Skill UI

Diagnose slow data pipeline jobs, expensive queries and latency regressions using Monte Carlo cross-platform observability, with a tiered approach that bridges jobs to tables and drills into root causes across Airflow, dbt, Databricks and warehouses.

Surfaces Monte Carlo data observability insights—health, lineage, alerts, and monitors-as-code—before developers edit dbt models or SQL pipelines, ensuring risk-aware code changes.

This skill analyzes data warehouses to identify stale, unused, or redundant tables that increase storage costs. It classifies waste patterns, computes safety tiers, and supports category drill-downs. Compatible with Snowflake, BigQuery, Redshift, and Databricks. Use it when users ask about storage optimization, cost reduction, or cleanup opportunities.

Generates SQL validation notebooks for dbt PR changes with before/after comparison queries. Supports GitHub PR URLs and local repositories. Creates interactive notebooks for database validation across Snowflake, BigQuery, Redshift, and Athena. Includes schema inference from dbt_project.yml and model configs.

This skill helps developers create custom external web service APIs for Moodle LMS. It covers following Moodle's API framework and coding standards, enabling integration with external applications, mobile backends, and course management systems using PHP.

This skill simulates a highly advanced 'Board of Experts,' consulting multiple specialized personas (e.g., Musk, Buffett, Jobs) simultaneously. It gathers distinct, multi-perspective analyses on any complex topic—from engineering feasibility to market strategy—and synthesizes them into a single, comprehensive, and actionable decision. Ideal for complex strategic planning, product development, and high-stakes investment decisions.

Cross-validate web research across at least two distinct search or retrieval capabilities, then produce an offline-checkable evidence ledger recording source diversity, claim-level confidence, explicit conflicts, and research gaps.

Design secure multi-tenant LLM hosting platforms on shared GPU inference infrastructure, covering tenant isolation, per-tenant quotas and rate limits, billing attribution, noisy-neighbor protection, and per-tenant policy controls for vLLM on Kubernetes.

Administer and optimize MySQL/MariaDB databases in production environments. Covers installation, configuration tuning, security hardening, backup strategies using mysqldump or XtraBackup, and source-replica replication setup. Essential for managing relational database deployments and ensuring high availability.

Handle n8n files and binary data across uploads, downloads, transforms, multimodal inputs, agent tools, and chat surfaces. Covers where binary lives, how to read/write it, preventing data loss, and the AI-agent tool boundary.

Diagnose and fix excessive Postgres egress (network data transfer) in a codebase. Use when users report high database bills, unexpected data transfer costs, egress spikes, or queries fetching more data than needed. Provides SQL diagnostics via pg_stat_statements and code-level fixes for common anti-patterns like SELECT *, missing pagination, and high-frequency static queries.

This skill combines a senior software engineering workflow with product design expertise. It ensures full planning, architecture, test-driven development, clean code, and pixel-perfect UX validation. Ideal for complex projects requiring both technical robustness and visual precision in Portuguese contexts.