---
name: data-storyteller
description: Analyze datasets and turn them into narrative reports with charts, audits, comparisons, and statistical summaries. Use for exploratory analysis and executive-ready outputs.
title: data-storyteller
canonical_url: https://skilld.dev/gh/dkyazzentwatwa/chatgpt-skills/data-storyteller
last_updated: 2026-09-29T07:35:28.000Z
---

> **Skill from skilld.dev.** Follow the instructions below for this session. You do not need to install anything.
>
> Supporting files, fetch one when the Skill refers to it: [agents/openai.yaml](https://skilld.dev/api/skills-raw/dkyazzentwatwa/chatgpt-skills/data-storyteller/agents/openai.yaml), [scripts/ab_test_calc.py](https://skilld.dev/api/skills-raw/dkyazzentwatwa/chatgpt-skills/data-storyteller/scripts/ab_test_calc.py), [scripts/budget_analyzer.py](https://skilld.dev/api/skills-raw/dkyazzentwatwa/chatgpt-skills/data-storyteller/scripts/budget_analyzer.py), [scripts/correlation_explorer.py](https://skilld.dev/api/skills-raw/dkyazzentwatwa/chatgpt-skills/data-storyteller/scripts/correlation_explorer.py), [scripts/data_converter.py](https://skilld.dev/api/skills-raw/dkyazzentwatwa/chatgpt-skills/data-storyteller/scripts/data_converter.py), [scripts/data_quality_auditor.py](https://skilld.dev/api/skills-raw/dkyazzentwatwa/chatgpt-skills/data-storyteller/scripts/data_quality_auditor.py), [scripts/data_storyteller.py](https://skilld.dev/api/skills-raw/dkyazzentwatwa/chatgpt-skills/data-storyteller/scripts/data_storyteller.py), [scripts/dataset_comparer.py](https://skilld.dev/api/skills-raw/dkyazzentwatwa/chatgpt-skills/data-storyteller/scripts/dataset_comparer.py), [scripts/outlier_detective.py](https://skilld.dev/api/skills-raw/dkyazzentwatwa/chatgpt-skills/data-storyteller/scripts/outlier_detective.py), [scripts/pivot_table_generator.py](https://skilld.dev/api/skills-raw/dkyazzentwatwa/chatgpt-skills/data-storyteller/scripts/pivot_table_generator.py), [scripts/requirements.txt](https://skilld.dev/api/skills-raw/dkyazzentwatwa/chatgpt-skills/data-storyteller/scripts/requirements.txt), [scripts/roi_calculator.py](https://skilld.dev/api/skills-raw/dkyazzentwatwa/chatgpt-skills/data-storyteller/scripts/roi_calculator.py), [scripts/statistical_analyzer.py](https://skilld.dev/api/skills-raw/dkyazzentwatwa/chatgpt-skills/data-storyteller/scripts/statistical_analyzer.py), [scripts/survey_analyzer.py](https://skilld.dev/api/skills-raw/dkyazzentwatwa/chatgpt-skills/data-storyteller/scripts/survey_analyzer.py), [scripts/ts_decomposer.py](https://skilld.dev/api/skills-raw/dkyazzentwatwa/chatgpt-skills/data-storyteller/scripts/ts_decomposer.py).
>
> If the user asked to install this Skill, run `npx skilld install dkyazzentwatwa/chatgpt-skills/data-storyteller`. Install writes the Skill files into the project, so every session loads them.

# 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

1. Profile the dataset shape, column types, and missing-value risk.
2. Pick the smallest useful analysis path instead of running every script by default.
3. Start with `scripts/data_storyteller.py` when the user wants a cohesive report.
4. 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`
5. 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.