Best Claude Skills for Data & Analytics (2026)
Data work is where a skill pays for itself fastest. Anthropic’s SQL Queries, Explore Data and Statistical Analysis skills give Claude a repeatable method — profile the table first, check the grain, state the test before running it — instead of improvising a new approach every conversation. Build Dashboard and Data Visualization cover the presentation layer, and Data Storytelling turns a result into a narrative a stakeholder will read.
Engineering-side skills sit beside them: SQL Optimization Patterns and PostgreSQL Table Design for the database, Data Quality Frameworks for validation, Grafana Dashboarding, chDB Datastore for ClickHouse, Jupyter Notebook for analysis you can hand over, and Anthropic’s XLSX skill for spreadsheets.
A skill supplies the method; it still needs the numbers. On BusinessMCP the same skills run against your connected analytics, CRM, Stripe revenue and databases through one hosted MCP endpoint — so “explore our conversion data” means your data, not a sample.
New to skills? Start with our Claude Skills guide, then come back and pick from the list below.
16 data & analytics skills from 6 publishers, listed alphabetically. 46 of their 48 skills.sh security audits are a pass and none is a fail; 3 ship scripts, flagged on their pages. How we vet skills
| Skill | Publisher | Licence | Audits |
|---|---|---|---|
| Build Dashboard | anthropics | Apache-2.0 | 3/3 pass |
| Business Pulse | anthropics | Apache-2.0 | 2/3 pass |
| chDB Datastore | clickhouse | Apache-2.0 | 3/3 pass |
| Data Quality Frameworks | wshobson | MIT | 3/3 pass |
| Data Storytelling | wshobson | MIT | 3/3 pass |
| Data Visualization | anthropics | Apache-2.0 | 3/3 pass |
| Explore Data | anthropics | Apache-2.0 | 3/3 pass |
| Grafana Dashboarding | grafana | Apache-2.0 | 3/3 pass |
| Jupyter Notebook | openai | Apache-2.0 | 3/3 pass |
| Marketing Analytics | coreyhaines31 | MIT | 3/3 pass |
| Marketing Attribution | coreyhaines31 | MIT | 3/3 pass |
| PostgreSQL Table Design | wshobson | MIT | 3/3 pass |
| SQL Optimization Patterns | wshobson | MIT | 3/3 pass |
| SQL Queries | anthropics | Apache-2.0 | 3/3 pass |
| Statistical Analysis | anthropics | Apache-2.0 | 3/3 pass |
XLSX
anthropics
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 .tsv file (e.g., adding columns,…
Data Visualization
anthropics
Create effective data visualizations with Python (matplotlib, seaborn, plotly). Use when building charts, choosing the right chart type for a dataset, creating publication-quality figures, or applying design principles…
Build Dashboard
anthropics
Build an interactive HTML dashboard with charts, filters, and tables. Use when creating an executive overview with KPI cards, turning query results into a shareable self-contained report, building a team monitoring…
Explore Data
anthropics
Profile and explore a dataset to understand its shape, quality, and patterns. Use when encountering a new table or file, checking null rates and column distributions, spotting data quality issues like duplicates or…
Statistical Analysis
anthropics
Apply statistical methods including descriptive stats, trend analysis, outlier detection, and hypothesis testing.
SQL Queries
anthropics
Write correct, performant SQL across all major data warehouse dialects (Snowflake, BigQuery, Databricks, PostgreSQL, etc.).
SQL Optimization Patterns
wshobson
Master SQL query optimization, indexing strategies, and EXPLAIN analysis to dramatically improve database performance and eliminate slow queries.
Data Storytelling
wshobson
Transform data into compelling narratives using visualization, context, and persuasive structure. Use when presenting analytics to stakeholders, creating data reports, or building executive presentations.
Data Quality Frameworks
wshobson
Implement data quality validation with Great Expectations, dbt tests, and data contracts. Use when building data quality pipelines, implementing validation rules, or establishing data contracts.
PostgreSQL Table Design
wshobson
Use this skill when designing or reviewing a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features
Grafana Dashboarding
grafana
Build, modify, and ship Grafana dashboards as JSON via the HTTP API — panel types (timeseries / stat / gauge / table / heatmap / logs / traces / node-graph), `gridPos` 24-column layout, units, thresholds, template +…
chDB Datastore
clickhouse
Use when the user has tabular data (pandas DataFrame, parquet, csv, Arrow, json) and wants to filter, group, aggregate, join, or speed up slow pandas.
Jupyter Notebook
openai
Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials;
Marketing Analytics
coreyhaines31
When the user wants to set up, improve, or audit analytics tracking and measurement.
Marketing Attribution
coreyhaines31
When the user wants to figure out which marketing actually drives conversions and revenue, choose or interpret an attribution model, or reconcile conflicting numbers across tools.
Business Pulse
anthropics
Produces a one-page cross-functional business snapshot for SMB owners — cash position (the ledger: MYOB, NetSuite, QuickBooks, Xero, or Zoho Books), sales trend (PayPal/Square/Stripe), pipeline movement (HubSpot), this…
Run data & analytics skills on your own data
Open any skill above and press “Use in BusinessMCP” to import it after a free signup.
Get started freeFrequently asked questions
Should I use a skill or an MCP server for analytics?
Both, for different jobs. An MCP server gives the agent live access to your data; a skill packages the analysis method it should apply. BusinessMCP’s hosted endpoint covers the data side out of the box, and imported skills supply the method.
Which data skill should I start with?
Explore Data if you are handed an unfamiliar dataset, SQL Queries if the work is mostly querying a warehouse, and Statistical Analysis once you need to say whether a difference is real. Add Data Storytelling when the output is for someone else.