artifact-verification
Three-level artifact verification - EXISTS, SUBSTANTIVE, WIRED
Discover documentation architecture patterns skills, compare source repositories and read the instructions for each workflow.
Three-level artifact verification - EXISTS, SUBSTANTIVE, WIRED
Orchestrate multi-agent development workflows. Use when starting a new feature to coordinate architecture design, implementation, code review, and release through specialized sub-agents.
MCP (Model Context Protocol) server building principles. Tool design, resource patterns, best practices.
Thin adapters pattern - connectors contain zero business logic. Use when adding platform integrations or refactoring boundaries.
Ensures that system changes don't break existing API consumers or persistent data structures. Use during feature modifications.
Design resource-oriented APIs following patterns from "API Design Patterns" by JJ Geewax (Google)
Persist context across sessions using external memory files
avoids expensive operations when lengths differ
Proactive maintenance to reduce complexity and remove dead code.
Testing strategies based on Clean Architecture layers. Trigger: Invoke when writing tests to enforce layer-specific mocking strategies (Unit vs Integration)
Universal coding standards, best practices, and patterns for Python development.
TypeScript strict patterns and best practices. Trigger: When writing TypeScript code - types, interfaces, generics.
Canonical deterministic concurrency patterns in X07 (defasync + task.* + chan.bytes.*), including the determinism constraints.
Autonomous recursive loop of Planning, Implementation, Review, and Verification. Use for end-to-end task execution with minimal user intervention.
Design WebSocket/SSE/long polling with ordering and delivery guarantees.
Containerization, orchestration, and deployment with Docker and K8s
Domain-Driven Design (DDD) patterns for Angular applications with clean architecture layers. Use when designing aggregates, entities, value objects, domain events, repositories, or implementing bounded contexts...
Multi-level caching, Invalidation patterns, and Stampede protection.
Tracks, classifies, and prioritizes technical debt (code, spec, and process) over time. Use to prevent silent rot.
Transactional Outbox + idempotency guardrails for practical exactly-once behavior. Use when you see double-publish, inconsistent state, or need reliable integration events.
RabbitMQ queue patterns with acknowledgements, retries, dead-lettering, and ordering constraints. Use when building job queues, async workers, or diagnosing requeue/poison issues.
Standardize API communication, error handling, and authentication. Use when building new API services or debugging network issues.
Provides architectural guidance and design patterns for implementing new features in the Nick Stack codebase. Use when planning implementations, designing new features, or making architectural decisions.
Compile-time dependency injection from Google.
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.