data-scientist · davila7 — Claude Code skill
A Claude Code skill for statistical analysis, machine learning, and data exploration. Use it when a task needs model selection, forecasting, or evidence-based analysis.
npx claude-code-templates@latest --skill ai-research/data-scientistWhat data-scientist does
This skill guides data-science work from clarifying the question through analysis and result checks. It covers exploratory analysis, hypothesis tests, experiment design, forecasting, clustering, supervised learning, feature work, and model interpretation.
Its reference stack includes Python tools such as pandas, NumPy, scikit-learn, SciPy, and statsmodels, plus R, SQL, PySpark, and Jupyter notebooks. It also discusses visualisation with matplotlib, seaborn, plotly, and dashboards built with Streamlit, Dash, or Shiny. Check which of the named stacks your project uses before asking for implementation details.
The scope reaches marketing, financial, and operations analytics, along with NLP, computer vision, graph analysis, and model deployment. MLflow, FastAPI, Docker, Airflow, and Prefect appear in the deployment and pipeline sections. The available description ends during the data-engineering section, so claims beyond those listed areas should not be inferred.
What it helps with
- explore a dataset and locate outliers
- design an A/B test with a measurable outcome
- compare predictive models and explain their features
- forecast a time series
- turn analysis results into a dashboard
Example prompts for the agent
- Run an exploratory analysis of
sales.csv, including missing values, outliers, and feature relationships. - Compare models for customer churn prediction and explain which features drive the result.
- Design an A/B test with a primary metric, a sample-size calculation, and a validation method.
How to install data-scientist
1claude-code-templates
npx claude-code-templates@latest --skill ai-research/data-scientist2Skills CLI (Vercel)
npx skills add davila7/claude-code-templates --skill data-scientist -a claude-code3Manually: put the files in place
~/.claude/skills/data-scientist/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/data-scientist/
Manually: put the files in place
.agents/skills/data-scientist/SKILL.mdFor all projects use ~/.agents/skills/
Manually: put the files in place
.cursor/skills/data-scientist/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install davila7/claude-code-templates data-scientist2Manually: put the files in place
.github/skills/data-scientist/SKILL.mdPlatform CLI
gemini skills install https://github.com/davila7/claude-code-templates --path cli-tool/components/skills/ai-research/data-scientistManually: put the files in place
.devin/skills/data-scientist/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about data-scientist
How do I install data-scientist in Claude Code?
Run npx claude-code-templates@latest --skill ai-research/data-scientist. The skill file is placed at ~/.claude/skills/data-scientist/SKILL.md.
What does the data-scientist skill do?
It helps Claude Code handle data exploration, statistical methods, machine learning, forecasting, and visualisation. It also guides result validation and model deployment work.
Which tools and methods are covered by data-scientist?
The skill covers pandas, NumPy, scikit-learn, SciPy, statsmodels, R, SQL, PySpark, Jupyter notebooks, MLflow, FastAPI, and Docker. The listed database systems include PostgreSQL, MySQL, BigQuery, Snowflake, and MongoDB.
Similar skills
All skills for Data and databases →data-scientist by other authors comes first.
