bmad-help
25Skill Claude Code
Analyzes current state and user query to answer BMad questions or recommend the next skill(s) to use. Use when user asks for help, bmad help, what to do next, or what to start with in BMad.
Token-efficient AI skill that reviews pending changes and writes senior-grade git commits. Install with npx for Claude Code, Cursor & more.
Skill Claude Code
Analyzes current state and user query to answer BMad questions or recommend the next skill(s) to use. Use when user asks for help, bmad help, what to do next, or what to start with in BMad.
Skill Claude Code
Forensic case investigation with evidence-graded findings, calibrated to the input. Use when the user asks to investigate a bug, trace what caused an incident, walk through unfamiliar code, or build a mental model of a code area before working on it.
Skill Claude Code
Conduct market research on competition and customers. Use when the user says they need market research.
Skill Claude Code
Orchestrates group discussions between installed BMAD agents, enabling natural multi-agent conversations where each agent is a real subagent with independent thinking. Use when user requests party mode, wants multiple agent perspectives, group discussion, roundtable, or multi-agent conversation about their project.
Skill Claude Code
Create, update, or validate a PRD. Use when the user wants help producing, editing, or validating a PRD.
Skill Claude Code
Working Backwards PRFAQ challenge to forge product concepts. Use when the user requests to 'create a PRFAQ', 'work backwards', or 'run the PRFAQ challenge'.
Skill Claude Code
Create, update, or validate a product brief. Use when the user wants help producing, editing, or validating a brief.
Skill Claude Code
Generate end to end automated tests for existing features. Use when the user says "create qa automated tests for [feature]".
Skill Claude Code
Implements any user intent, requirement, story, bug fix or change request by producing clean working code artifacts that follow the project's existing architecture, patterns and conventions. Use when the user wants to build, fix, tweak, refactor, add or modify any code, component or feature.
Skill Claude Code
Post-epic review to extract lessons and assess success. Use when the user says "run a retrospective" or "lets retro the epic [epic]".
Skill Claude Code
Perform a Cynical Review and produce a findings report. Use when the user requests a critical review of something.
Skill Claude Code
Walk every branching path and boundary condition in content, report only unhandled edge cases. Orthogonal to adversarial review - method-driven not attitude-driven. Use when you need exhaustive edge-case analysis of code, specs, or diffs.
Skill Claude Code
Splits large markdown documents into smaller, organized files based on level 2 (default) sections. Use if the user says perform shard document.
Skill Claude Code
Distill any intent input into the SPEC kernel + companions — the canonical, preservation-validated machine contract for downstream work. Use when the user says "create a spec", "distill this into a spec", "validate this spec", or "update the spec".
Skill Claude Code
Generate sprint status tracking from epics. Use when the user says "run sprint planning" or "generate sprint plan".
Skill Claude Code
Summarize sprint status and surface risks. Use when the user says "check sprint status" or "show sprint status".
Skill Claude Code
Conduct technical research on technologies and architecture. Use when the user says they would like to do or produce a technical research report.
Skill Claude Code
Plan UX patterns and design specifications. Use when the user says "lets create UX design" or "create UX specifications" or "help me plan the UX".
Skill Claude Code
DEPRECATED — consolidated into bmad-prd validate intent - this skill will be removed in v7 in favor of bmad-prd.
Skill Claude CodeCodex
Review pending git changes and create senior-quality commits. Groups unrelated changes into separate logical commits, writes Conventional Commits messages that explain the why, and executes them — all on a tight token budget. Use when the user says "commit", "commit my changes", "commit like a pro", "ship this", or…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: