AI pipeline architecture design — development pipelines, production pipelines, data stores, model registry, CI/CD for AI, and non-functional requirements. This skill should be used when the user asks to 'design AI pipelines', 'architect ML pipelines', 'select data stores for AI', 'design model registry', 'implement CI/CD for ML', 'define AI pipeline requirements', or mentions MLOps, training pipeline, inference pipeline, feature pipeline, Blue and Gold deployment, or pipeline patterns. [EXPLICIT]

This skill should be used when the user asks to operate Claude Code /goal, write a goal completion condition, compare /goal with /loop, Stop hooks, or auto mode, diagnose a stuck goal loop, set stop conditions, resume or clear an active goal, or define safe continuation gates for autonomous Claude Code sessions.

Generative AI architecture — RAG patterns, LLM orchestration, multi-model tiering, agent workflow design, vector database architecture, knowledge connectors, and GenAI quality assurance. This skill should be used when the user asks to 'design RAG architecture', 'architect LLM system', 'select vector database', 'design AI agents', 'implement knowledge retrieval', 'plan GenAI quality', or mentions RAG, embeddings, vector search, LLM orchestration, agent framework, context-aware generation, hallucination reduction, or multi-model routing. [EXPLICIT]

Functional specifications. MVP modules, 8+ use cases, business rules, acceptance criteria. Data models (relational/NoSQL). [EXPLICIT]

Build on Firebase: Auth, Cloud Functions, Firestore security rules and query optimization, Hosting, Storage, scheduled jobs, emulator suite, and cost control. [EXPLICIT] One of the three target platforms (Firebase + Vercel + Hostinger). Trigger: 'firebase', 'firestore', 'cloud functions', 'firebase auth', 'firebase hosting', 'security rules'.

Cloud financial operations assessment and strategy using FinOps Foundation framework. Use when the user asks to 'assess cloud costs', 'optimize cloud spending', 'FinOps assessment', 'cloud cost analysis', 'rightsizing', 'reservation strategy', 'showback/chargeback model', 'cloud unit economics', 'cost allocation', or mentions 'cloud financial management', 'cost optimization', 'FinOps maturity'. [EXPLICIT]

Performs 7-dimension technical feasibility assessment covering architecture, team capability, timeline, cost, risk, integration, and scalability. [EXPLICIT] Produces go/no-go recommendations with confidence levels. [EXPLICIT] Trigger: 'feasibility', 'technical assessment', 'go/no-go', 'viability'

Event-driven architecture — event catalog, schema registry, eventual consistency, saga, CQRS, event sourcing. Use when the user asks to 'design event-driven system', 'build event catalog', 'implement CQRS', 'design saga patterns', 'set up schema registry', 'implement event sourcing', or mentions Kafka, RabbitMQ, Pulsar, event bus, dead-letter queue, consumer groups, or event replay. [EXPLICIT]

This skill should be used when the user asks to 'map business capabilities', 'build a technology radar', 'define architecture governance', 'prioritize strategic initiatives', or mentions capability mapping, DDD domains, ARB, DORA metrics, or target operating model. [EXPLICIT] It generates enterprise architecture alignment artifacts including capability maps, domain decomposition, governance frameworks, technology radars, and strategic initiative roadmaps. [EXPLICIT] Use this skill whenever the user needs to align technology initiatives with business strategy, even if they don't explicitly ask for 'enterprise architecture'. [EXPLICIT]

Code review headless con claude -p output-format json validado contra schema; el humano sigue siendo gate final de merge.

This skill should be used when the user asks to create, review, save, or validate Claude Code dynamic workflows, asks to use the Workflow tool, mentions ultracode, /workflows, saved workflows, background workflow runs, resumable workflow orchestration, or needs to distinguish dynamic JavaScript workflows from workflow-forge static slash-command workflows.

Applies Domain-Driven Design tactical and strategic patterns to model complex business domains. Identifies bounded contexts, aggregates, domain events, and establishes ubiquitous language shared by developers and domain experts. [EXPLICIT] Trigger: 'bounded context', 'aggregate', 'domain event', 'ubiquitous language', 'DDD'

Memoria jerárquica durable en CLAUDE.md por nivel usuario/equipo/módulo, con frontera explícita frente a la compaction transitoria del transcript.

Doc-as-code strategy design, documentation taxonomy, content governance, and knowledge base architecture. Use when the user asks to 'design documentation strategy', 'build knowledge base', 'create doc-as-code pipeline', or mentions documentation governance, content taxonomy, or technical writing standards. [EXPLICIT]

Aislamiento multi-agente con AgentDefinition y built-in Agent; cada subagente arranca con contexto vacio y modelo propio.

Handoff a humano con payload tipado autocontenido (customer_id, issue_summary, actions_taken); end-state del bucle, no pausa.

Multi-pass review con reviewer independiente en sesion limpia; per-file y cross-file; rechazo de quorum N-de-M.

Coordinates full analysis pipeline (phases 0-6). Sequences skills 009-023. Manages G1 gate. Does NOT analyze. [EXPLICIT]

DevSecOps pipeline architecture — CI/CD design, shift-left security, supply chain integrity, release management, and compliance automation. Use when the user asks to 'design the CI/CD pipeline', 'integrate security into delivery', 'set up SBOM and artifact signing', 'automate compliance', 'measure DORA metrics', or mentions SAST, SCA, DAST, secrets scanning, IaC scanning, canary deployment, or policy-as-code. [EXPLICIT]

Configuracion de MCP servers: project vs user scope, env-var expansion para credenciales y rotacion ante secreto leakeado.