Use this skill when designing, cleaning, deduplicating, or documenting datasets for model training and evaluation including schema design, class imbalance handling, and train/val/test splits. Not for running model training or hyperparameter tuning. Not for real-time data pipeline engineering.
Use this skill when building evaluation frameworks to measure LLM quality, safety, accuracy, or alignment including test suites, human eval rubrics, automated evals, and metrics design. Not for training or fine-tuning models. Not for dataset curation or benchmark comparison across publicly available models.
Use this skill when comparing AI or LLM models on benchmarks, capability, cost, latency, context window, or task-specific fit to help teams select the right model for their use case and budget. Not for training or fine-tuning models. Not for building eval frameworks from scratch.
Use this skill when crafting, iterating, or optimizing prompts for LLMs including zero-shot, few-shot, chain-of-thought, role prompting, structured output, and prompt chaining. Not for fine-tuning or training models. Not for evaluating model quality across benchmarks.
Use this skill when designing or improving observability stacks with Prometheus, Grafana, Loki, Jaeger, or configuring alerting rules and SLIs/SLOs. Not for application code debugging or infrastructure provisioning. Not for log analysis of already-collected logs.
Use this skill when generating, planning, or describing structured Word-compatible documents from outlines, raw content, or templates including heading hierarchy, table structures, and formatting conventions. Not for editing existing DOCX files programmatically. Not for PDF layout or presentation slide design.
Use this skill when describing, summarizing, extracting structured data from, or answering questions about PDF documents, or when planning PDF layout and structure for reports, contracts, and publications. Not for editing binary PDF files directly. Not for converting PDFs to other formats programmatically.
Use this skill when planning and scripting PowerPoint or Google Slides presentations with slide titles, bullet points, speaker notes, transitions, and narrative flow, or when converting documents into slide decks. Not for designing graphic assets or custom visual themes. Not for video or animation production.