Reusable agent skills that make AI coding agents do data science correctly: explore before modelling,
clean without hiding anything, and catch leakage before it fakes a great score. Each skill is a short SKILL.md
plus one tested Python script. Free libraries only, no API keys.
Profile a dataset: shape, column types, missing values, distributions, correlations and the target, saved as a markdown report with charts.
SKILL.md ↗ · exampleFix what is clearly broken (spaces, "N/A" text, money strings, mixed dates, spelling variants, duplicates), flag what needs a decision, log every change.
SKILL.md ↗ · exampleFind target leakage (columns recorded after the outcome) and train/test contamination (shared rows, groups, time overlap), with HIGH/MEDIUM/LOW findings.
SKILL.md ↗ · exampleTitanic passenger list (1,309 people). Same model and pipeline, 5-fold cross-validation × 3.
| Columns | Accuracy | ROC AUC | |
|---|---|---|---|
| Before: every column | 12, incl. boat, body | 0.974 | 0.993 |
| After: leakage-check first | 10 (removed: boat, body) | 0.787 | 0.847 |
The 97% is fake: boat is the lifeboat a passenger got into and body the number of a recovered body. Neither is known before the ship sinks. The honest score is 78.7%.
Problems planted on purpose into four real datasets (scikit-learn breast cancer, wine, diabetes, and Titanic without the leaking columns).
| Planted leak | Found |
|---|---|
| Copy of the target (re-coded or noisy) | 12/12 |
| Value recorded after the outcome | 12/12 |
| Value present for one outcome only | 9/9 |
| File sorted by the target | 12/12 |
| Same customer/patient in train and test | 12/12 |
| Test older than train | 12/12 |
| Training rows copied into test | 12/12 |
In breast cancer, 10 genuinely strong measurements are marked MEDIUM ("check when this value is known"): strong is not the same as leaking. The thresholds and planted problems were designed by me, so these numbers show the scripts do what they promise, not that they catch every leak in the wild.
git clone --depth 1 https://github.com/m-shahmeer-kz/dataskills ~/dataskills && mkdir -p ~/.claude/skills && cp -r ~/dataskills/skills/* ~/.claude/skills/ && pip install -r ~/dataskills/requirements.txt
Then ask your agent things like "Explore data/sales.csv" or "Is my churn model leaking?".
MIT licence · Muhammad Shahmeer · github.com/m-shahmeer-kz/dataskills