ce-mondrian-conditional
Configure and validate Mondrian and conditional calibration for subgroup-aware uncertainty and fairness-sensitive workflows.
npx skills add majiayu000/claude-skill-registry --skill ce-mondrian-conditional --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 Mondrian Conditional You are setting up Mondrian (conditional) calibration, which partitions calibration data into subgroups so that each group receives its own uncertainty estimate. This reveals group-specific prediction quality and is the foundational technique for fairness-aware deployments in CE. **Research**: [Conditional Calibrated Explanations (xAI 2024)](https://link.springer.com/chapter/10.1007/978-3-031-63787-2_17) Load `references/mondrian_examples.md` for full code examples (Options A/B/C, fairness analysis, global vs conditional comparison). --- ## Why Mondrian matters for fairness Without conditional calibration, the CPS/Venn-Abers calibrator averages over all calibration instances. A minority group with harder prediction patterns may receive the same interval width as an easy majority group, hiding bias. Mondrian splits calibration by a grouping key and fits a separate calibrator per bin. Resulting intervals are: - **Narrower** for groups the model predicts reliably. - **Wider** for groups the model predicts poorly. --- ## Three options for specifying bins - **Option A — Inline `bins` array**: pass integer group labels directly at calibrate time. - **Option B —
- Why Mondrian matters for fairness
- Three options for specifying bins
- Calibration -> predict -> explain consistency rules
- Minimum bin size warning
- Out of Scope
- Evaluation Checklist
What does the ce-mondrian-conditional skill do?
Configure and validate Mondrian and conditional calibration for subgroup-aware uncertainty and fairness-sensitive workflows.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill ce-mondrian-conditional --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.