Los agentes ADK en producción necesitan señales de trazas, registros y analítica sin exponer datos de prompts. Esta skill guía Cloud Trace, el registro de prompts, BigQuery Analytics y las opciones de proveedor.

Los equipos de agentes necesitan evidencia repetible antes de cambiar prompts, herramientas o ajustes de despliegue. Esta skill guía el diseño de datasets, la selección de métricas, la calificación, la comparación y el análisis de fallos para agentes de Google ADK.

Desplegar agentes ADK en distintos destinos de Google Cloud requiere muchas decisiones de infraestructura. Esta habilidad guía la selección del destino, los comandos de despliegue, los secretos, CI/CD, las pruebas y la recuperación.

Los desarrolladores necesitan patrones ADK fiables al crear agentes en Python. Esta skill proporciona referencias concisas para herramientas, callbacks, estado, orquestación multiagente y código de flujos de trabajo.

Tarot requests can become inconsistent or overconfident without a structured source. This skill uses a bundled 78-card dataset and defined spreads for reflective interpretations.

Los cambios en contratos y esquemas pueden afectar a servicios dependientes, clientes y flujos de datos. Esta skill identifica las referencias afectadas y genera un informe de impacto empresarial antes de hacer commit.

Buying by token name can select a copycat or create unsafe order parameters. This skill resolves the contract, screens risks, and prepares a confirmed order card.

Token research requires combining market, holder, trader, and contract data. This skill queries GMGN and presents structured due diligence across supported chains.

Manual token trading across wallets and chains requires careful parameter handling. This skill prepares GMGN CLI operations with validation, quotes, and confirmation checkpoints.

Raw candle data makes token trends difficult to assess consistently. This skill calculates six measurements, classifies the pattern, and explains a reproducible 0-100 score.

Release decisions often rely on incomplete evidence and inconsistent standards. This skill applies structured controls, deterministic scoring, and mandatory gates to assess readiness.

Long technical tasks lose decisions, evidence, and next actions across sessions. This skill maintains a concise Markdown state file with reviewed local evidence references.

Python teams need repeatable checks for common application security controls. This skill provides configurable pytest coverage with clear evidence, boundaries, and release decisions.

Spam review can expose private mail or remove legitimate messages. This skill audits Gmail headers locally and applies only owner-confirmed quarantine or Trash actions.

Automated drafts can sound repetitive or overly polished and may lose the writer's original voice. This skill applies minimal editorial fixes while preserving meaning.

Los shells POSIX de Windows pueden distorsionar la salida en chino de Python, PowerShell y cmd.exe. Esta skill proporciona correcciones específicas de UTF-8 y GBK para Claude, Codex y agentes relacionados.

Weak tests can hide production bugs while inflating coverage metrics. This skill reviews test quality and identifies misleading, redundant, or excessively mocked tests.

Ambiguous specifications create implementation gaps, security risks, and costly rework. This skill reviews plans through architecture, security, quality, user, and governance perspectives before engineers begin implementation.

Complex features fail when requirements, architecture effects, and verification criteria remain unclear. This skill guides agents through research and produces an implementation-ready Gjalla specification.

Code changes can hide correctness, security, and maintainability issues before merge. This skill reviews diffs from relevant perspectives and returns prioritized, location-specific fixes.