senior-data-scientist

World-class senior data scientist skill specialising in statistical modeling, experiment design, causal inference, and predictive analytics. Covers A/B testing (sample sizing, two-proportion z-tests, Bonferroni correction), difference-in-differences, feature engineering pipelines (Scikit-learn, XGBoost), cross-validated model evaluation (AUC-ROC, AUC-PR, SHAP), and MLflow experiment tracking — using Python (NumPy, Pandas, Scikit-learn), R, and SQL. Use when designing or analysing controlled experiments, building and evaluating classification or regression models, performing causal analysis on observational data, engineering features for structured tabular datasets, or translating statistical findings into data-driven business decisions.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

92%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A high-quality, executable skill body: complete runnable code, validation-laden checklists with explicit thresholds, a pipeline feedback loop, and well-organized one-level-deep references that all exist. The only real weakness is minor redundant padding in the opening line and a few docstrings.

Suggestions

Remove the redundant opening sentence ('World-class senior data scientist skill for production-grade AI/ML/Data systems.') since it restates the frontmatter and adds no actionable content.

Trim descriptive docstring prose (e.g. 'Returns a fitted-ready ColumnTransformer for structured tabular data') to parameter-only docs where the intent is already obvious to Claude.

Consider moving the long per-workflow checklists into the matching reference files to keep SKILL.md as a tighter overview, now that those references exist.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean executable code with terse parameter-focused docstrings and bullet checklists, but the redundant opening line 'World-class senior data scientist skill for production-grade AI/ML/Data systems.' and a few descriptive docstrings are minor padding that could be trimmed, matching the 4 rather than the every-token-earns-its-place 5.	4 / 5
Actionability	Provides fully executable, copy-paste-ready functions (calculate_sample_size, analyze_experiment, build_feature_pipeline, evaluate_model, train_and_log, diff_in_diff) covering the common cases, matching the 5 anchor.	5 / 5
Workflow Clarity	Each workflow pairs code with a numbered checklist of explicit validation checkpoints ('Check for sample ratio mismatch: abs(n_control - n_treatment) / expected < 0.01', 'Check overfit_gap > 0.05', 'Validate parallel trends ... before trusting DiD estimates') plus a feedback loop for the bundled scripts ('any status other than completed means the stage failed — fix before moving to the next pipeline stage'), matching the 5 anchor.	5 / 5
Progressive Disclosure	A clearly signaled 'Reference Documentation' section uses bold labels linking one-level-deep to existing reference files, the bundled pipeline scripts are listed under 'Common Commands', and the core quick-start workflows are appropriately inline — all referenced paths verified to exist, matching the 5 anchor.	5 / 5
	Total	19 / 20 Passed

Description

88%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, concrete description that clearly states capabilities and explicit 'Use when' triggers across the data-science lifecycle. It is slightly held back by minor overlap breadth and a few missing natural synonyms, plus mild over-claim phrasing ('World-class').

Suggestions

Add a few natural synonyms/users' terms (e.g. 'machine learning / ML', '.csv/.xlsx', 'metrics/dashboards') to lift trigger-term coverage toward comprehensive.

Drop or soften the 'World-class' over-claim to avoid buzzword padding the rubric penalizes.

Tighten the distinctiveness by foregrounding the most distinctive niche (causal inference / experiment design) earlier in the sentence.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the full lifecycle — 'A/B testing (sample sizing, two-proportion z-tests, Bonferroni correction)', 'difference-in-differences', 'feature engineering pipelines', 'cross-validated model evaluation (AUC-ROC, AUC-PR, SHAP)', and 'MLflow experiment tracking' — giving comprehensive coverage rather than the minor gaps of a 4.	5 / 5
Completeness	Explicitly answers both what ('Covers A/B testing ... difference-in-differences ... MLflow experiment tracking') and when ('Use when designing or analysing controlled experiments, building and evaluating classification or regression models, performing causal analysis ...'), with concrete trigger phrases matching the 5 anchor.	5 / 5
Trigger Term Quality	Good natural-term coverage ('A/B testing', 'classification or regression models', 'causal analysis', 'feature engineering', 'observational data'), but it misses common variations a user might say ('machine learning', 'ML', '.csv/.xlsx', 'metrics') that would push it to a 5.	4 / 5
Distinctiveness Conflict Risk	The causal-inference and experiment-design niche is mostly distinct, but the breadth ('predictive analytics', feature engineering, model evaluation) creates minor overlap risk with a general ML skill, keeping it just below the minimal-conflict 5 anchor.	4 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: alirezarezvani/claude-skills
Path: engineering-team/skills/senior-data-scientist/SKILL.md
Commit: 19392f7

Reviewed: ~7 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.