AlterLab SHAP
技能 已验证 活跃Part of the AlterLab Academic Skills suite. Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model.
To empower users to understand and explain their machine learning model predictions using the SHAP framework, enabling better debugging, fairness analysis, and model deployment.
功能
- Compute SHAP values for diverse model types (tree, deep learning, linear, black-box)
- Generate a wide range of SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap)
- Provide detailed workflows for model explanation, debugging, feature engineering, and fairness analysis
- Offer comprehensive reference documentation for explainers, plots, theory, and advanced techniques
- Guidance on production deployment and performance optimization
使用场景
- Explaining individual model predictions to stakeholders
- Debugging why a model made a specific incorrect prediction
- Identifying and quantifying feature importance across a dataset
- Analyzing model bias and fairness across different demographic groups
- Understanding feature interactions and nonlinear relationships
非目标
- Training machine learning models
- Performing hyperparameter tuning
- Deploying models directly to production environments (guidance provided, not direct deployment)
- Replacing the need for domain expertise in interpreting results
工作流
- Select the appropriate SHAP explainer based on model type.
- Compute SHAP values for the model's predictions using background data.
- Visualize results using plots like waterfall, beeswarm, bar, or scatter plots.
- Interpret feature contributions to understand global importance and individual predictions.
- Debug model behavior, analyze fairness, or engineer features based on insights.
- Integrate explanations into production systems or workflows.
实践
- Model Interpretability
- Explainable AI
- Machine Learning Workflow
先决条件
- Python 3.7+
- numpy
- pandas
- scikit-learn
- matplotlib
- shap
- xgboost, lightgbm, tensorflow, torch (depending on model type)
Execution
- info:Pinned dependenciesDependencies are listed, and installation instructions suggest standard package managers, but explicit lockfiles for pinning are not evident.
安装
npx skills add AlterLab-IEU/AlterLab-Academic-Skills通过 npx 运行 Vercel skills CLI(skills.sh)— 需要本地安装 Node.js,以及至少一个兼容 skills 的智能体(Claude Code、Cursor、Codex 等)。前提是仓库遵循 agentskills.io 格式。
质量评分
已验证类似扩展
SHAP Model Interpretability
100Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model.
TimesFM Forecasting
100Zero-shot time series forecasting with Google's TimesFM foundation model. Use for any univariate time series (sales, sensors, energy, vitals, weather) without training a custom model. Supports CSV/DataFrame/array inputs with point forecasts and prediction intervals. Includes a preflight system checker script to verify RAM/GPU before first use.
Molfeat
99Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML.
OraClaw Forecast
100AI 代理的时间序列预测。ARIMA 和 Holt-Winters 预测（含置信区间）。预测收入、流量、价格或任何序列数据。推理延迟低于 5 毫秒。
Arize Evaluator
100Handles LLM-as-judge evaluation workflows on Arize including creating/updating evaluators, running evaluations on spans or experiments, managing tasks, trigger-run operations, column mapping, and continuous monitoring. Use when the user mentions create evaluator, LLM judge, hallucination, faithfulness, correctness, relevance, run eval, score spans, score experiment, trigger-run, column mapping, continuous monitoring, or improve evaluator prompt.
PyTorch Lightning
100Deep learning framework (PyTorch Lightning). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard), distributed training (DDP, FSDP, DeepSpeed), for scalable neural network training.