core-service

Run comprehensive CI checks before committing changes. Use when the user asks to run CI, run quality checks, validate code quality, or before finishing any task that involves code changes.

Ensure proper code organization with class names, directories, namespaces, and naming consistency following the principle "Directory X contains ONLY class type X".

Design and implement DDD patterns (entities, value objects, aggregates, CQRS). Use when creating new domain objects, implementing bounded contexts, designing repository interfaces, or learning proper layer separation. For fixing existing Deptrac violations, use the deptrac-fixer skill instead.

Implement production-grade caching with cache keys/TTLs/consistency classes per query, SWR (stale-while-revalidate), layered explicit invalidation, and comprehensive testing for stale reads and cache warmup. Use when adding caching to queries, implementing cache invalidation, or ensuring cache consistency and performance.

Systematically retrieve and address PR code review comments using make pr-comments. Enforces DDD architecture, code organization principles, and quality standards. Use when handling code review feedback, refactoring based on reviewer suggestions, or addressing PR comments.

Guide for contributing to the OpenAPI layer using processor pattern, complexity management, and functional programming. Use when adding endpoint factories, processors, parameter descriptions, reducing cyclomatic complexity, or fixing OpenAPI validation errors. Covers architecture patterns from user-service repository.

Portable autonomous BMALPH planning for Codex. Use when the user wants specs from a short task description and expects the current AI session to orchestrate BMALPH subagents without human interaction.

BMAD master agent — navigate phases. Use when the user asks about bmalph.

Create BMALPH planning artifacts autonomously from a short task description by delegating each planning phase to a focused subagent and orchestrating the handoffs without human interaction.

advanced elicitation. Use when the user asks about advanced elicitation.

adversarial review. Use when the user asks about adversarial review.

Research, briefs, discovery. Use when the user asks about analyst.

Technical design, architecture. Use when the user asks about architect.

bmad help. Use when the user asks about bmad help.

brainstorm-project. Use when the user asks about brainstorm project.

brainstorming. Use when the user asks about brainstorming.

Anytime: Navigate significant changes. May recommend start over update PRD redo architecture sprint planning or correct epics and stories. Use when the user asks about correct course.

Guided Workflow to document technical decisions. Use when the user asks about create architecture.

A guided experience to nail down your product idea. Use when the user asks about create brief.

Create the Epics and Stories Listing. Use when the user asks about create epics stories.

Expert led facilitation to produce your Product Requirements Document. Use when the user asks about create prd.

Trigger the story cycle for the next story in the sprint plan or a specified epic/story. Use when the user asks about create story.

Guidance through realizing the plan for your UX, strongly recommended if a UI is a primary piece of the proposed project. Use when the user asks about create ux.

Implementation, coding. Use when the user asks about dev.

distillator. Use when the user asks about distillator.

Analyze an existing project to produce useful documentation. Use when the user asks about document project.

Industry domain deep dive subject matter expertise and terminology. Use when the user asks about domain research.

Identify edge cases, failure paths, and boundary-condition risks. Use when the user asks for edge-case analysis.

Improve and enhance an existing PRD. Use when the user asks about edit prd.

editorial prose. Use when the user asks about editorial prose.

editorial structure. Use when the user asks about editorial structure.

Scan the existing codebase to generate a lean, LLM-optimized `project-context.md` with critical implementation rules, patterns, and conventions for AI agents. Use this for brownfield projects and when the user asks about generate project context.

Ensure PRD UX Architecture and Epics Stories are aligned. Use when the user asks about implementation readiness.

Index and organize documentation files for search and retrieval. Use when the user asks about index docs.

Market analysis competitive landscape customer needs and trends. Use when the user asks about market research.

party mode. Use when the user asks about party mode.

PRDs, epics, stories. Use when the user asks about pm.

Generate automated API and E2E tests for implemented code using the project's existing test framework (detects commonly used test frameworks). Use after implementation to add test coverage. Not for code review or story validation; use CR for that. Use when the user asks about qa automate.

Test automation, quality assurance. Use when the user asks about qa.

Unified quick flow (experimental): clarify intent plan implement review and present in a single workflow. Use when the user asks about quick dev new.