senior-data-scientist

tessl i github:alirezarezvani/claude-skills --skill senior-data-scientist

World-class data science skill for statistical modeling, experimentation, causal inference, and advanced analytics. Expertise in Python (NumPy, Pandas, Scikit-learn), R, SQL, statistical methods, A/B testing, time series, and business intelligence. Includes experiment design, feature engineering, model evaluation, and stakeholder communication. Use when designing experiments, building predictive models, performing causal analysis, or driving data-driven decisions.

52%

Overall

Validation — 88%

Implementation — 7%

Activation — 92%

SKILL.md

Review

Evals

Validation

88%

Warnings & errors only

Criteria	Description	Result
metadata_version	'metadata' field is not a dictionary	Warning
license_field	'license' field is missing	Warning

	Total	14 / 16 Passed

Implementation

This skill reads like a job description or capability statement rather than actionable guidance. It lists technologies, concepts, and responsibilities that Claude already knows without providing any concrete instructions for performing data science tasks. The referenced scripts and documentation files appear to be placeholders, leaving no executable content.

Suggestions

Replace capability lists with concrete, executable examples: show actual code for designing an A/B test, calculating sample size, or building a feature engineering pipeline

Add step-by-step workflows with validation checkpoints for key tasks like experiment design (hypothesis → power analysis → randomization → analysis plan → validation)

Remove generic content Claude already knows (what TDD is, soft skills, basic best practices) and focus on project-specific patterns, gotchas, or non-obvious techniques

Either create the referenced scripts/documentation or remove the references and inline the essential actionable content

Dimension	Reasoning	Score
Conciseness	Extremely verbose with extensive lists of concepts Claude already knows (what TDD is, what code reviews are, generic best practices). The 'Senior-Level Responsibilities' section is entirely unnecessary padding about soft skills Claude understands. Tech stack lists and generic production patterns add no actionable value.	1 / 3
Actionability	Despite showing command examples, they reference non-existent scripts (experiment_designer.py, feature_engineering_pipeline.py) with no actual implementation. The content describes capabilities rather than instructs - it's a resume, not a skill. No concrete, executable guidance for any data science task.	1 / 3
Workflow Clarity	No clear workflows for any data science task. Lists like 'Pattern 1: Scalable Data Processing' contain only bullet points of concepts without sequenced steps. No validation checkpoints, no feedback loops, no actual process to follow for experiment design, model building, or analysis.	1 / 3
Progressive Disclosure	References external files (references/statistical_methods_advanced.md, etc.) which is good structure, but the main content is a monolithic list of capabilities rather than a focused overview. The referenced files likely don't exist, and the main document doesn't provide enough actionable content to stand alone.	2 / 3
	Total	5 / 12 Passed

Activation

92%

This is a strong skill description that clearly articulates capabilities with specific tools and methods, includes natural trigger terms users would use, and provides explicit 'Use when' guidance. The main weakness is its broad scope which could create overlap with other data-related skills in a large skill library.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'statistical modeling, experimentation, causal inference, advanced analytics, experiment design, feature engineering, model evaluation, stakeholder communication' along with specific tools (NumPy, Pandas, Scikit-learn, R, SQL).	3 / 3
Completeness	Clearly answers both what (statistical modeling, experimentation, causal inference, etc.) AND when with explicit 'Use when...' clause covering four distinct trigger scenarios: designing experiments, building predictive models, performing causal analysis, or driving data-driven decisions.	3 / 3
Trigger Term Quality	Includes natural keywords users would say: 'A/B testing', 'time series', 'predictive models', 'causal analysis', 'data-driven decisions', 'experiments', plus tool names like 'Python', 'R', 'SQL' that users commonly mention.	3 / 3
Distinctiveness Conflict Risk	While it specifies data science and statistical methods, terms like 'advanced analytics', 'Python', 'SQL', and 'business intelligence' could overlap with general coding skills or BI-specific skills. The scope is broad enough to potentially conflict with more specialized analytics or ML skills.	2 / 3
	Total	11 / 12 Passed

Reviewed

18 days ago

Table of Contents

Validation Implementation Activation

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.