Data Question Analyzer
Answer data questions ranging from quick lookups to formal analytical reports
Someone in leadership asks 'why did conversions drop last Tuesday?' and what should be a 10-minute answer turns into a 3-hour investigation across multiple dashboards, data sources, and Slack threads.
Who it's for: data analysts fielding ad-hoc questions from leadership, BI teams supporting business stakeholders, product analysts investigating metric changes, revenue analysts preparing reports, anyone who gets data questions that range from simple to deeply complex
Example
"Why did our signup rate drop 15% last week?" → Question scoped, relevant data gathered and validated, multi-dimensional analysis performed (by channel, device, geography), root cause identified, and findings presented at the right level of detail
CLAUDE.md Template
New here? 3-minute setup guide → | Already set up? Copy the template below.
npx ccplaybooks add data-question-analyzer# Answer Data Questions
Answer a data question, from a quick lookup to a full analysis to a formal report.
## Usage
Provide a natural language question about your data.
## Workflow
### 1. Understand the Question
Get new playbooks like this one
One email a week with new Claude Code workflows. Free, like everything here.
No spam. Unsubscribe anytime.
What This Does
Helps you answer data questions of any complexity -- from quick metric lookups to multi-dimensional trend analyses to formal reports for stakeholders. The assistant understands your question, gathers and validates data, performs the analysis, and presents findings in the appropriate format.
Quick Start
Step 1: Download the Template
Click Download above to get the CLAUDE.md file.
Step 2: Set Up Your Project
Create a project folder and place the template inside:
my-data-project/
├── CLAUDE.md
├── data/ # Place CSV/Excel files here
└── output/ # Analysis results go here
Step 3: Start Working
claude
Say: "How many new users signed up in December?"
How It Determines Complexity
The assistant automatically classifies your question into one of three levels:
- Quick answer: Single metric, simple filter, factual lookup
- Full analysis: Multi-dimensional exploration, trend analysis, comparison
- Formal report: Comprehensive investigation with methodology, caveats, and recommendations
Each level produces progressively more detailed output, from a single number to a full report with executive summary and recommendations.
Validation Checks
Before presenting any results, the assistant runs through these 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?
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, the assistant may break them into multiple queries
- Results are always validated before presentation -- if something looks off, it will be flagged
Example Prompts
"How many new users signed up in December?"
"What's causing the increase in support ticket volume over the past 3 months? Break down by category and priority."
"Prepare a data quality assessment of our customer table -- completeness, consistency, and any issues we should address."