Chatgpt-skills data-storyteller

Analyze datasets and turn them into narrative reports with charts, audits, comparisons, and statistical summaries. Use for exploratory analysis and executive-ready outputs.

install

source · Clone the upstream repo

git clone https://github.com/dkyazzentwatwa/chatgpt-skills

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/dkyazzentwatwa/chatgpt-skills "$T" && mkdir -p ~/.claude/skills && cp -r "$T/data-storyteller" ~/.claude/skills/dkyazzentwatwa-chatgpt-skills-data-storyteller && rm -rf "$T"

manifest: data-storyteller/SKILL.md

source content

Data Storyteller

Use this as the primary analytics skill for structured data. It now absorbs the repo's audit, comparison, statistics, pivot, experiment, and time-series helpers.

Use This For

Executive summaries and narrative reports from CSV or spreadsheet data
Data quality audits, comparisons, and anomaly reviews
Statistical analysis, pivots, experiment reads, ROI and budget analysis
Survey summaries and time-series decomposition

Workflow

Profile the dataset shape, column types, and missing-value risk.
Pick the smallest useful analysis path instead of running every script by default.
Start with
```
scripts/data_storyteller.py
```
when the user wants a cohesive report.

Reach for focused helpers when the task is narrow:

```
data_quality_auditor.py
```
```
dataset_comparer.py
```
```
correlation_explorer.py
```
```
outlier_detective.py
```
```
statistical_analyzer.py
```
```
survey_analyzer.py
```
```
ts_decomposer.py
```
```
pivot_table_generator.py
```
```
ab_test_calc.py
```
```
roi_calculator.py
```
```
budget_analyzer.py
```

Translate outputs into plain-English findings, risks, and next actions.

Guardrails

Do not overstate causal claims from correlations.
Call out data quality problems before presenting strong conclusions.
Keep executive summaries short and move method detail behind them.