# Ml Model Code Review

> Use when performing ml model code review — mL/AI code review template covering data leakage detection, model reproducibility, bias assessment, feature engineering validation, and experiment tracking. Provides a systematic review framework for machine learning pipelines, model training code, and inference service changes.

- Skill: `cloudthinker-ai/ml-model-code-review` (Agent Skill)
- Install (CLI): `npx skillmds@latest add cloudthinker-ai/ml-model-code-review`
- Raw SKILL.md: https://api.skillmd.com/api/skills/cloudthinker-ai/ml-model-code-review/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: cloudthinker-ai (https://skillmd.com/u/cloudthinker-ai)
- Updated: 2026-09-08
- Page: https://skillmd.com/skills/cloudthinker-ai/ml-model-code-review

---


# ML Model Code Review Skill

Review ML PR **#{{ pr_number }}** in **{{ repository }}** for **{{ model_type }}** model.

## Workflow

### Phase 1 — Data Leakage

```
DATA LEAKAGE CHECK
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
[ ] Train/test split:
    [ ] Data split before any preprocessing
    [ ] No information from test set in training
    [ ] Temporal splits for time-series data
    [ ] Group-aware splits (same entity not in both sets)
[ ] Feature leakage:
    [ ] No target-derived features
    [ ] No future data used in features
    [ ] No features unavailable at inference time
    [ ] Label encoding fit only on training data
[ ] Preprocessing leakage:
    [ ] Scalers/normalizers fit only on training data
    [ ] Imputation values from training data only
    [ ] Feature selection based on training data only
```

### Phase 2 — Reproducibility

```
REPRODUCIBILITY CHECK
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
[ ] Random seeds:
    [ ] Random seeds set for all stochastic operations
    [ ] Seeds documented and versioned
    [ ] Deterministic mode enabled where possible
[ ] Experiment tracking:
    [ ] Hyperparameters logged (MLflow, W&B, etc.)
    [ ] Training metrics tracked
    [ ] Model artifacts versioned
    [ ] Data version recorded (DVC, dataset hash)
[ ] Environment:
    [ ] Dependencies pinned (requirements.txt / conda.yml)
    [ ] GPU/CUDA version documented
    [ ] Docker image versioned for training environment
```

### Phase 3 — Bias and Fairness

```
BIAS ASSESSMENT
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
[ ] Data bias:
    [ ] Training data representative of target population
    [ ] Class imbalance addressed (oversampling, weights)
    [ ] Protected attributes identified
    [ ] Demographic parity evaluated
[ ] Model bias:
    [ ] Performance metrics computed per subgroup
    [ ] Disparate impact ratio calculated
    [ ] Fairness constraints applied if needed
    [ ] Bias mitigation documented
[ ] Documentation:
    [ ] Model card created/updated
    [ ] Known limitations documented
    [ ] Intended use cases specified
```

### Phase 4 — Model Quality

```
MODEL QUALITY
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
[ ] Evaluation:
    [ ] Appropriate metrics for task (not just accuracy)
    [ ] Evaluation on held-out test set
    [ ] Cross-validation where appropriate
    [ ] Baseline comparison provided
[ ] Production readiness:
    [ ] Model size acceptable for deployment target
    [ ] Inference latency within SLA
    [ ] Model serialization format compatible
    [ ] Input validation at inference time
    [ ] Graceful handling of missing/malformed features
    [ ] A/B test plan for model rollout
```

## Counter-Rationalizations

| Shortcut | Counter | Why |
|----------|---------|-----|
| "We can skip some steps for this case" | Adapt the workflow steps, don't skip them | Skipped steps are where incidents and oversights originate |
| "The user seems to already know what to do" | Complete all workflow phases with the user | The workflow catches blind spots that experience alone misses |
| "This is a minor case, full process is overkill" | Scale the process down, don't turn it off | Minor cases become major when unstructured; the process scales, not disappears |
| "I'll fill in the details later" | Complete each section before moving on | Deferred details are forgotten; real-time capture is more accurate |
| "The template output isn't necessary" | Always produce the structured output format | Structured output enables comparison, audit trails, and handoff to other teams |

## Output Format

Produce an ML review report with:
1. **Data leakage findings** (none / potential / confirmed)
2. **Reproducibility assessment** (reproducible / partially / not reproducible)
3. **Bias and fairness** evaluation
4. **Model quality** metrics vs baseline
5. **Production readiness** checklist status