Agent skill

ce-explain-interact

Post-process CE explanations by narrating, plotting, inspecting rules, filtering features, and managing conjunctions.

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

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

Facts
Files in the skill folder: 2
SKILL.md size: 8 KB
Bundled scripts: none
Path: skills/ai-ml/ce-explain-interact/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 Explain Interact This skill covers the generic post-generation API that is shared by every CE explanation type. It applies to both individual `CalibratedExplanation` instances and `CalibratedExplanations` collections. ## Conjunctions Add compound multi-feature rules on top of the existing atomic rules: ```python # On a single instance (mutates in place, returns self for chaining) explanations[0].add_conjunctions(max_rule_size=2) # default explanations[0].add_conjunctions(max_rule_size=3) # triples explanations[0].add_conjunctions(max_rule_size=2, n_top_features=5) # limit outer # On the whole collection (applies to each instance) explanations.add_conjunctions(max_rule_size=2, n_top_features=5) ``` ### Parameters | Parameter | Default | Meaning | |---|---|---| | `max_rule_size` | `2` | **Primary control.** Maximum number of features in a conjunctive rule. Must be ≥ 2. Values ≥ 4 require batched mode (internal). | | `n_top_features` | `5` | Optional: limit the outer feature loop to the N most impactful features. Higher values explore more combinations but take longer. | **`max_rule_size` is the key knob.** `n_top_features` is a speed/pruning control. ### After adding conjunction

What's inside
Steps it walks through
  1. Conjunctions
  2. Parameters
  3. After adding conjunctions
  4. Narrative
  5. Plotting
  6. Common kwargs (all explanation types)
  7. Filtering Rules by Size
  8. Filtering Rules by Feature
  9. Notes for conjunctive rules
  10. Inspecting Explanation Contents
  11. Chaining
  12. Out of Scope
  13. Evaluation Checklist
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the ce-explain-interact skill do?

Post-process CE explanations by narrating, plotting, inspecting rules, filtering features, and managing conjunctions.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill ce-explain-interact --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