Dados e Análise

Use when user invokes /explain with a file path, directory path, function/class name, or natural language concept. Also triggers on "explain this", "how does X work", "walk me through". Produces a structured, layered explanation of what the code does, how it connects, and where to start if you need to change it. Do NOT use when the user wants to trace data flow through a pipeline — use /lineage in

Use ao realizar a exportação mensal de datasets do HuggingFace para o Ceres Open Data Index. Abrange o fluxo de trabalho completo: verificações de qualidade de dados, exportação em parquet, atualização do cartão de dataset README, versionamento e push para o HuggingFace.

Ceres é um kit de ferramentas Rust 'harvest-first' para portais de dados abertos, cobrindo coleta, sincronização, incorporação e busca opcionais, suporte a CKAN e DCAT, Ollama ou provedores hospedados, CLI, API REST, configuração de portal, arquitetura, extensão via traits e contribuição para o código-base.

Handle ethical requirements, IRB approval, trial registration, and pre-analysis plans for RCTs. Use when user mentions: research ethics, IRB, informed consent, trial registration, pre-analysis plan, PAP, data security, vulnerable populations, research transparency.

Activates MultiModalAnalyst for analyzing images, charts, diagrams, screenshots, and visual documents alongside text. Use when you need to extract data from chart images, analyze UI screenshots for UX issues, interpret architectural diagrams, read scanned documents, analyze product mockups, or process any visual input that requires both vision and reasoning.

Generate a production-grade OEE (Overall Equipment Effectiveness) measurement pipeline for a manufacturing line — data ingestion from MQTT/OPC-UA/Modbus/CSV, A×P×Q calculation engine, Six Big Losses categorizer, MTBF/MTTR/TEEP metrics, Grafana or Streamlit dashboard, and downtime alerting. TRIGGER on phrases like "OEE", "overall equipment effectiveness", "downtime tracking", "production monitoring

Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.

Workflow for designing, querying, and reasoning about databases — schema modeling, normalization, keys/constraints, indexing strategy, query patterns, EXPLAIN plans, transactions and isolation. Covers general database concepts, relational/SQL behavior, engine-specific quirks, non-relational systems, and workload shapes. Defaults to relational; covers non-relational when the user is working there.

Activates BusinessIntelligence-Pro for KPI design, dashboard strategy, and SQL optimization. Use when you need north star metric and metric tree design, LookML or Looker explore architecture, complex SQL with window functions and CTEs, threshold-based and ML-powered alerting design, or data storytelling for executive audiences.

Orientação para avaliar e selecionar fornecedores de marketing, agências, ferramentas de IA e martech, cobrindo estruturas de avaliação, perguntas de verificação e gestão de stack. Aciona quando um usuário está avaliando uma nova ferramenta, auditando sua pilha de tecnologia ou selecionando uma agência ou provedor de dados.

Activates SQLAnalyzer for advanced SQL optimization, query analysis, and database performance tuning. Use when you need to optimize a slow query using EXPLAIN plans, rewrite subqueries as CTEs or window functions, design complex analytical queries, identify missing indexes, eliminate N+1 patterns, or write advanced SQL using window functions, recursive CTEs, or pivot logic.

Use a live Jupyter kernel for stateful, iterative Python execution via hamelnb. Load this skill when the task involves exploration, iteration, or inspecting intermediate results — data science, ML experimentation, API exploration, or building up complex code step-by-step. Uses terminal to run CLI commands against a live Jupyter kernel. No new tools required.