Data analysis, machine learning, LLM apps, and prompt design (8.9K skills)
Calculate portfolio risk and performance measures, including potential losses, declines from past peaks, and returns relative to risk. Use multiple indicators to support risk limits, position sizing, and ongoing monitoring.
Export an approved fine-tuned model into a format suited to its hardware and runtime. Choose weight packaging and quantization, which reduces numerical precision, then compare outputs before and after export to check for regressions.
Design backtests that evaluate trading strategies against historical data. Account for trading costs, avoid using future information or excluding delisted securities, and compare strategies using separate development and evaluation periods.
Prepare datasets for language model training by formatting examples, checking conversation templates, and packing examples into training sequences. Document data sources, synthetic data ratios, and validation results in a dataset card before starting a run.
Choose a model training method and configuration from paired response preferences or individual positive and negative ratings. Covers DPO, ORPO, KTO, and SimPO, including pair construction, repeated training rounds, and troubleshooting learning settings.
Prepare an evaluation framework before fine-tuning a language model. Build labeled examples, checks for each failure type, and a base-model benchmark, while calibrating model-based judges against human labels to support comparisons after training.
Tune vector indexes, which organize data for similarity searches, to balance speed, memory use, and missed matches. Choose index types, adjust HNSW settings, and assess compression options using benchmarks with real queries.
Prepare and review LoRA or QLoRA settings for adapting language models using example responses. Choose trainable layers, adapter capacity, learning rate, and memory-related options, then produce configuration values for a downstream training script.
Configure supervised fine-tuning for models that process images and text. Define which components remain unchanged, set LoRA adapters for updating selected model weights, choose image resolution limits, and investigate training runs whose evaluation results fail to improve.
Build AI applications that answer questions using retrieved documents. Covers vector databases, text embeddings that represent meaning as numbers, search strategies, and result reranking to connect language models with external knowledge.
Choose embedding models, which represent text as numerical vectors, for meaning-based search and RAG applications. Compare options for code, prose, and multilingual content, and plan document splitting, preprocessing, caching, and dimension reduction to improve retrieval quality.
Check ten recurring problems before or during machine learning runs on NVIDIA DGX Spark. Diagnose startup failures, out-of-memory errors, and falling throughput, with guidance on compatible environments, resource use, numeric formats, and training across two devices.
Set up machine learning training and inference on NVIDIA DGX Spark. Get guidance on choosing containers and packages, resolving CUDA compatibility errors, and checking that PyTorch can access the GPU before starting a workload.
Evaluate LLM applications using automated scores, human reviews, and model-based judging. Build repeatable checks to compare models or prompts, assess answer quality, and detect declines in performance before deployment.
Design AI applications with LangChain 1.x and LangGraph, libraries for coordinating language models and workflows. Build agents that use external tools, manage conversation history and saved state, process documents, and support tracing and testing.
Combine vector search, which finds similar meanings, with keyword search for exact terms. Design retrieval for search engines and RAG systems that supply reference material to AI, using methods to merge and rerank results.
Plan memory use and monitor long training jobs on NVIDIA DGX Spark. It guides troubleshooting for out-of-memory failures, tracks temperature and power alongside training logs, and helps assess competition between training and inference workloads.
Design and refine prompts for AI applications using examples, reusable templates, and structured outputs such as JSON. Test variations for accuracy, consistency, response time, and token usage to diagnose unreliable answers and formatting failures.
Improve slow Apache Spark jobs by reviewing data partitions, caching, memory settings, and shuffles, which move data between workers. Use the guidance to investigate bottlenecks and tune pipelines for larger datasets.
Turn analysis into reports and presentations that explain what the numbers mean. Combine charts, context, and a clear narrative to highlight key findings, connect them to audience goals, and propose next steps.
Design dbt data transformations with clearly organized models, data quality tests, documentation, and incremental processing that updates only part of a dataset. Use it to structure analytics tables and organize a dbt project.
Build data quality checks with Great Expectations, dbt tests, and data contracts, which define shared expectations between teams. Check missing values, duplicates, and freshness, then integrate validation into data pipelines and CI/CD.
Build Apache Airflow workflows for data pipelines and scheduled jobs. The skill guides task dependencies, retries, waiting for conditions, testing, and deployment, with patterns for tasks that can be safely rerun.
Turn supplied data into a suitable chart, dashboard, or visual explanation. The workflow chooses readable ways to show comparisons, includes source and assumption notes, and checks axes, units, and missing values without inventing data or hiding uncertainty.