Data Scientist

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkNone observedNo outbound calls in the source
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass.

.codex/skills/a11y-audit

.codex/skills/ab-test-setup

.codex/skills/account-executive

.codex/skills/ad-creative

.codex/skills/aeo

Audit 0.4.1 · source sha 6e3fcbdbb5cf · 19 Oct 2026Report an issue or request a re-scan

• Publisherborghei GitHub userOwner of the repository this skill is read from
• Source folderborghei/Claude-Skills/data-analytics/data-scientistThe exact folder we audited
• LicenceNOASSERTIONAs the repository states it
• Commit pinned for this verdict6e3fcbdbb5cfA new audit runs when the source changes
• Repository statusNot archivedLast push 12 days ago
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: Data science across machine learning, statistical modeling, and experimentation. Use when selecting ML algorithms, engineering features, designing A/B tests, evaluating model performance, or building predictive…

---
name: data-scientist
description: >
  Data science across machine learning, statistical modeling, and
  experimentation. Use when selecting ML algorithms, engineering features,
  designing A/B tests, evaluating model performance, or building predictive
  pipelines.
license: MIT + Commons Clause
metadata:
  version: 1.0.0
  author: borghei
  category: data-analytics
  updated: 2026-03-31
  tags: [data-science, machine-learning, statistics, modeling, analytics]
---
# Data Scientist

The agent operates as a senior data scientist, selecting algorithms, engineering features, designing experiments, evaluating models, and translating predictions into business impact.

## Clarify First

Before modeling, confirm these inputs. If any is unknown or vague, ASK — do not assume:

- [ ] **ML task + primary metric** — classification, regression, ranking, or clustering, and the metric that defines success (e.g., F1, RMSE) (drives algorithm selection and evaluation)
- [ ] **Constraints** — latency, interpretability, and data volume (decides where on the simple→complex model ladder to land)
- [ ] **Target variable and label quality** — what is being predicted and how clean/balanced the labels are (drives feature engineering and imbalance handling)
- [ ] **For an A/B test: baseline rate + MDE** — current conversion and the smallest lift worth detecting (drives the required sample size)

Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.

## Workflow

1. **Define the problem** -- Restate the business objective as an ML task (classification, regression, ranking, clustering). Define the primary evaluation metric (e.g., F1 for imbalanced classification, RMSE for regression). Document constraints (latency, interpretability, data volume).
2. **Collect and profile data** -- Identify sources, check row counts, null rates, class balance, and feature distributions. Flag data-quality issues before modeling.
3. **Engineer features** -- Create numerical transforms (log, binning), encode categoricals (one-hot, target, frequency), extract time components (hour, day-of-week, cyclical sin/cos). Select top features via importance, mutual information, or RFE.
4. **Select and train models** -- Use the algorithm selection matrix below. Start simple (logistic/linear regression), then add complexity (Random Forest, XGBoost, neural nets) only if needed. Use cross-validation.
5. **Evaluate rigorously** -- Report classification metrics (accuracy, precision, recall, F1, AUC-ROC) or regression metrics (MAE, RMSE, R-squared, MAPE). Compare against a baseline. Check for overfitting (train vs. test gap).
6. **Communicate results** -- Present business impact (e.g., "model reduces false positives by 30%, saving $500K/yr"). Recommend deployment path or next experiment.

## Algorithm Selection Matrix

| Scenario | Recommended | When to upgrade |
|----------|------------|-----------------|
| Need interpretability | Logistic / Linear Regression | Always start here for stakeholder-facing models |
| Small data (< 10K rows) | Random Forest | Move to XGBoost if accuracy insufficient |
| Medium data, high accuracy needed | XGBoost / LightGBM | Default workhorse for tabular data |
| Large data, complex patterns | Neural Network | Only when tree methods plateau |
| Unsupervised grouping | K-Means / DBSCAN | Use silhouette score to validate k |

## Feature Engineering Examples

**Numerical transforms:**
```python
import numpy as np, pandas as pd

def engineer_numerical(df: pd.DataFrame, col: str) -> pd.DataFrame:
    return pd.DataFrame({
        f'{col}_log':     np.log1p(df[col]),
        f'{col}_sqrt':    np.sqrt(df[col].clip(lower=0)),
        f'{col}_squared': df[col] ** 2,
        f'{col}_binned':  pd.cut(df[col], bins=5, labels=False),
    })
```

**Time-based features with cyclical encoding:**
```python
def engineer_time(df: pd.DataFrame, col: str) -> pd.DataFrame:
    dt = pd.to_datetime(df[col])
    return pd.DataFrame({
        f'{col}_hour':      dt.dt.hour,
        f'{col}_dayofweek': dt.dt.dayofweek,
        f'{col}_month':     dt.dt.month,
        f'{col}_is_weekend': dt.dt.dayofweek.isin([5, 6]).astype(int),
        f'{col}_hour_sin':  np.sin(2 * np.pi * dt.dt.hour / 24),
        f'{col}_hour_cos':  np.cos(2 * np.pi * dt.dt.hour / 24),
    })
```

**Feature selection (importance-based):**
```python
from sklearn.ensemble import RandomForestClassifier

def select_top_features(X, y, n=20):
    rf = RandomForestClassifier(n_estimators=100, random_state=42)
    rf.fit(X, y)
    importance = pd.Series(rf.feature_importances_, index=X.columns)
    return importance.nlargest(n).index.tolist()
```

## Model Evaluation

**Classification:**
```python
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, roc_auc_score

def evaluate_classifier(y_true, y_pred, y_proba=None) -> dict:
    m = {
        "accuracy":  accuracy_score(y_true, y_pred),
        "precision": precision_score(y_true, y_pred),
        "recall":    recall_score(y_true, y_pred),
        "f1":        f1_score(y_true, y_pred),
    }
    if y_proba is not None:
        m["auc_roc"] = roc_auc_score(y_true, y_proba)
    return m
```

**Regression:**
```python
from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score
import numpy as np

def evaluate_regressor(y_true, y_pred) -> dict:
    return {
        "mae":  mean_absolute_error(y_true, y_pred),
        "rmse": np.sqrt(mean_squared_error(y_true, y_pred)),
        "r2":   r2_score(y_true, y_pred),
    }
```

## A/B Test Design and Analysis

**Sample size calculation:**
```python
from scipy import stats
import numpy as np

def required_sample_size(baseline_rate: float, mde: float, alpha: float = 0.05, power: float = 0.8) -> int:
    """Return required N per variant. mde is relative (e.g., 0.10 = 10% lift)."""
    effect = baseline_rate * mde
    z_a = stats.norm.ppf(1 - alpha / 2)

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

git clone https://github.com/borghei/Claude-Skills
git -C Claude-Skills checkout 6e3fcbdbb5cf

Works in

1. 2026-10-19
   !CAUTION B 89 / 100

   first audit · source 6e3fcbdbb5cf

Questions about Data Scientist

• github.com/borghei/Claude-Skills/tree/main/data-analytics/data-s — the audited source at commit 6e3fcbdbb5cf and every finding aboveObserved · 19 Oct 2026

Spotted something wrong? Report a correction · Methodology