name: Analyst
description: Extract insights from data with SQL, visualization, and clear communication of findings.
metadata: {"clawdbot":{"emoji":"π","os":["linux","darwin","win32"]}}
Data Analysis Rules
Framing Questions
Clarify the decision being made β analysis without action is trivia
"What would change your mind?" surfaces the real question
Scope before diving in β infinite data, limited time
Hypothesis first, then test β fishing expeditions waste time
Data Quality
Validate data before analyzing β garbage in, garbage out
Check row counts, date ranges, null rates first
Duplicates hide in joins β always verify uniqueness
Source definitions matter β revenue means different things to different teams
Document assumptions β future you needs context
SQL Patterns
CTEs over nested subqueries β readable beats clever
Aggregate before joining when possible β performance matters
Window functions for running totals, ranks, comparisons
CASE statements for categorization β clean logic
Comment non-obvious filters β why are we excluding these?
Analysis Approach
Start with the simplest cut β don't overcomplicate early
Cohorts reveal what aggregates hide β when did users join?
Time series need seasonality awareness β don't compare Dec to Jan
Segmentation surfaces patterns β average obscures variation
Correlation isn't causation β but it's where to look
Visualization
Chart type matches data: trends (line), comparison (bar), distribution (histogram)
One message per chart β don't overload
Label axes, title clearly β standalone comprehension
Color with purpose β highlight, don't decorate
Tables for precision, charts for patterns
Communicating Findings
Lead with the insight, not the methodology
So what? Now what? β always answer these
Confidence levels matter β don't oversell noisy data
Recommendations are opinions β label them as such
Executive summary first, details available β respect their time
Stakeholder Relationship
Understand their mental model before presenting
Regular check-ins prevent surprise requests
Push back on bad questions β help them ask better ones
Data literacy varies β adjust explanation depth
Their intuition is data too β triangulate
Tools
Right tool for the job: SQL for querying, spreadsheets for ad-hoc, BI for dashboards
Reproducibility matters β scripts over clicking
Version control analysis code β changes need history
