shap
Use when "SHAP", "Shapley values", "feature importance", "model explainability", or asking about "explain predictions", "interpretable ML", "feature attribution", "waterfall plot", "beeswarm plot", "model debugging"
How do I install this agent skill?
npx skills add https://github.com/eyadsibai/ltk --skill shapIs this agent skill safe to install?
- Gen Agent Trust Hubpass
The skill provides comprehensive documentation and code examples for using the SHAP library for machine learning model interpretability. No malicious code or hidden behaviors were detected. The only security consideration is the inherent risk of indirect prompt injection when processing external datasets.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
- Runlayerpass
1 file scanned · No issues
What does this agent skill do?
SHAP Model Explainability
Explain ML predictions using Shapley values - feature importance and attribution.
When to Use
- Explain why a model made specific predictions
- Calculate feature importance with attribution
- Debug model behavior and validate predictions
- Create interpretability plots (waterfall, beeswarm, bar)
- Analyze model fairness and bias
Quick Start
import shap
import xgboost as xgb
# Train model
model = xgb.XGBClassifier().fit(X_train, y_train)
# Create explainer
explainer = shap.TreeExplainer(model)
# Compute SHAP values
shap_values = explainer(X_test)
# Visualize
shap.plots.beeswarm(shap_values)
Choose Explainer
# Tree-based models (XGBoost, LightGBM, RF) - FAST
explainer = shap.TreeExplainer(model)
# Deep learning (TensorFlow, PyTorch)
explainer = shap.DeepExplainer(model, background_data)
# Linear models
explainer = shap.LinearExplainer(model, X_train)
# Any model (slower but universal)
explainer = shap.KernelExplainer(model.predict, X_train[:100])
# Auto-select best explainer
explainer = shap.Explainer(model)
Compute SHAP Values
# Compute for test set
shap_values = explainer(X_test)
# Access components
shap_values.values # SHAP values (feature attributions)
shap_values.base_values # Expected model output (baseline)
shap_values.data # Original feature values
Visualizations
Global Feature Importance
# Beeswarm - shows distribution and importance
shap.plots.beeswarm(shap_values)
# Bar - clean summary
shap.plots.bar(shap_values)
Individual Predictions
# Waterfall - breakdown of single prediction
shap.plots.waterfall(shap_values[0])
# Force - additive visualization
shap.plots.force(shap_values[0])
Feature Relationships
# Scatter - feature vs SHAP value
shap.plots.scatter(shap_values[:, "feature_name"])
# With interaction coloring
shap.plots.scatter(shap_values[:, "Age"], color=shap_values[:, "Income"])
Heatmap (Multiple Samples)
shap.plots.heatmap(shap_values[:100])
Common Patterns
Complete Analysis
import shap
# 1. Create explainer and compute
explainer = shap.TreeExplainer(model)
shap_values = explainer(X_test)
# 2. Global importance
shap.plots.beeswarm(shap_values)
# 3. Top feature relationships
shap.plots.scatter(shap_values[:, "top_feature"])
# 4. Individual explanation
shap.plots.waterfall(shap_values[0])
Compare Groups
# Compare feature importance across groups
group_a = X_test['category'] == 'A'
group_b = X_test['category'] == 'B'
shap.plots.bar({
"Group A": shap_values[group_a],
"Group B": shap_values[group_b]
})
Debug Errors
# Find misclassified samples
errors = model.predict(X_test) != y_test
error_idx = np.where(errors)[0]
# Explain why they failed
for idx in error_idx[:5]:
shap.plots.waterfall(shap_values[idx])
Interpret Values
- Positive SHAP → Feature pushes prediction higher
- Negative SHAP → Feature pushes prediction lower
- Magnitude → Strength of impact
- Sum of SHAP values = Prediction - Baseline
Baseline: 0.30
Age: +0.15
Income: +0.10
Education: -0.05
Prediction: 0.30 + 0.15 + 0.10 - 0.05 = 0.50
Best Practices
- Use TreeExplainer for tree models (fast, exact)
- Use 100-1000 background samples for KernelExplainer
- Start global (beeswarm) then go local (waterfall)
- Check model output type (probability vs log-odds)
- Validate with domain knowledge
vs Alternatives
| Tool | Best For |
|---|---|
| SHAP | Theoretically grounded, all model types |
| LIME | Quick local explanations |
| Feature Importance | Simple tree-based importance |
Resources
- Docs: https://shap.readthedocs.io/
- Paper: Lundberg & Lee (2017) "A Unified Approach to Interpreting Model Predictions"
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/eyadsibai/ltk/shap">View shap on skillZs</a>