Generates a Jupyter notebook that fine-tunes a base model using SageMaker serverless training jobs. Use when the user says "start training", "fine-tune my model", "I'm ready to train", or when the plan reaches the finetuning step. Supports SFT, DPO, and RLVR trainers, including RLVR Lambda reward function creation.
Generates a Jupyter notebook that evaluates a fine-tuned SageMaker model using LLM-as-a-Judge. Use when the user says "evaluate my model", "how did my model perform", "compare models", or after a training job completes. Supports built-in and custom evaluation metrics, evaluation dataset setup, and judge model selection.
Reflect, Evaluate, Fine-tune, Learn, Evolve, Correct, Transform — nightly automated performance review
Plan a new feature end-to-end — impact analysis across all layers before delegating to /domain, /read-model, /controller skills
Guide for working with the TOM (Tabular Object Model) wrapper. Use this when modifying semantic models programmatically.
Scaffold a new number system type with all required files, CMake wiring, exception hierarchy, traits, tests, and numeric_limits. Use when adding a new arithmetic type to the Universal library.
Validate a newly supported optimum-intel model with OpenVINO GenAI. Use when: checking new model support, verifying model export to OpenVINO IR, running GenAI inference test with llm_bench, benchmarking model accuracy with who-what-benchmark.
Expert knowledge for Azure AI Anomaly Detector development including troubleshooting, best practices, architecture & design patterns, limits & quotas, configuration, and deployment. Use when using univariate/multivariate APIs, Docker/IoT Edge containers, predictive maintenance flows, or regional limits, and other Azure AI Anomaly Detector related development tasks. Not for Azure AI Metrics Advisor (use azure-metrics-advisor), Azure Monitor (use azure-monitor), Azure Machine Learning (use azure-machine-learning).
Expert knowledge for Azure Machine Learning development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when using Azure ML workspaces, AutoML, Prompt Flow, online/batch endpoints, or SDK/CLI v2 deployments, and other Azure Machine Learning related development tasks. Not for Azure Databricks (use azure-databricks), Azure Synapse Analytics (use azure-synapse-analytics), Azure Data Science Virtual Machines (use azure-data-science-vm), Azure HDInsight (use azure-hdinsight).
LLM and ML development best practices with LangChain and transformers. Use when building AI/ML applications.
Performs logistic regression for clinical trial outcomes including binary, ordinal, and multinomial models. Extracts odds ratios with confidence intervals, handles covariate adjustment, and provides Firth penalized regression for rare events or separation. Use when modeling binary or ordinal endpoints from clinical data.
Implements nested cross-validation and stratified splits for unbiased model evaluation on biomedical datasets. Prevents data leakage and overfitting in biomarker discovery. Use when validating classifiers or optimizing hyperparameters on omics data.
Builds classification models for omics data using RandomForest, XGBoost, and logistic regression with sklearn-compatible APIs. Includes proper preprocessing and evaluation metrics for biomarker classifiers. Use when building diagnostic or prognostic classifiers from expression or variant data.
Analyzes time-to-event data using Kaplan-Meier curves, log-rank tests, and Cox proportional hazards regression with lifelines. Builds survival models from clinical and omics features. Use when predicting patient survival or modeling time-to-event outcomes.
How to discover, load, and effectively use skills to solve SkillBench tasks.
Prompt 优化助手。适用于用户想优化提示词、改进 AI 指令、为特定任务设计更好的 prompt，或需要选择合适提示框架时使用。会根据任务场景匹配合适框架，必要时先追问关键信息，再输出更清晰、更可执行的提示词版本。
讯飞超拟人语音合成 - 支持文本转语音、语音合成（发音人/语速/语调/音量/输出格式）。大模型语音合成技能。语音合成, 文字转语音, 超拟人, TTS. 用户指令如"把这段文案读出来"时使用此Skill。
iFlytek Voice Clone tts(声音复刻) — train a custom voice model from audio samples and synthesize speech with the cloned voice. Supports the full workflow: get training text → create task → upload audio → submit training → poll results → synthesize with cloned voice. Pure Python stdlib, no pip dependencies.
Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
Problem-solving strategies for gradient methods in optimization
