BMad Method is a set of skills for agile, AI-driven software delivery. It covers the path from a vague idea through briefs, PRDs, UX, architecture and tickets to built, reviewed code. It is for developers and small teams who use AI coding tools and want the important decisions made explicit and carried forward, not left buried in chat.
Why read it
Long conversational skills log every decision, assumption and override as one line through a shared script. They never hand-edit the log, and they build the final document from the log at the end. Because the state lives on disk, a session survives interruption and can be resumed. It also gives an audit trail that the Finalize step walks with the user.
Several SKILL.md files hold only one command. That command prints the actual workflow, and the skill handles three outcomes explicitly: follow the printed workflow, stop on HALT, or report any other failure. Flags from the invocation become `--set` overrides. The skill also forbids running the workflow source directly, so the rendered, customized version is always the one that runs.
Source documents go to subagents, which return filtered digests, so the parent's context stays small. The ticket file is the one named exception and is always read in full. Reviewers write their full output to files and return only a short summary, which the parent reads in detail only when the user asks.
Authoring skills ask the user to pick a working mode. On the Fast path the skill drafts quickly and tags its inferences with `[ASSUMPTION]`. On the Coaching path it draws the decisions out of the user. The tags become open items that get triaged at Finalize, so speed doesn't quietly turn into invented content.
The architecture skill gives the model a three-part test for deciding what goes in the document. Anything that fails the test goes under Deferred. A bounded rule like this keeps the output short and gives the model a concrete way to decide.
Party mode sets a quality bar for the session as a list of concrete behaviors. Voices should clash without being resolved, the user gets pulled into the room, and the skill never slips in a summary. It also gives a recovery rule for when the conversation goes flat.
The forge-idea skill lists three valid endings: Hardened, Killed or Clarified. Each has its own artifact. Because rejecting the idea counts as a success, the model isn't pushed toward always saying "let's build it".
Skills say what to do when no human is present: don't ask, infer what's needed, log each judgment call, stop with `blocked` only when they can't infer, and end with a defined JSON block. Counts in that block come from a script, not from the model's own tally. Orchestrators can then chain these skills safely.
A model read each skill to find these. Top to bottom is the usual order. Select a box to read the skill, or a line to see the text behind it.
Links to many skills, so not drawn: bmad-agent-po (9), bmad-architecture (7), bmad-forge-idea (7), bmad-prd (7), bmad-prfaq (7), bmad-ux (6), bmod-method (6)
Many skills link to it, so not drawn: bmad (29), bmad-agent-po (8), bmad-build (8), bmad-prd (6)
bmad-agent-analyst, bmad-agent-architect, bmad-agent-dev, bmad-agent-pm, bmad-agent-ux-designer, bmad-build-auto, bmad-project-context, bmad-qa-generate-e2e-tests, bmod-core-tools
Every one is a skill. Started by: You or the agent.
| SKILL | DESCRIPTION | LINKS |
|---|---|---|
| bmad | Answers BMad questions and recommends the next skill from what is installed. Use when the user asks bmad for help, what to do next or where to start; to set up, update, repair, doctor, migrate or check the status of the installation, or add modules; or to see or change the active initiative. | 1 |
| bmad-advanced-elicitation | 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 | 2 |
| bmad-agent-analyst | Business analyst for market research, competitive analysis, and requirements. Use when the user asks to talk to Mary or requests the business analyst | 1 |
| bmad-agent-architect | System architect and technical design leader. Use when the user asks to talk to Winston or requests the architect | 1 |
| bmad-agent-dev | Senior software engineer who implements stories and code changes. Use when the user asks to talk to Amelia or requests the developer agent | 1 |
| bmad-agent-pm | Product manager for PRD creation and requirements discovery. Use when the user asks to talk to John or requests the product manager | 1 |
| bmad-agent-po | Sofia, the Product Owner: turns any input (an idea, brief, PRD, transcript, notes) into a ticket''s requirements, slices initiatives into epics and epics into stories, writes and refines tickets, runs the board, validates the tree, replans when a change lands, and sets up the ticket store. Use when the user asks for Sofia or the product owner, or says ''create a spec'', ''distill this PRD'', ''write the initiative from'', ''slice this'', ''split this epic'', ''break this into stories'', ''make a ticket'', ''refine this ticket'', ''what''s ready'', ''status of'', ''publish'', ''validate these tickets'', ''this changed, what now'', ''set up the ticket store''. | 12 |
| bmad-agent-ux-designer | UX designer and UI specialist. Use when the user asks to talk to Sally or requests the UX designer | 1 |
| bmad-architecture | Work out and record the architecture decisions that keep separately built parts of a system consistent, in a short architecture document. Creates, updates, or validates one; works from a ticket file, with an existing codebase or architecture document beside it. Use when the user says "create the architecture", "create technical architecture", "architecture spine", or "create a solution design" | 7 |
| bmad-brainstorming | Facilitate a brainstorming session using diverse creative techniques. Use when the user says 'help me brainstorm' or 'help me ideate' | 7 |
| bmad-build | Implements a story, feature, or bug fix end to end: plan, code, review, verify. Use when the user hands one over and leaves the edits to you; a bare ticket id or link counts. Skip obvious, low-risk mechanical maintenance such as small ignore-file, typo-only, formatting-only, or configuration-hygiene edits. Explicit BMAD requests always qualify. Do not volunteer for user-directed interactive edits or version-control operations that only record existing work. | 4 |
| bmad-build-auto | Implements one story, feature, or bug fix end to end without human interaction: plan, code, review, verify, report status. Use when invoked by name, usually by an orchestrator | 1 |
| bmad-code-review | Review code changes with several independent reviewers in parallel, then triage and present the findings. Use when the user says "run code review" or "review this code" | 2 |
| bmad-customize | Authors and updates customization overrides for installed BMad skills. Use when the user says 'customize bmad', 'override a skill', 'change agent behavior', or 'customize a workflow' | 4 |
| bmad-deep-recon | Decision-grade research on a topic or this repository. Use when the user says "deep recon", "research this", "draft a research prompt", "process this research report", "market research", "domain research", "technical research", "competitor research", "what users say about X", "literature review", "help me choose between", "research the codebase", "research how X works here" or "why is X built this way". Not for a quick code question answered in chat. | 6 |
| bmad-eval | Runs the evals of a BMad skill through the agent harness the user works in and reports what they show: baseline against the bare model, variant against a stripped or prior version, quality against a rubric, and trigger accuracy of the description with an optional optimization loop. Use when the user asks to evaluate, benchmark, test the triggers of, grade, or compare versions of a skill, or when the bmad-toolsmith skill asks for an eval of a skill it built. | 2 |
| bmad-forge-idea | 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' | 8 |
| bmad-party-mode | Orchestrates lively group discussions between installed BMAD agents or custom personas, and helps author custom parties. Use when the user requests party mode, a roundtable, or multiple agent perspectives — or wants to create/configure a party, define personas, or build an AI focus-group panel | 3 |
| bmad-prd | Create, update, or validate a PRD. Use when the user wants help producing, editing, or validating a PRD | 9 |
| bmad-prfaq | Test a product concept with Amazon's Working Backwards method: write the press release for the finished product first, then answer hard customer and stakeholder questions, ending in a complete PRFAQ document. Use when the user requests to 'create a PRFAQ', 'work backwards', or 'run the PRFAQ challenge' | 7 |
| bmad-product-brief | Create, update, or validate a product brief. Use when the user wants help producing, editing, or validating a brief | 6 |
| bmad-project-context | Set up, adopt, refresh, or audit a repository''s agent instructions (the AGENTS.md block) so AI agents work well in that repo. Also records observed agent mistakes as pitfalls. Use when invoked by name | 2 |
| bmad-qa-generate-e2e-tests | Add end-to-end and API tests for features that already work, following the project''s existing test harness. Use when the user asks for e2e tests, API tests, or automated coverage of an existing feature, or says "create qa automated tests for [feature]". Not for unit tests on work in flight, which the build writes. | 2 |
| bmad-retrospective | Review a finished epic folder in the ticket tree against the evidence it left behind — the epic file, each ticket''s story file and plan, diffs, commits — and produce a retrospective with sourced findings, action items, and an acceptance decision. Use when the user says "run a retrospective" or "lets retro the epic [epic]". Supports -H/--headless | 5 |
| bmad-review | Runs one or more installed review lenses — adversarial critique, edge cases, verification gaps, structure, prose — and reports triaged findings. Use when, and only when, the user asks you to review a diff, a pull request, or an artifact — code or documents, one or many — and actually says "review"; an explicit skill:bmad-review directive from another skill counts as that ask. A request to act on feedback from an earlier review is a change, not a review. Never invoke this uninvited, including on edits you just made. | 1 |
| bmad-toolsmith | Smithy the Toolsmith builds and maintains BMad skills, agents and modules. Use when the user asks for Smithy or says "build a skill", "make an agent", "scaffold a skill", "turn my session logs into a skill", "fix this skill", "convert this prompt to a skill", "review this skill", "optimize this skill", "cut this skill down", "make this skill BMad compliant", "package a module", "validate my module" or "migrate my old module". Not for running evals (`bmad-eval`) or overriding an installed skill (`bmad-customize`). | 5 |
| bmad-ux | Capture the user''s UX vision in two documents: DESIGN.md for how the product looks and EXPERIENCE.md for how it behaves. Use when the user says "lets create UX design" or "create UX specifications" or "help me plan the UX" | 8 |
| bmad-walkthrough | Guide a human review of a commit, PR, file, or directory. Use when invoked by name | 3 |
| bmod-core-tools | Required bmod metadata. Never invoke this skill. | 11 |
| bmod-method | Required bmod metadata. Never invoke this skill. | 25 |
| bmod-toolsmith | Required bmod metadata. Never invoke this skill. | 9 |
From bmad-code-org/BMAD-METHOD at bd70c64, 2026-10-31. Skills read by DeepSeek V4.1 Flash on 2026-11-04. Summary and techniques by Claude Opus 5.5 on 2026-11-06.