В каталоге 183 730 навыков в 14 категориях.
qa agent
Test automation, quality assurance. Use when the user asks about qa.
Generate automated API and E2E tests for implemented code using the project's existing test framework (detects existing...
Generate automated API and end-to-end tests for implemented features. Use when the user says "create qa automated tests...
Generate end to end automated tests for existing features. Use when the user says "create qa automated tests for [featur...
Implement a Quick Tech Spec for small changes or features. Use when the user provides a quick tech spec and says "implem...
Deprecated: forwards to bmad-build. Do not use unless invoked by name.
Implements any user intent, requirement, story, bug fix or change request by producing clean working code artifacts that...
Quick one-off tasks small changes simple apps utilities without extensive planning - Do not suggest for potentially very...
Unified quick flow (experimental): clarify intent plan implement review and present in a single workflow. Use when the u...
quick-flow-solo-dev agent
Very quick process to create implementation-ready quick specs for small changes or features. Use when the user says "cre...
Post-epic review to extract lessons and assess success. Use when the user says "run a retrospective" or "lets retro the...
Review a finished epic folder in the ticket tree against the evidence it left behind — the epic file, each ticket plan,...
Evidence-based epic retrospective — collect what the epic produced, verify findings against sources, render an acceptanc...
Review a completed epic against the evidence it left behind — spec, stories, diffs, commits, sprint status — and produce...
Optional at epic end: Review completed work lessons learned and next epic or if major issues consider CC. Use when the u...
Maintainer-only. Use when re-vendoring skills/BMAD/ against a newer BMAD-METHOD commit — "update BMAD", "re-vendor BMAD"...
Runs one or more installed review lenses — adversarial critique, edge cases, verification gaps, structure, prose — and r...
Multi-lens review over any diff, doc, spec, or artifact — whichever installed lenses fit the content, run singly or toge...
Perform a Cynical Review and produce a findings report. Use when the user requests a critical review of something
Execute review-adversarial-general
Walk every branching path and boundary condition in content, report only unhandled edge cases. Orthogonal to adversarial...
Execute review-edge-case-hunter
Inspect and explain bmad-loop run artifacts under `.bmad-loop/runs/`. Use for live health checks ("is it stuck?", "is th...
Splits large markdown documents into smaller, organized files based on level 2 (default) sections. Use if the user says...
Execute shard-doc
sm agent
Sprint planning, status, coordination. Use when the user asks about sm.
Condense any input — an idea, brief, PRD, transcript, or mixed notes — into a short spec: one kernel file plus supportin...
Distill any intent input into the SPEC kernel + companions — the canonical, preservation-validated machine contract for...
Condense any input — an idea, brief, PRD, transcript, or mixed notes — into a short spec: SPEC.md plus supporting files...
Autonomous story execution with Codex validation. Runs create/implement/review cycles per story in a bash loop until don...
Generate sprint status tracking from epics. Use when the user says "run sprint planning" or "generate sprint plan"
Gate planning readiness, generate sprint status tracking from epics, summarize sprint progress, and validate or repair t...
Check that planning is complete enough to implement, then generate the sprint status file from the epics. Can also summa...
Summarize sprint status and surface risks. Use when the user says "check sprint status" or "show sprint status"
Deprecated — forwards to bmad-sprint-planning (status view).
Anytime: Summarize sprint status and route to next workflow. Use when the user asks about sprint status.
Master Test Architect and Quality Advisor. Use when the user asks to talk to Murat or requests the Test Architect.
bmad-tea-teach-me-testing skill
Teach testing progressively through structured sessions. Use when user says "lets learn testing" or "I want to study tes...
bmad-tea-testarch-atdd skill
Generate failing acceptance tests using TDD cycle. Use when the user says "lets write acceptance tests" or "I want to do...
bmad-tea-testarch-ci skill
Scaffold CI/CD quality pipeline with test execution. Use when the user says "lets setup CI pipeline" or "I want to creat...
bmad-tea-testarch-nfr skill
Assess NFRs like performance security and reliability. Use when the user says "lets assess NFRs" or "I want to evaluate...
Senku × Gear 5. The ultimate Gen AI, Architecture, and BMAD mentor. Acts as a Socratic teacher to deeply educate the use...
Do not suggest for potentially very complex things unless requested or if the user complains that they do not want to fo...
tech-writer agent
Documentation, technical writing. Use when the user asks about tech writer.
Conduct technical research on technologies and architecture. Use when the user says "create a technical research report...
Conduct technical research on technologies and architecture. Use when the user says they would like to do or produce a t...
Generate red-phase acceptance test scaffolds using the TDD cycle. Use when the user says "lets write acceptance tests" o...
Expand test automation coverage for codebase. Use when user says "lets expand test coverage" or "I want to automate test...
Run scored behavioral evaluations and repair gaps. Use when the user says "evaluate this agent" or "I want proof this be...
Initialize test framework with Playwright or Cypress. Use when the user says "lets setup test framework" or "I want to i...
Audit NFR evidence for performance, security, reliability, and scalability. Use when implementation evidence exists and...
Audit NFR evidence for performance, security, reliability, and maintainability. Use when implementation evidence exists...
Create system-level or epic-level test plans. Use when the user says "lets design test plan" or "I want to create test s...
Review test quality using best practices validation. Use when user says "lets review tests" or "I want to evaluate test...
Generate traceability matrix and quality gate decision. Use when the user says "lets create traceability matrix" or "I w...
Create and manage tickets — initiatives, epics, stories, bugs. Use when the user says "create a new initiative", "slice...
Smithy the Toolsmith builds, converts, reviews, packages, validates and migrates BMad skills, agents and modules. Use wh...
Capture the user's UX vision in two documents: DESIGN.md for how the product looks and EXPERIENCE.md for how it behaves....
Plan UX patterns and design specifications. Use when the user says "lets create UX design" or "create UX specifications"...
ux-designer agent
User experience, wireframes. Use when the user asks about ux designer.
Validate a PRD against standards. Use when the user says "validate this PRD" or "run PRD validation"
Deprecated — forwards to bmad-prd (validate intent).
DEPRECATED — consolidated into bmad-prd validate intent - this skill will be removed in v7 in favor of `bmad-prd`.
Validate PRD is comprehensive lean well organized and cohesive. Use when the user asks about validate prd.
Story cycle start: Prepare first found story in the sprint plan that is next, or if the command is run with a specific e...
Guidance through realizing the plan for your UX, strongly recommended if a UI is a primary piece of the proposed project...