and recommends the next skill.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.
| 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 |
| 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 |
| 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 |
| 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 |
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.
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 |
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Use when long-lived agents, project memories, system prompts, or playbooks are repeatedly summarized, rewritten, or optimized and risk losing domain detail, provenance, or execution learnings.
The English summary is being prepared. Showing the original description.
Use this skill when the user explicitly asks to map, document, or onboard into an existing codebase. Trigger for prompts like "map this codebase", "document this architecture", "onboard me to this repo", or "create codebase docs". Do not trigger for routine feature implementation, bug fixes, or narrow code edits unless the user asks for repository-level discovery.
The English summary is being prepared. Showing the original description.
Adds educational comments to a code file so it becomes a learning resource, asking for the file (with a list of close matches) if none is given. Use when preparing code for learners, onboarding, or teaching.
The English summary is being prepared. Showing the original description.
Write, debug, and optimize Adobe Illustrator automation scripts using ExtendScript (JavaScript/JSX). Use when creating or modifying scripts that manipulate documents, layers, paths, text frames, colors, symbols, artboards, or any Illustrator DOM objects. Covers the complete JavaScript object model, coordinate system, measurement units, export workflows, and scripting best practices.
The English summary is being prepared. Showing the original description.
Patterns and techniques for adding governance, safety, and trust controls to AI agent systems. Use this skill when: - Building AI agents that call external tools (APIs, databases, file systems) - Implementing policy-based access controls for agent tool usage - Adding semantic intent classification to detect dangerous prompts - Creating trust scoring systems for multi-agent workflows - Building audit trails for agent actions and decisions - Enforcing rate limits, content filters, or tool restrictions on agents - Working with any agent framework (PydanticAI, CrewAI, OpenAI Agents, LangChain, AutoGen)
The English summary is being prepared. Showing the original description.
Check any AI agent codebase against the OWASP Agentic Security Initiative (ASI) Top 10 risks. Use this skill when: - Evaluating an agent system's security posture before production deployment - Running a compliance check against OWASP ASI 2026 standards - Mapping existing security controls to the 10 agentic risks - Generating a compliance report for security review or audit - Comparing agent framework security features against the standard - Any request like "is my agent OWASP compliant?", "check ASI compliance", or "agentic security audit"
The English summary is being prepared. Showing the original description.