ce-integration-compare
Guide CE integration with SHAP and LIME, compare explanation outputs, and configure the calibrated-explanations integration adapters.
npx skills add majiayu000/claude-skill-registry --skill ce-integration-compare --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# CE Integration Compare You are helping users work with the CE integrations for SHAP and LIME. ## Required references - `src/calibrated_explanations/integrations/shap.py` - `src/calibrated_explanations/integrations/lime.py` - `src/calibrated_explanations/integrations/__init__.py` ## Use this skill when - A user asks how to use CE with SHAP or LIME. - Comparing CE explanations with SHAP/LIME outputs. - Configuring or debugging the integration adapters. - Understanding the differences between calibrated explanations and feature-attribution methods. ## Key concepts ### CE vs. feature attribution methods Calibrated explanations provide **rule-based explanations with calibrated uncertainty intervals**. SHAP and LIME provide **feature attribution values** (importance scores per feature). The approaches are complementary: - CE rules tell you *which conditions* justify a prediction with calibrated confidence. - SHAP/LIME tell you *how much* each feature contributed to the prediction. ### Integration architecture The integration modules provide adapter classes that: 1. Wrap a fitted CE explainer to produce SHAP-compatible or LIME-compatible outputs. 2. Allow side-by-side comparison of CE r
- Required references
- Use this skill when
- Key concepts
- CE vs. feature attribution methods
- Integration architecture
- Workflow
- Constraints
What does the ce-integration-compare skill do?
Guide CE integration with SHAP and LIME, compare explanation outputs, and configure the calibrated-explanations integration adapters.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill ce-integration-compare --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.