How do I install the Bmad skill?

Run npx skillmds add majiayu000/bmad in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

This skill has not completed SkillMD's automated safety review yet. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Bmad?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

majiayu000 (@majiayu000) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Bmad by majiayu000 — Agent Skill

Name: Bmad
Rating: 4.2 (5 reviews)
Author: majiayu000

File contents

BMad Method (BMAD) v6

Source: https://github.com/bmad-code-org/BMAD-METHOD

When to use

Use BMAD for structured, end-to-end delivery when the request is broad enough to need planning artifacts and a workflow.

Typical triggers:

Track selection (Quick vs Method vs Enterprise).
Planning artifacts (tech spec, PRD, UX, architecture).
Turning requirements into epics/stories and sprint execution.
“What should we do next?” workflow guidance.

Core concepts

Workflows, not ad-hoc prompts

BMAD v6 is organized around workflows run by specialized agents. Common entry points:

workflow-init to analyze the project and choose a track.
workflow-status when unsure what’s next.

Tracks (planning depth)

Quick Flow: fast path; typically a tech spec; small changes/features.
BMad Method: fuller planning; PRD + optional UX + architecture.
Enterprise Method: extended planning; higher governance/compliance/testing needs.

Lifecycle

Analysis (optional): brainstorm/research/brief.
Planning (required): PRD (Method/Enterprise) or tech spec (Quick).
Solutioning (track-dependent): architecture, then epics/stories.
Implementation (required): sprint plan → story → implement → review → repeat.

Context rule

Prefer fresh chats per workflow to reduce context bleed.

Lightweight playbook (in chat)

Establish context (greenfield/brownfield, outcomes/users, constraints).
Recommend a track and why.
Outline the minimum artifacts for that track.
Drive the next workflow step explicitly (workflow-init or workflow-status).

Activation cues

"BMAD" / "BMad Method" / "BMAD v6"
"workflow-init" / "workflow-status" / "track selection"
"PRD" / "tech spec" / "UX" / "architecture"
"epics and stories" / "sprint planning" / "dev-story"
"greenfield" / "brownfield"

Non-goal

If the user only wants a narrow A-vs-B technology comparison (TCO/lock-in/etc.) without delivery workflow, use a dedicated decision framework instead.

---name: bmaddescription: BMad Method v6: workflow-driven agile delivery (track selection, PRD/spec, UX, architecture, epics/stories).--- # BMad Method (BMAD) v6 Source: https://github.com/bmad-code-org/BMAD-METHOD ## When to use Use BMAD for structured, end-to-end delivery when the request is broad enough to need planning artifacts and a workflow. Typical triggers: - Track selection (Quick vs Method vs Enterprise). - Planning artifacts (tech spec, PRD, UX, architecture). - Turning requirements into epics/stories and sprint execution. - “What should we do next?” workflow guidance. ## Core concepts ### Workflows, not ad-hoc prompts BMAD v6 is organized around workflows run by specialized agents. Common entry points: - `workflow-init` to analyze the project and choose a track. - `workflow-status` when unsure what’s next. ### Tracks (planning depth) - Quick Flow: fast path; typically a tech spec; small changes/features. - BMad Method: fuller planning; PRD + optional UX + architecture. - Enterprise Method: extended planning; higher governance/compliance/testing needs. ### Lifecycle - Analysis (optional): brainstorm/research/brief. - Planning (required): PRD (Method/Enterprise) or tech spec (Quick). - Solutioning (track-dependent): architecture, then epics/stories. - Implementation (required): sprint plan → story → implement → review → repeat. ### Context rule Prefer fresh chats per workflow to reduce context bleed. ## Lightweight playbook (in chat) 1. Establish context (greenfield/brownfield, outcomes/users, constraints). 2. Recommend a track and why. 3. Outline the minimum artifacts for that track. 4. Drive the next workflow step explicitly (`workflow-init` or `workflow-status`). ## Activation cues - "BMAD" / "BMad Method" / "BMAD v6" - "workflow-init" / "workflow-status" / "track selection" - "PRD" / "tech spec" / "UX" / "architecture" - "epics and stories" / "sprint planning" / "dev-story" - "greenfield" / "brownfield" ## Non-goal If the user only wants a narrow A-vs-B technology comparison (TCO/lock-in/etc.) without delivery workflow, use a dedicated decision framework instead.

Frequently asked questions