100 Best Claude Prompts for Data Analysis

Introduction

This page is a practical Claude prompts library for Data Analysis. It targets analysts, data scientists, BI professionals, and teams seeking actionable prompts to accelerate data-driven insights using Anthropic Claude prompts, Claude AI prompts, and related tooling.

Use these prompts to structure your data work from discovery through delivery, with repeatable steps that can be adapted to any dataset.

Direct Answer

The best Claude prompts for Data Analysis are a curated, copyable set of 100 prompts organized to cover data cleaning, exploration, modeling, visualization, storytelling, and governance. Each prompt includes a role, task, placeholders, output format, and constraints to ensure concrete, reusable results.

How to Use These Claude Prompts

• Replace placeholders in each prompt with your [dataset], [columns], [business goals], and [timeframe].
• Add constraints such as data privacy rules, tooling, and delivery format to tailor prompts to your environment.
• Request outputs in clear formats (e.g., JSON, CSV, markdown) and specify the required level of detail.
• Combine prompts to build end‑to‑end analyses, then verify outputs against acceptance criteria or dashboards.
• Test prompts on a small sample first to ensure outputs align with expectations before scaling to production data.

100 Best Claude Prompts for Data Analysis

1. Clarify Data Analysis Objective: As a Data Analyst, given dataset [dataset], define the primary objective of this analysis in 2–3 clear questions. Specify success metrics [metrics], outline the deliverables in [format], and propose a realistic timeline of [deadline]. Include constraints like [data access], [tools], and [privacy] and request required data fields [fields] and a verification plan.
2. Inventory Data Sources and Quality: Act as a Data Quality Auditor. For dataset [dataset], list all data sources, assess data quality dimensions (completeness, accuracy, consistency, timeliness), identify critical gaps, and recommend remediation steps. Deliver a data quality score and a remediation plan in [format].
3. Define Success Metrics: In the context of [business objective], define a metric set to measure success of the analysis. For each metric specify calculation formula, data source, granularity, sampling rules, and acceptable thresholds. Provide at least 3 primary metrics and 2 secondary metrics. Output in [format].
4. Plan Data Cleaning Steps: Create a data cleaning plan for dataset [dataset]. List cleaning steps (nulls, duplicates, outliers, type casting, encoding), assign owners, effort, and order. Include validation checks after each step and a final data quality score. Output as a checklist in [format].
5. Prepare Data Cleaning Checklist: Produce a reusable data cleaning checklist for [dataset] that can be applied to repeated analyses. Include profiling, missing value handling, outlier strategy, normalization rules, and audit trail requirements. Output in [format].
6. Identify Missing Values and Imputation Strategy: For dataset [dataset], classify missing values by mechanism (MCAR, MAR, MNAR). Propose imputation strategies for numeric and categorical fields, with rationale and impact on bias. Include a sensitivity note and fallback plan. Output in [format].
7. Detect Outliers and Handling Plan: Identify potential outliers in [dataset]. Distinguish errors from true rare events. Propose handling options (capping, winsorizing, transformation, exclusion) with justification. Provide before/after summary in [format].
8. Standardize Data Types and Units: Review all columns in [dataset] for type inconsistencies and unit mismatches. Propose a standard schema, create a migration plan and a mapping table. Output in [format].
9. Create a Data Dictionary: Generate a data dictionary for [dataset], including column name, data type, allowed values, meaning, source, and quality notes. Provide machine-readable and human-readable versions in [format].
10. Initial Exploratory Data Analysis Plan: Draft an EDA plan for [dataset], outlining hypotheses, key variables to explore, and visuals to produce. Include schedule, success criteria, and risk flags. Output in [format].
11. Descriptive Statistics Summary: Compute descriptive statistics (mean, median, mode, std dev, min, max, quartiles) for [dataset] and stratify by [group]. Present results in [format] with interpretation notes.
12. Distributions by Segment: For [dataset], produce distribution analyses of key variables [variables] across segments defined by [segment]. Include histograms, box plots, density plots. Summarize findings in [format].
13. Group Comparison Tests: Plan to compare groups in [dataset] on [outcome]. Determine appropriate tests (t-test, ANOVA, nonparametric) based on distributions. Include effect sizes and assumptions checks. Output in [format].
14. Correlation and Covariance Analysis: Compute correlations among [variables] in [dataset]. Highlight strong associations, multicollinearity risks. Output a correlation matrix and narrative in [format].
15. Time Series Trend Detection: If [dataset] includes time data, detect trends with moving averages, decomposition, and seasonality checks. Provide visuals and a narrative describing trend direction. Output in [format].
16. Seasonal Decomposition Prep: Prepare data for seasonal decomposition on [dataset] by confirming frequency, handling missing periods, and choosing a decomposition method. Provide plan and sample result in [format].
17. Missing Data Estimation Using Models: Experiment with simple imputation models (regression, kNN) for missing values in [dataset]. Compare against mean/median imputation, report accuracy, note limitations. Output in [format].
18. Feature Engineering Plan: Propose feature engineering plan for modeling on [dataset]. List candidate features, transformations, interactions, and rationale. Include how to validate new features with a pilot model. Output in [format].
19. Identify Potential Causal Relationships: Outline plan to explore potential causal relationships in [dataset] using controlled comparisons, instrumental variables, or quasi-experimental designs. State assumptions, limitations, and data needs. Output in [format].
20. Baseline Model Evaluation Plan: Create a plan to establish a baseline model for [dataset], including model types, evaluation metrics, cross-validation, and stopping criteria. Provide a template for reporting results in [format].
21. Data Visualization Storyboard: Develop a visualization storyboard for communicating insights from [dataset] to non-technical stakeholders. Include 3–5 visuals, captions, and a short narrative. Output in [format].
22. Insight Narrative Template: Draft a concise insight narrative for [dataset], focusing on 3 actionable takeaways. Include data-backed evidence, caveats, and recommended actions. Output in [format].
23. Data Quality Assurance Plan: Create a QA plan to ensure ongoing data quality for analyses on [dataset], including monitoring checks, alert thresholds, and review cadence. Output in [format].
24. Data Provenance and Audit Trail: Define a data provenance approach for [dataset], detailing how data is collected, transformed, and stored. Include reproducibility checklist and audit log requirements. Output in [format].
25. Data Pipeline Reproducibility: Document steps to reproduce the analysis from raw data to results in [dataset], including environment, libraries, and versioning. Provide a runnable notebook template in [format].
26. KPI Alignment with Business Objectives: Map analysis goals to business KPIs. For dataset [dataset], align each KPI with data sources and calculations, and propose dashboards to monitor them. Output in [format].
27. Reproducible Analysis Notebook: Create a fully reproducible analysis notebook for [dataset], including data loading, cleaning, EDA, modeling, and reporting cells. Ensure outputs are deterministic. Output in [format].
28. Benchmark Dataset Comparison: Compare [dataset] against a benchmark dataset [benchmark] on key metrics. Show differences, explain causes, and propose actions. Output in [format].
29. Validate Data Transformations: Audit all data transformations applied to [dataset]. Verify input-output mappings, check for data leakage, and document validation results. Output in [format].
30. Sensitivity Analysis Plan: Design a sensitivity analysis to test how changes in [assumptions] affect conclusions from [dataset]. Define scenarios, parameters, and interpretation rules. Output in [format].
31. Multivariate Visualization: Create 3–5 multivariate visualizations (scatter matrices, parallel coordinates) for [dataset]. Explain what each reveals about relationships among [variables]. Output in [format].
32. Interaction Effects Exploration: Investigate potential interaction effects between [feature A] and [feature B] on [outcome] in [dataset]. Provide plots and a brief interpretation. Output in [format].
33. Hypothesis Testing Plan: Draft a hypothesis testing plan for [dataset], including null/alternative hypotheses, test selection, significance level, and power considerations. Include a decision rule and reporting template. Output in [format].
34. Confidence Intervals and Effect Sizes: Compute confidence intervals and effect sizes for key comparisons in [dataset]. Interpret practical significance and report results with visual aids. Output in [format].
35. Model-Agnostic Explanation Plan: Outline a plan to explain model predictions for [dataset] using SHAP/Permutation methods. Include explanation scope, audience, and limitations. Output in [format].
36. Dash-ready Data Summary: Create a concise, dashboard-ready data summary for [dataset], highlighting key metrics, trends, and top insights. Include a one-page digest and a data appendix in [format].
37. User-Centric Data Storytelling: Prepare a data story for stakeholders in the [audience] describing insights from [dataset]. Include user personas, pain points, and recommended actions. Output in [format].
38. Stakeholder-friendly Summary Dashboard: Design a stakeholder dashboard summary for [dataset] that emphasizes action items over raw numbers. Provide layout, KPIs, and narrative annotations. Output in [format].
39. Promote Data-Driven Decision Making: Craft a plan to advocate for data-driven decisions using findings from [dataset]. Include talking points, recommended actions, and risk considerations. Output in [format].
40. Anomaly Detection Plan: Develop an anomaly detection plan for [dataset], including detection methods, alert thresholds, and remediation steps. Provide example alerts and a testing plan in [format].
41. Identify Data Gaps and Assumptions: List data gaps and underlying assumptions in the analysis of [dataset]. Propose data collection or alternative approaches to mitigate risk. Output in [format].
42. Normalization and Scaling Strategy: Propose normalization and scaling rules for numeric features in [dataset], specifying when to use which method and how to preserve interpretability. Output in [format].
43. Dimensionality Reduction Plan: Plan a dimensionality reduction approach for [dataset], selecting methods (PCA, t-SNE, UMAP) based on data characteristics. Include visualization plans. Output in [format].
44. Feature Importance Evaluation: Evaluate feature importance for [dataset] using multiple methods (tree-based, SHAP, permutation). Provide a consensus ranking and actionable insights. Output in [format].
45. Model Selection Criteria: Define criteria to select the best model type for predicting [outcome] in [dataset], including performance, interpretability, and deployment constraints. Output in [format].
46. Cross-Validation Strategy: Design a cross-validation strategy for [dataset], detailing folds, shuffling, and stratification rules. Provide a template to reproduce results in [format].
47. Overfitting and Underfitting Checks: Create checks to detect overfitting/underfitting in models built on [dataset], with remediation steps. Include plots and metrics in [format].
48. Accessibility in Data Visualizations: Audit visualizations for accessibility (color contrast, alt text, keyboard navigation) in analyses of [dataset]. Provide fixes and a checklist in [format].
49. Regional or Segment Analysis: Perform regional or segment analysis on [dataset], comparing metrics across [regions/segments]. Include visuals and interpretation notes in [format].
50. Attribution Analysis Setup: Set up an attribution analysis to determine which channels or touchpoints drive outcomes in [dataset]. Outline data requirements and a reporting plan in [format].
51. Product Metrics Deep Dive: Deep-dive into product metrics from [dataset], such as usage, engagement, or retention. Provide insights, hypotheses, and recommended actions in [format].
52. Customer Segmentation Analysis: Cluster customers in [dataset] and profile segments by key behaviors. Validate clusters and propose targeting strategies in [format].
53. Retention and Churn Analysis Plan: Plan a churn/retention analysis for [dataset], including cohort definitions, survival analysis options, and actionable retention levers. Output in [format].
54. Price Elasticity Estimation Setup: Estimate price elasticity using [dataset], specify model, interpret coefficients, and translate into pricing recommendations. Output in [format].
55. Forecast Accuracy Evaluation: Evaluate forecast accuracy for [time series dataset], comparing baseline vs enhanced models. Report MAE/MAPE/CRPS and calibration plots in [format].
56. Scenario Analysis Prompts: Create scenario analysis prompts for [dataset], outlining best-case, worst-case, and baseline scenarios with probabilistic ranges. Output in [format].
57. Data-Driven Experiment Design: Design a data-driven experiment for [business goal] using [dataset], detailing control/treatment, sample size, randomization, and success criteria in [format].
58. A/B Test Data Preparation Guide: Prepare data for an A/B test in [dataset], including cohort definitions, masking, and pre/post period alignment. Provide a data preparation script in [format].
59. Experimentation Validity Check: Assess internal validity of experiments in [dataset], listing threats to validity and mitigation steps. Output in [format].
60. Sampling Strategy for Analysis: Define a sampling strategy for analysis on [dataset], including sample size, stratification, and weighting. Provide a sampling protocol in [format].
61. Bootstrapping Plan: Outline a bootstrapping plan for estimating confidence intervals in [dataset], with code snippets and interpretation guidance in [format].
62. Bayesian vs Frequentist Considerations: Compare Bayesian and frequentist approaches for analyzing [dataset], including priors, posteriors, and decision rules. Output in [format].
63. Data Governance and Privacy: Assess governance and privacy considerations for analyses on [dataset], including data access controls, anonymization, and compliance. Output in [format].
64. Compliance and Ethical Analysis Prompts: Ensure analyses on [dataset] meet ethical guidelines and regulatory requirements. Provide a compliance checklist with references in [format].
65. Metadata Documentation: Document metadata for [dataset], including lineage, definitions, and change history. Provide machine-readable and human-readable versions in [format].
66. Visualization Best Practices: Summarize best practices for creating clear, honest data visuals for [dataset], including color, labeling, and narration guidelines. Output in [format].
67. Macro-to-Micro Insight Translation: Translate high-level insights from [dataset] into actionable micro-tasks for front-line teams. Provide an implementation plan in [format].
68. Data Story Quality Checklist: Create a quality checklist for data stories from [dataset] covering clarity, rigor, relevance, and actionability. Output in [format].
69. Insight Prioritization Framework: Develop a framework to rank insights from [dataset] by impact, feasibility, and risk. Apply the framework to a sample finding and report in [format].
70. Actionable Recommendations Framing: Frame 3 actionable recommendations based on findings from [dataset], with rationale, owners, and success metrics. Output in [format].
71. Risk and Uncertainty Communication: Prepare a brief communicating risk and uncertainty around key conclusions from [dataset], including caveats and probability ranges. Output in [format].
72. Business Impact Estimation: Estimate business impact for recommended actions from [dataset], including potential revenue, cost savings, or efficiency gains. Provide a calculator template in [format].
73. ROI Calculation Prompts: Calculate ROI for a proposed data-driven initiative using [dataset], including inputs, assumptions, and a sensitivity table. Output in [format].
74. Data-Driven Roadmap Outline: Draft a 12-month analytics roadmap for the domain represented by [dataset], with milestones, metrics, and resource needs. Output in [format].
75. Scenario Planning Visuals: Create visuals for scenario planning based on [dataset], showing best/worst-case outcomes and decision triggers in [format].
76. Data Analysis Quality Metrics: Define quality metrics for analytics on [dataset], including data quality, process quality, and output quality. Provide a dashboard-ready report in [format].
77. Reproducibility Audit Checklist: Generate a reproducibility audit checklist for analyses on [dataset], covering data, code, environment, and results traceability in [format].
78. Data Output Format Standards: Specify standards for data outputs from analyses on [dataset], including file formats, naming conventions, and delivery templates in [format].
79. Export Templates for Stakeholders: Create export templates for stakeholders summarizing findings from [dataset], tailored to roles (executive, analyst, engineer). Output in [format].
80. Automated Report Generation Prompt: Design a prompt to generate automated reports from [dataset], including freshness cadence, visuals, and executive summary. Output in [format].
81. Dashboard Narrative Annotations: Add narrative annotations to dashboard visuals for [dataset], explaining trends, caveats, and recommended actions. Output in [format].
82. Data Export Validation Rules: Define validation rules for data exports from analyses on [dataset], including row/column checks and file integrity tests. Output in [format].
83. Data Anomaly Labeling Convention: Create a labeling convention for anomalies detected in [dataset], including thresholds, definitions, and labeling schema. Output in [format].
84. EDA Cheatsheet: Produce a concise EDA cheatsheet for [dataset], listing quick checks, plots, and decision rules. Output in [format].
85. Data Cleaning Script Template: Provide a reusable data cleaning script template for [dataset], with modular functions for missing values, outliers, and type casting. Output in [format].
86. Statistical Process Control Prompts: Apply SPC concepts to [dataset] to monitor process stability. Define control charts, thresholds, and action rules. Output in [format].
87. Data Analysis for Sales Funnel: Analyze the sales funnel data in [dataset], identify leak points, and suggest optimizations. Provide visuals and a narrative in [format].
88. Data Analysis for Marketing Attribution: Assess attribution in [dataset], compare models (last touch, multi-touch), and recommend a preferred attribution approach with caveats. Output in [format].
89. Data Analytics for Supply Chain: Analyze supply chain data in [dataset], focusing on lead times, variability, and inventory levels. Propose optimization insights and dashboards in [format].
90. Data Analysis for Product Analytics: Examine product usage data in [dataset], identify engagement drivers, and suggest feature experiments with expected outcomes in [format].
91. Data Analysis for Finance: Perform a financial data analysis on [dataset], including revenue, cost, and profitability metrics. Provide risk flags and governance notes in [format].
92. Data Analysis for HR Analytics: Analyze HR data in [dataset], focusing on turnover, hiring pipelines, and workforce planning. Deliver insights and recommended actions in [format].
93. Data Analysis for Healthcare Analytics: Inspect healthcare data in [dataset], ensuring privacy, and extract clinical and operational insights with appropriate caveats in [format].
94. Data Analysis for Education Analytics: Assess student performance data in [dataset], identify predictors of success, and propose interventions with impact estimates in [format].
95. Data Analysis for Social Science: Explore social science data in [dataset], test hypotheses, and discuss limitations and policy implications in [format].
96. Data Analysis in Python or R Guidance: Provide concise executable guidance for performing the above analyses in [Python/R], including libraries, sample code snippets, and troubleshooting notes in [format].
97. Data Analysis with Excel PowerTools: Outline a data analysis workflow using Excel PowerTools for [dataset], including data cleaning, modeling, and visualization steps in [format].
98. Data Visualization Tools and Libraries Prompt: Recommend visualization tools for [dataset], with rationale for each library, chart types, and accessibility considerations in [format].
99. Data Storyboard to Executive Summary: Convert a data storyboard created from [dataset] into an executive summary tailored to decision-makers. Include visuals, key insights, and recommended actions in [format].
100. Final Deliverables Checklist and Handover: Prepare a final deliverables package for [dataset], including data artifacts, code, visuals, and a summary deck. Provide a handover checklist and acceptance criteria in [format].

Best Practices

Keep prompts concrete, modular, and reusable. Use placeholders that map to your data and business goals. Validate outputs against dashboards or business KPIs, and document assumptions. Maintain versioning for data, code, and prompts to ensure reproducibility.

Common Mistakes to Avoid

Avoid vague objectives, missing data provenance, overfitting in modeling prompts, and delivering outputs without interpretation or business context. Do not assume data quality without checks, and avoid asking for impossible data access constraints.

Related resources

Use these related resources to connect this Claude prompt library with practical AI workflows, implementation examples, blog analysis, and business use cases.

• AI Prompts Library
• Claude Prompts
• AI workflow simulator
• Cross-model AI workflows with Claude
• Claude Excel analysis prompts
• Claude business intelligence prompts
• Why analytics products need metric definitions
• Xero reports and business performance insights
• QuickBooks reports and management dashboards

FAQ

What is this page?

It is a Claude prompts library for Data Analysis with 100 copyable prompts designed for practical analytics work.

How do I use the prompts?

Replace placeholders like [dataset], [variables], and [format], then run, verify outputs, and incorporate results into dashboards or reports.

Are these prompts reusable for different datasets?

Yes. Prompts are designed with placeholders so you can adapt them to any dataset that fits the described task.

Can I contribute more prompts?

Yes. You can submit feedback with concrete prompts to extend the library and improve coverage.

Do these prompts assume a specific toolset?

Prompts are written to be tool-agnostic while mentioning common tools. Replace with your preferred environment if needed.