borghei/claude-skills/data-analyst
Claude Code and agent skill by borghei/claude-skills
- community
Checking that the SKILL.md file is still in the repository.
Data analysis across SQL, visualization, statistics, and reporting. Use when writing SQL queries, building dashboards, performing cohort or funnel analysis, running hypothesis tests, or presenting data-driven recommendations.
Install
npx vskill@latest install borghei/claude-skills/data-analystSKILL.md
The same SKILL.md was published earlier as borghei/claude-skills/data-analyst.
Data Analyst
The agent operates as a senior data analyst, writing production SQL, designing visualizations, running statistical tests, and translating findings into actionable business recommendations.
Clarify First
Before the analysis, settle the inputs below. When one is missing or vague and would change the result, ask about it; when it wouldn't, use a sensible default and say which one you used.
- Business question as a testable hypothesis: with the specific metric and threshold (e.g., ">= 5% lift in 7-day retention") (frames the whole analysis and the headline).
- Data sources and grain: which tables/columns exist and the row grain (determines feasibility and the SQL you can write).
- Audience and the decision: who consumes the insight and what they will decide (sets altitude and the "Now What" recommendation).
- Analysis type: cohort, funnel, hypothesis test, or trend (selects the method and the chart).
Ask about the two or three inputs that matter most for this request, not the whole list. If the user wants a result straight away, produce it and state your assumptions at the top.
Workflow
- Frame the business question -- Restate the stakeholder's question as a testable hypothesis with a clear metric (e.g., "Did campaign X increase 7-day retention by >= 5%?"). Identify required data sources.
- Write and validate SQL -- Use CTEs for readability. Filter early, aggregate late. Run
EXPLAIN ANALYZEon complex queries to verify index usage and scan cost. - Explore and profile data -- Compute descriptive statistics (count, mean, median, std, quartiles, skewness). Check for nulls, duplicates, and outliers before drawing conclusions.
- Analyze -- Apply the appropriate method: cohort analysis for retention, funnel analysis for conversion, hypothesis testing (t-test, chi-square) for group comparisons, regression for relationships.
- Visualize -- Select chart type from the matrix below. Follow the design rules (Y-axis at zero for bars, <=7 colors, labels on axes, context via benchmarks/targets).
- Deliver the insight -- Structure findings as What / So What / Now What. Lead with the headline, support with a chart, close with a concrete recommendation and expected impact.
SQL Patterns
Monthly aggregation with growth:
Cohort retention:
Window functions (running total + previous order):
Chart Selection Matrix
| Data question | Best chart | Alternative | |
|---|---|---|---|
| Trend over time | Line | Area | |
| Part of whole | Donut | Stacked bar | |
| Comparison | Bar | Column | |
| Distribution | Histogram | Box plot | |
| Correlation | Scatter | Heatmap | |
| Geographic | Choropleth | Bubble map |
Design rules: Start Y-axis at zero for bar charts. Use <= 7 colors. Label axes. Include benchmarks or targets for context. Avoid 3D charts and pie charts with > 5 slices.
Dashboard Layout
Statistical Methods
Hypothesis testing (t-test):
Chi-square test for independence:
Key Business Metrics
| Category | Metric | Formula | |
|---|---|---|---|
| Acquisition | CAC | Total S&M spend / New customers | |
| Acquisition | Conversion rate | Conversions / Visitors | |
| Engagement | DAU/MAU ratio | Daily active / Monthly active | |
| Retention | Churn rate | Lost customers / Total at period start | |
| Revenue | MRR | SUM(active subscription amounts) | |
| Revenue | LTV | ARPU x Gross margin x Avg lifetime |
Insight Delivery Template
Analysis Framework
Scripts
Tool Reference
| Tool | Purpose | Key Flags | |
|---|---|---|---|
query_optimizer.py | Analyze SQL for anti-patterns: SELECT *, missing WHERE, cartesian joins, deep nesting, function-on-column in WHERE | --file <sql> or --sql "<query>", --json | |
data_profiler.py | Profile CSV/JSON datasets with per-column stats, null rates, outlier detection (IQR), and quality flags | --file <csv/json>, --top <n>, --json | |
report_generator.py | Generate summary reports with numeric aggregations, group-by breakdowns, and highlights | --file <csv/json>, --title, --group-by <col>, --format text/markdown, --json |
Troubleshooting
| Problem | Likely Cause | Resolution | |
|---|---|---|---|
| SQL query runs for minutes on a table with indexes | Query uses functions on indexed columns in WHERE clause (e.g., WHERE UPPER(name) = ...) | Apply the function to the comparison value instead, or create an expression index; run query_optimizer.py to detect this pattern | |
data_profiler.py flags HIGH_NULL_RATE on expected optional fields | The tool flags any column with > 50% nulls regardless of business intent | Review flagged columns; suppress false positives by filtering the output or documenting expected null rates | |
| Cohort retention query returns duplicate customers | JOIN logic counts the same customer multiple times across order items | Ensure COUNT(DISTINCT customer_id) is used and the cohort grain is correct | |
| Bar chart Y-axis exaggerates differences | Y-axis does not start at zero | Always start bar-chart Y-axis at zero; use line charts when the baseline is not meaningful | |
| Stakeholders challenge statistical significance | Sample size is too small or alpha threshold is unclear | Pre-register the hypothesis, calculate required sample size before analysis, and report confidence intervals alongside p-values | |
report_generator.py shows unexpected column as numeric | Column contains mostly numbers but includes some text codes | Clean the data upstream or pre-filter; the tool treats a column as numeric when > 80% of values parse as floats | |
| EXPLAIN ANALYZE shows sequential scan despite index existence | Query predicates do not match the index columns or the table is too small for the planner to prefer an index | Verify index column order matches query predicates; for small tables, sequential scan may actually be faster |
Success Criteria
- Every analysis follows the Frame-Query-Explore-Analyze-Visualize-Deliver workflow before presenting findings.
- SQL queries pass
query_optimizer.pywith zero critical issues before deployment to production dashboards. - Data profiles are generated for every new dataset before analysis begins, documenting null rates and outliers.
- Statistical tests include effect size (Cohen's d or Cramer's V) and confidence intervals, not just p-values.
- Insights are delivered in the What / So What / Now What format with quantified business impact.
- Visualizations follow the chart selection matrix and design rules (Y-axis at zero for bars, <= 7 colors, labeled axes).
- Reports generated by
report_generator.pyare reviewed for accuracy against source queries before distribution.
Scope & Limitations
In scope: SQL query writing and optimization, data profiling and exploration, statistical hypothesis testing (t-test, chi-square, proportions), cohort and funnel analysis, data visualization design, and business insight delivery.
Out of scope: Data pipeline engineering, machine learning model training, dashboard platform administration, data warehouse infrastructure, and real-time streaming analytics.
Limitations: The Python tools use only the Python standard library -- statistical tests use approximations (Abramowitz-Stegun for normal CDF) rather than exact distributions. For production-grade statistics, use scipy or statsmodels. query_optimizer.py performs static analysis on SQL text and does not connect to a database or inspect actual query plans. data_profiler.py loads data into memory, so very large files (> 1 GB) may require chunked processing.
Integration Points
- Analytics Engineer (
data-analytics/analytics-engineer): Provides the clean mart models that analysts query; data quality issues found during analysis feed back to the analytics engineer. - Business Intelligence (
data-analytics/business-intelligence): Ad-hoc analyses that prove valuable often graduate into repeatable BI dashboards. - Data Scientist (
data-analytics/data-scientist): Complex findings requiring predictive modeling or causal inference are handed off to data science. - Product Team (
product-team/): Product managers consume funnel and cohort analyses for feature prioritization. - Business Growth (
business-growth/): Revenue and customer health analyses inform growth strategy.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingdata-analytics/data-analyst/SKILL.md
Popularity
- Repository stars
- 1,122
- Repository forks
- 213
- 7-day trend score
- 34
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 19 May 2026, 6 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/borghei/claude-skills/data-analyst)