Skill

Official

Pass

Audit score 90

analyze

anthropics/knowledge-work-plugins

Answer data questions from quick lookups to formal analyses using SQL and connected data warehouses.

What is analyze?

The analyze skill lets you ask natural language questions about your data and get answers ranging from simple metric lookups to comprehensive investigations and formal reports. It handles schema exploration, query execution, validation, and presentation of findings across multiple complexity levels.

Execute SQL queries against connected data warehouses to retrieve relevant data
Parse questions to determine complexity level (quick answer, full analysis, or formal report)
Validate results through row count, null checks, magnitude checks, and aggregation logic before presenting
Break down complex multi-dimensional questions into sub-questions and address each systematically
Generate tables, charts, and narrative summaries with methodology and caveats
Support manual data input via CSV, Excel, or query results when no warehouse is connected

How to install analyze

npx skills add https://github.com/anthropics/knowledge-work-plugins --skill analyze

Prerequisites

A connected data warehouse MCP server (optional; can work with manually provided data)
Access to relevant tables and columns in your data schema

Claude Code

Cursor

Windsurf

Cline

How to use analyze

1.Ask your question using /analyze <natural language question>
2.Provide table names if you know them to speed up schema exploration
3.For manual data input, paste query results, upload CSV/Excel, or describe the schema
4.Review the validation checks and caveats Claude flags before accepting results
5.Use follow-up questions to drill deeper into findings

Use cases

Good for

Quick metric lookups like 'How many users signed up last week?'
Trend investigations like 'What's driving the drop in conversion rate?'
Segment comparisons across time periods or categories
Data quality assessments and completeness reviews
Quarterly business reviews and formal stakeholder reports

Who it's for

Data analysts investigating metrics and trends
Business stakeholders preparing reports and reviews
Product managers analyzing user behavior and funnel metrics
Finance teams reviewing business performance

analyze FAQ

What if I don't have a data warehouse connected?

You can still use the skill by providing data manually—paste query results, upload a CSV/Excel file, or describe your schema so Claude can write queries for you to execute.

How does the skill validate results?

It runs checks on row counts, null values, numeric ranges, time series continuity, and aggregation logic to catch unexpected patterns before presenting findings.

Can it handle complex multi-dimensional analyses?

Yes. For complex questions, Claude breaks them into sub-questions, addresses each systematically, and synthesizes findings into a cohesive narrative.

What output formats are supported?

Numbers, tables, charts, narrative summaries, and combinations thereof depending on the question complexity and what best communicates the results.

How do I know which tables to query?

The skill explores your schema automatically if a data warehouse is connected. If not, you can describe your schema or provide table names to help guide the analysis.

Full instructions (SKILL.md)

Source of truth, from anthropics/knowledge-work-plugins.

name: analyze description: Answer data questions -- from quick lookups to full analyses. Use when looking up a single metric, investigating what's driving a trend or drop, comparing segments over time, or preparing a formal data report for stakeholders. argument-hint: "<question>"

/analyze - Answer Data Questions

If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.

Answer a data question, from a quick lookup to a full analysis to a formal report.

Usage

/analyze <natural language question>

Workflow

1. Understand the Question

Parse the user's question and determine:

Complexity level:
- Quick answer: Single metric, simple filter, factual lookup (e.g., "How many users signed up last week?")
- Full analysis: Multi-dimensional exploration, trend analysis, comparison (e.g., "What's driving the drop in conversion rate?")
- Formal report: Comprehensive investigation with methodology, caveats, and recommendations (e.g., "Prepare a quarterly business review of our subscription metrics")
Data requirements: Which tables, metrics, dimensions, and time ranges are needed
Output format: Number, table, chart, narrative, or combination

2. Gather Data

If a data warehouse MCP server is connected:

Explore the schema to find relevant tables and columns
Write SQL query(ies) to extract the needed data
Execute the query and retrieve results
If the query fails, debug and retry (check column names, table references, syntax for the specific dialect)
If results look unexpected, run sanity checks before proceeding

If no data warehouse is connected:

Ask the user to provide data in one of these ways:
- Paste query results directly
- Upload a CSV or Excel file
- Describe the schema so you can write queries for them to run
If writing queries for manual execution, use the sql-queries skill for dialect-specific best practices
Once data is provided, proceed with analysis

3. Analyze

Calculate relevant metrics, aggregations, and comparisons
Identify patterns, trends, outliers, and anomalies
Compare across dimensions (time periods, segments, categories)
For complex analyses, break the problem into sub-questions and address each

4. Validate Before Presenting

Before sharing results, run through validation checks:

Row count sanity: Does the number of records make sense?
Null check: Are there unexpected nulls that could skew results?
Magnitude check: Are the numbers in a reasonable range?
Trend continuity: Do time series have unexpected gaps?
Aggregation logic: Do subtotals sum to totals correctly?

If any check raises concerns, investigate and note caveats.

5. Present Findings

For quick answers:

State the answer directly with relevant context
Include the query used (collapsed or in a code block) for reproducibility

For full analyses:

Lead with the key finding or insight
Support with data tables and/or visualizations
Note methodology and any caveats
Suggest follow-up questions

For formal reports:

Executive summary with key takeaways
Methodology section explaining approach and data sources
Detailed findings with supporting evidence
Caveats, limitations, and data quality notes
Recommendations and suggested next steps

6. Visualize Where Helpful

When a chart would communicate results more effectively than a table:

Use the data-visualization skill to select the right chart type
Generate a Python visualization or build it into an HTML dashboard
Follow visualization best practices for clarity and accuracy

Examples

Quick answer:

/analyze How many new users signed up in December?

Full analysis:

/analyze What's causing the increase in support ticket volume over the past 3 months? Break down by category and priority.

Formal report:

/analyze Prepare a data quality assessment of our customer table -- completeness, consistency, and any issues we should address.

Tips

Be specific about time ranges, segments, or metrics when possible
If you know the table names, mention them to speed up the process
For complex questions, Claude may break them into multiple queries
Results are always validated before presentation -- if something looks off, Claude will flag it