ai-dev-kit-pgi

Use when creating, updating, or compacting Architecture Decision Records (ADRs). Use when user says "adr", "crear ADR", "create ADR", "actualizar ADR", "update ADR", "compactar ADR", "compact ADR", "registrar decision", "record decision", "decision record".

Use when needing to query a PostgreSQL database in DEV or PROD, check if records exist, count rows, inspect data, or run read-only SQL queries from within the cluster. Use when user says "consulta la BD", "query", "busca en la tabla", "check database", "db query", or "existe este registro".

Use when user asks to deploy to production, check what's deployed, find a docker image tag for a PR, or trigger a production deployment. Use when user mentions "deploy", "prod", "production", "release", or "ship".

Use when checking pod logs, searching for errors, viewing recent log output, or debugging runtime issues in DEV or PROD. Use when user says "logs de", "ver logs", "qué errores hay", "check logs", "show errors", or mentions log analysis of a service.

Use when user asks to run database migrations, create tables, apply schema changes, or mentions "migration" in the context of DEV or PROD environments. Use when user mentions "migrate", "migration:up", "create table", or "schema changes" for remote environments.

Use when checking pod status, listing running services, investigating crashloops, viewing pod events, or checking resource usage. Use when user says "pods", "qué está corriendo", "pod status", "check pods", "restart", "crashloop", or "pod events".

Use when doing comprehensive ticket analysis before implementation. Analyzes Jira ticket, Figma designs, Confluence/Notion docs, and codebase to produce a data map where every field is questioned and scope is explicitly defined. Use when user says "analiza ticket", "ticket analysis", "prepara ticket", "revisar ticket completo", or "qué falta en este ticket".

Use when interrogating the codebase to understand an entity, field, or business concept. Traces data origin, mutations, validations, and relationships without assumptions. Use when user says "analiza entidad", "de dónde viene este dato", "analyze data model", "qué campos tiene", "quién genera este campo", or "explica esta entidad".

Use when evaluating a sprint before starting it. Detects duplicates, poorly defined tickets, missing acceptance criteria, estimation gaps, vague language, dependency risks, and balance issues. Use when user says "revisa sprint", "sprint review", "analiza sprint", "sprint health", "evalúa sprint", or provides a list of ticket keys for pre-sprint review.

Use when sending any communication to the team — incidents, announcements, questions, status updates, or review requests. Use when user says "notifica al equipo", "avisa al equipo", "crea un mensaje", "anuncia", "pregunta al equipo", "draft a message", or wants to communicate anything to the team via Slack.

Use when analyzing Figma designs to extract data fields, UI states, and actions without assumptions. Uses Figma MCP with Playwright fallback. Use when user says "analiza diseño", "revisa el figma", "qué campos tiene el diseño", "analyze design", or shares a Figma URL for review.

Use when searching for documentation about a concept, entity, or business term in Confluence and Notion. Extracts definitions and rules without interpretation. Use when user says "busca documentación", "qué dice confluence", "analyze docs", "busca en notion", "hay documentación sobre", or "qué sabemos de".

Use when creating new skills, editing existing skills, or reviewing skill quality. Use when user mentions building, writing, or improving a SKILL.md file or skill folder. Guides skill authoring following Anthropic's official best practices.

Use when needing to port-forward to any Kubernetes service (RabbitMQ, PostgreSQL, internal APIs). Use when user says "port-forward", "portforward", "connect to", "forward port", or needs local access to a cluster service in DEV or PROD.

Use when analyzing a Jira ticket for ambiguities, missing information, or unclear acceptance criteria. Use when user says "clarify ticket", "review ticket", "analyze ticket", or passes a Jira ticket key like DEVPT-XX. Reads the ticket from Jira, detects vague content, and generates concrete questions.

Use when creating a bug report in Jira, reporting an issue found during development or operations, or filing a ticket for a production problem. Use when user says "crea un bug", "reporta bug", "create bug", "file a bug", "abre un ticket", or "report issue".

Use when checking RabbitMQ queue status, listing queues with messages, checking DLQ counts, or monitoring consumer health. Use when user says "list queues", "lista colas", "queue status", "cuántos mensajes", "check queues", or "DLQ status".

Use when needing to reprocess messages from a RabbitMQ Dead Letter Queue (DLQ), move messages between queues using shovel, republish with clean headers, or purge unprocessable messages. Use when user mentions "reprocess", "reprocesar", "shovel", "purge DLQ", or "move messages from DLQ".

Use when investigating why messages are failing in a RabbitMQ Dead Letter Queue (DLQ), diagnosing root causes of message rejections, or analyzing DLQ message patterns. Use when user says "triage DLQ", "why are messages failing", "analyze DLQ", "diagnose DLQ", "analiza esta cola", or wants to understand message failures before deciding whether to reprocess or purge.