Use when creating an R modeling package that needs standardized preprocessing for formula, data frame, matrix, and recipe interfaces. Covers: mold() for training data preprocessing, forge() for prediction data validation, blueprints, model constructors, spruce functions for output formatting.
Design and refactor beam tracking ML/RL pipelines (CSI teacher vs RSRP student), enforce shape contracts, and produce inference-safe models.
GLM-4.7 모델을 효과적으로 활용하는 방법을 안내합니다. 사용자가 "GLM 사용법", "GLM 프롬프트", "GLM 최적화" 등을 질문할 때 활성화됩니다.
深度学习训练体系与实验编排专家。当用户询问“训练”“验证”“测试”“启动命令” “数据集划分”等问题时使用。要求模型结构已被明确定义。
Fix phantom MaxDD values in training by calibrating reward_scale. Trigger when: (1) validation MaxDD shows 35-80% values, (2) MaxDD doesn't correlate with training quality, (3) gating thresholds seem too lenient/strict.
Complete context for TAR UMT Data Science FYP implementing CrossViT for COVID-19 chest X-ray classification. Use when working on Jupyter notebooks, code implementation, data analysis, model training, or any task related to Tan Ming Kai's final year project. This skill provides dataset specs, model architecture details, hardware constraints (NVIDIA RTX 6000 Ada Generation (51GB VRAM) VRAM), preprocessing parameters, baseline models, evaluation metrics, hypotheses, and coding guidelines for reproducible research following TAR UMT academic requirements.
Exhaustive solution space exploration methodology. Use when solution space is unknown, you need multiple viable options (not just one best), or can't afford to miss alternatives. Explores 8-10 approaches in parallel at each level, prunes conservatively (keep above 40% confidence), returns 3-5 viable solutions. Example - data pipeline options - Apply BoT to explore all architectures exhaustively.
Training models on extended context lengths using optimized RoPE scaling and memory-efficient attention kernels. Triggers: long context, max_seq_length, rope scaling, large context window, flex attention.
Post-training model validation workflow: gating, backtesting, walk-forward validation, deployment decisions. Trigger after GPU training completes.
Run model validation on a dataset. Use when testing model performance, comparing checkpoints, or running final evaluation.
Guidelines for using Zen MCP tools effectively in this repo. Use for complex multi-model tasks, architectural decisions, or when cross-model validation adds value.
See the main Model Explainability skill for comprehensive XAI coverage.
Эксперт active learning. Используй для ML с участием человека, uncertainty sampling, annotation workflows и labeling optimization.
Follow these patterns when extending the OptAIC Python SDK with new domain operations. Use for adding client methods for datasets, signals, portfolios, backtests, and other resources. Covers async/sync interfaces, uploads, and long-running operations.
GPU-aware PPO training configuration for A100/H100. Trigger when training is slow or GPU utilization is low.
Foundational knowledge for writing PyMC 5 models including syntax, distributions, sampling, and ArviZ diagnostics. Use when creating or reviewing PyMC models.
Recognize/Describe clearML architecture and extension points
