Skip to content
alyn

Best Claude skills for data analysis

Data skills help your agent clean messy files, write SQL, build charts and explain what the numbers mean. The strongest ones force the agent to compute with code rather than estimate in prose, which is where most AI analysis goes wrong.

209 data analysis skills · ranked live · November 2026

The top 10. Ranked by the Alyn Score.

  1. Anthropic

    Skills

    #1
    Anthropic

    Xlsx

    Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or…

    Pack192k3.8MScore 91
    Details
  2. Corey Haines

    Marketingskills

    #2
    Corey Haines

    Conversion Tracking

    When the user wants to set up, audit, or fix conversion tracking to Google Ads, Meta, GA4, LinkedIn, and TikTok, or asks why conversions are missing or doubled: GTM, pixels, CAPI, Enhanced…

    Pack60k6.3MScore 90
    Details
  3. Corey Haines

    Marketingskills

    #3
    Corey Haines

    Ab Testing

    When the user wants to plan, run, or read A/B tests, or asks a judgement call on one: is the result real, can we stop, which version won, is this worth testing at all: sample size…

    Pack60k6.3MScore 88
    Details
  4. Corey Haines

    Marketingskills

    #4
    Corey Haines

    Analytics

    When the user wants to set up or audit analytics, or asks whether a metric or number is calculated right, what to track, or how to name events: tracking plans, GA4, GTM, Mixpanel, PostHog…

    Pack60k6.3MScore 88
    Details
  5. wshobson

    Agents

    #5
    wshobson

    Kpi Dashboard Design

    Design effective KPI dashboards with metrics selection, visualization best practices, and real-time monitoring patterns. Use this skill when building an executive SaaS metrics dashboard…

    Pack42k2.6MScore 84
    Details
  6. #6
    Yuan1z0825

    Nature Figure

    Create, revise, audit, and export manuscript scientific figures in Python or R. Use for 论文配图、科研绘图、多面板图 and submission-ready plots, or explicitly requested AI-generated graphical abstracts…

    Pack53k301kScore 84
    Details
  7. sickn33

    Agentic Awesome Skills

    #7
    sickn33

    Ab Testing

    When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program.

    Pack49k584kScore 83
    Details
  8. sickn33

    Agentic Awesome Skills

    #8
    sickn33

    Accounting Software Selection

    Scores shortlisted accounting packages against 57 evidence-backed fields, emitted as CSV, SQL, JSON Schema or Notion on request. Use for choosing accounting software.

    Pack49k584kScore 83
    Details
  9. Google

    Skills

    #9
    Google

    Agent Platform Alert Configuration

    Configures best-practice alerting policies for AI agents using OpenTelemetry (OTel) metrics, generating output as Terraform (.tf) configuration files. Use when analyzing, writing, or…

    Pack24k1.1MScore 83
    Details
  10. #10
    Yuan1z0825

    Nature Statistics

    Audit or improve manuscript statistical reporting, including experimental units, replication, uncertainty, tests, and figure statistics. Use for 统计审查、统计方法小节、图注统计 and reviewer concerns…

    Pack53k301kScore 82
    Details

What makes a great data analysis skill.

  • Code-first analysis: pandas, SQL or spreadsheets, never mental math.

  • Checks for data quality before conclusions.

  • Chart guidance so outputs are readable, not decorative.

All 209 data analysis skills.

Microsoft

Skills For Fabric

62
Microsoft

sqldw-cli

Manage Fabric Warehouse, Lakehouse SQL endpoints, and Mirrored Databases: DDL/DML, COPY INTO, read-only T-SQL, Query Insights diagnostics, and Capacity Metrics CU-spike correlation. Synapse…

Pack1.3k8.1kData analysis

Microsoft

Skills For Fabric

60
Microsoft

e2e-medallion-architecture

Plans and builds end-to-end Fabric data platforms on the Bronze, Silver, and Gold medallion pattern: ingestion to analytics, PySpark and Delta layers, pipeline orchestration, per-layer…

Pack1.3k8.1kCoding

OpenClaudia

Openclaudia Skills

60
OpenClaudia

glasser-research

Use Glasser to retrieve live marketing data through one prepaid account when a task needs SERPs, keyword metrics, ad libraries, community posts, company data, or another external API and no…

Pack73734kResearch

kostja94

Marketing Skills

60
kostja94

traffic-analysis

Compatibility pointer for source, UTM and direct-traffic analysis; maintained in Open Analytics.

Pack1.1k231kMarketing

databricks

Databricks Agent Skills

59
databricks

databricks-dbsql

Databricks SQL (DBSQL) advanced features and SQL warehouse capabilities. This skill MUST be invoked when the user mentions: "DBSQL", "Databricks SQL", "SQL warehouse", "SQL scripting"…

Pack39417kData analysis

databricks

Databricks Agent Skills

59
databricks

databricks-execution-compute

Execute code and manage compute on Databricks: run Python/Scala/SQL/R via serverless, classic, or interactive clusters, and create/resize/delete clusters and SQL warehouses.

Pack39417kData analysis

databricks

Databricks Agent Skills

59
databricks

databricks-metric-views

Unity Catalog metric views: define, create, query, and manage governed business metrics in YAML. Use when building standardized KPIs, revenue metrics, order analytics, or any reusable…

Pack39417kData analysis

Aperivue

Medsci Skills

59
Aperivue

find-cohort-gap

Use when looking for research topics a longitudinal cohort database can answer (NHIS, UK Biobank, an institutional EMR or registry). Profiles the cohort, matches PI expertise, scans…

Pack3766.8kData analysis

OpenClaudia

Openclaudia Skills

59
OpenClaudia

github-stars

Show a GitHub repo's star growth as CLI charts — by day and by hour, in any timezone. Use when the user asks to "check GitHub stars", "stars by hour/day for ", "star growth", "how many…

Pack73734kMarketing
59
petrkindlmann

qa-metrics

Define, track, and act on QA metrics: test coverage percentage, flakiness rate, defect escape rate, MTTR, test execution time trends, automation ROI, quality gates, and SLAs for test…

Pack26170kTesting

Aperivue

Medsci Skills

57
Aperivue

generate-codebook

Use when a tabular dataset (CSV, Excel, Parquet, Stata, SAS) needs a data dictionary. Profiles every variable (type, levels, range, missingness) into codebook.md and codebook.json and flags…

Pack3766.8kResearch
56
jaechang-hits

multipanel

Assemble multiple plots into ONE publication-ready multi-panel journal figure (e.g. Figure 1 with panels A, B, C). Use whenever the user asks to combine, compose, or lay out several plots…

Pack38713kData analysis

sanjay3290

AI Skills

56
sanjay3290

notebooklm

Query and manage Google NotebookLM notebooks with persistent profile auth, source sync, batch/multi queries, and structured exports. Use when user asks to query NotebookLM, 'ask my…

Pack45410kResearch
56
jaechang-hits

omics-plotting

omics-plotting: publication-style figure authoring for omics / bioinformatics results with matplotlib / seaborn. Read this before writing any plotting or figure code in any omics analysis —…

Pack38713kScience
56
jaechang-hits

plotly-interactive-plots

Interactive scientific visualization with Plotly. Two APIs: plotly.express (px) for one-liner DataFrame plots, plotly.graph_objects (go) for trace-level control. 40+ chart types with hover…

Pack38713kData analysis
56
jaechang-hits

plotly-interactive-visualization

Interactive visualization with Plotly. 40+ chart types (scatter, line, heatmap, 3D, geographic) with hover, zoom, pan. Two APIs: Plotly Express (DataFrame) and Graph Objects (fine control)…

Pack38713kScience

sanjay3290

AI Skills

56
sanjay3290

postgres

Execute read-only SQL queries against multiple PostgreSQL databases. Use when: (1) querying PostgreSQL databases, (2) exploring database schemas/tables, (3) running SELECT queries for data…

Pack45410kBackend
56
jaechang-hits

scientific-visualization

Guide for choosing and creating scientific visualizations for publications and talks. Covers chart-type selection by data structure, color theory for accessibility/print, figure…

Pack38713kScience
56
jaechang-hits

seaborn-statistical-plots

Statistical visualization on matplotlib with native pandas support. Auto aggregation, CIs, grouping for distributions (histplot, kdeplot), categorical (boxplot, violinplot), relational…

Pack38713kData analysis
56
jaechang-hits

seaborn-statistical-visualization

Statistical visualization on matplotlib + pandas. Distributions (histplot, kdeplot, violin, box), relational (scatter, line), categorical, regression, correlation heatmaps. Auto…

Pack38713kData analysis
56
jaechang-hits

statistical-significance-annotation

Guide for annotating statistical significance (p-value asterisks) on comparison plots. Covers standard notation (ns, *, **, ***, ****), matplotlib bracket+asterisk implementation, and use…

Pack38713kData analysis
56
jaechang-hits

statsmodels-statistical-modeling

Python statistical modeling: regression (OLS, WLS, GLM), discrete (Logit, Poisson, NegBin), time series (ARIMA, SARIMAX, VAR), with rigorous inference, diagnostics, and hypothesis tests…

Pack38713kData analysis

Aperivue

Medsci Skills

55
Aperivue

batch-cohort

Use when one validated cohort analysis must be repeated across many exposure/outcome pairs. Generates one R/Python script per combination from a single methodology template, changing only…

Pack3766.8kData analysis

zLanqing

Codex Claude Academic Skills

54
zLanqing

matlab

MATLAB and GNU Octave numerical computing for matrix operations, data analysis, visualization, and scientific computing. Use when writing MATLAB/Octave scripts for linear algebra, signal…

Pack5.9k3.2kScience

zLanqing

Codex Claude Academic Skills

54
zLanqing

scientific-toolkit-skill

Research computing toolkit for optoelectronic information science and engineering, MATLAB/Octave, Python scientific analysis, signal processing, image processing, statistics, simulation…

Pack5.9k3.2kScience

zLanqing

Codex Claude Academic Skills

54
zLanqing

seaborn

Statistical visualization with pandas integration. Use for quick exploration of distributions, relationships, and categorical comparisons with attractive defaults. Best for box plots…

Pack5.9k3.2kScience

zLanqing

Codex Claude Academic Skills

54
zLanqing

statsmodels

Statistical models library for Python. Use when you need specific model classes (OLS, GLM, mixed models, ARIMA) with detailed diagnostics, residuals, and inference. Best for econometrics…

Pack5.9k3.2kScience

zLanqing

Codex Claude Academic Skills

54
zLanqing

xlsx

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file…

Pack5.9k3.2kDocuments

Affitor

Affiliate Skills

53
Affitor

internal-linking-optimizer

Analyze site's internal link structure and optimize for hub-and-spoke SEO architecture. Triggers on: "optimize internal links", "internal linking", "link structure", "hub and spoke links"…

Pack7781.4kMarketing

Data analysis skills, explained.

Also searched as: data analysis skill, excel skill claude, sql skill, analytics agent skills.

What are the best Claude skills for data analysis?

Right now the top-ranked data analysis skills on Alyn are Xlsx (Anthropic), Conversion Tracking (Corey Haines), Ab Testing (Corey Haines). Rankings combine GitHub stars, installs, freshness and depth, and update live.

Is there a Claude skill for Excel?

Yes. Anthropic's xlsx skill creates and edits spreadsheets with formulas, and several community skills cover cleaning and analysis.

Do data skills send my data anywhere?

Skills are instructions and local scripts. Where your data goes depends on the agent you run them in.

How do I install a data analysis skill?

Run npx skills add owner/repo in your project, or copy the folder with SKILL.md into ~/.claude/skills. Every skill on this page has a ready-to-copy command.

Built a data analysis skill? Get it ranked.

Submit a skill