Agent skill

ce-alternatives-explore

Generate and interpret CE alternative and counterfactual explanations, including ensured filters and alternatives-specific plot workflows.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill ce-alternatives-explore --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 3 KB
Bundled scripts: none
Path: skills/ai-ml/ce-alternatives-explore/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# CE Alternatives Explorer You are producing alternative calibrated explanations — counterfactual rules that show what feature changes would produce a different prediction. The CE-First pipeline (fit + calibrate) is a prerequisite. If not in place, invoke `ce-pipeline-builder` first. For all post-generation interaction (plot, narrative, `add_conjunctions`, `filter_rule_sizes`, `filter_features`) see `ce-explain-interact`. Load `references/alternatives_api_reference.md` for the ensured framework, plot styles, ranking controls, and conjunction API. --- ## Two Entry Points ### Standard path ```python alternatives = explainer.explore_alternatives(X_query) ``` ### Explaining all classes (multiclass) ```python multi_alts = explainer.explore_alternatives(X_query, multi_labels_enabled=True) ``` ### Guarded path (production / unknown distributions — ADR-032) ```python alternatives = explainer.explore_guarded_alternatives(X_query) ``` Guarded variant: out-of-distribution instances are flagged rather than silently included. Use in production or when the input distribution is unknown. --- ## Threshold Semantics For **classification** — change the decision boundary: ```python alternatives = exp

What's inside
Steps it walks through
  1. Two Entry Points
  2. Standard path
  3. Explaining all classes (multiclass)
  4. Guarded path (production / unknown distributions — ADR-032)
  5. Threshold Semantics
  6. Output Types
  7. Out of Scope
  8. Evaluation Checklist
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the ce-alternatives-explore skill do?

Generate and interpret CE alternative and counterfactual explanations, including ensured filters and alternatives-specific plot workflows.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill ce-alternatives-explore --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.

Keep going