ds-model-explainability

Name: ds-model-explainability
Availability: InStock
Author: phife726

Explain ML model predictions and audit fairness with SHAP, LIME, and model cards.

Updated Mar 8, 2026

Search Tags:#fairness #explainability #interpretability #shap #lime #model-cards #pdp-ice

Ready to run

npx skills add https://github.com/Phife726/ds_agent --skill ds-model-explainability

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ds-model-explainability
Source: https://github.com/Phife726/ds_agent/tree/main/ds-model-explainability
Command: npx skills add https://github.com/Phife726/ds_agent --skill ds-model-explainability

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Explainability and fairness in machine learning models, enabling you to communicate predictions, audit biases, and document behavior for stakeholders and regulators.

Core Features & Use Cases

Global and local explanation capabilities for model predictions (SHAP, PDP/ICE, LIME).
Fairness auditing and documentation via model cards and fairness metrics.
Use Cases: regulatory reviews, deployment documentation, and product-ready explanations for customers.

Quick Start

Explain a given model prediction using SHAP values and provide a concise global model summary.

Frequently Asked Questions about ds-model-explainability

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I explain ML model predictions for regulatory reviews?▼

Explain ML model predictions for regulatory reviews by generating global summaries, local explanations, and regulatory artifacts using SHAP, LIME, and fairness metrics to audit biases and document model behavior for stakeholders.

Can I generate model cards to audit fairness for deployment documentation?▼

Yes, you can generate model cards to audit fairness for deployment documentation by calculating fairness metrics and documenting model behavior across tabular, image, and text data to communicate predictions and biases to stakeholders.

What is the difference between global and local model interpretability?▼

Global interpretability provides overall feature importance summaries using PDP/ICE curves, while local interpretability explains individual predictions using SHAP and LIME values to clarify specific outcomes for stakeholders.

Does this work for explaining predictions on both text and image models?▼

Yes, it works for explaining predictions on text and image models by applying modular explanation toolkits like SHAP and LIME to generate global summaries and local explanations across tabular, image, and text modalities.

How do I use counterfactuals and PDP/ICE for model explainability?▼

Use counterfactuals and PDP/ICE for model explainability to generate global summaries showing feature impacts and local explanations identifying alternative outcomes, enabling stakeholder communication and ongoing monitoring.