dianaprior

4 mods across 1 repository, 5 stars between them.

tabpfn-classify

01

dianaprior/kaggle-competition-agent-skill

Skill Claude CodeCodex

Run a TabPFN classification baseline, generate the first submission, rapidly probe features, then optimize with GBT ensembles, threshold tuning, and calibration. Use after tabpfn-explore has prepared the data and CV folds.

5 6mo ago A 51 tokens

tabpfn-core

02

dianaprior/kaggle-competition-agent-skill

Skill Claude CodeCodex

Shared identity, behavior rules, workflow principles, and project conventions for TabPFN tabular competition skills. Referenced by tabpfn-classify, tabpfn-regress, and tabpfn-explore — not invoked directly.

5 6mo ago A 52 tokens

tabpfn-explore

03

dianaprior/kaggle-competition-agent-skill

Skill Claude CodeCodex

EDA, data profiling, adversarial validation, preprocessing checks, CV scheme setup, and API budget verification for tabular Kaggle competitions. Run at the start of every new competition before any modeling.

5 6mo ago A 45 tokens

tabpfn-regress

04

dianaprior/kaggle-competition-agent-skill

Skill Claude CodeCodex

Run a TabPFN regression baseline, generate the first submission, then optimize with GBT ensembles and regression-specific post-processing (clipping, target transforms, rank blending). Use after tabpfn-explore has prepared the data and CV folds.

5 6mo ago A 55 tokens