$npx -y skills add dkyazzentwatwa/chatgpt-skills --skill data-storytellerAnalyze datasets and turn them into narrative reports with charts, audits, comparisons, and statistical summaries. Use for exploratory analysis and executive-ready outputs.
| 1 | # Data Storyteller |
| 2 | |
| 3 | 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. |
| 4 | |
| 5 | ## Use This For |
| 6 | |
| 7 | - Executive summaries and narrative reports from CSV or spreadsheet data |
| 8 | - Data quality audits, comparisons, and anomaly reviews |
| 9 | - Statistical analysis, pivots, experiment reads, ROI and budget analysis |
| 10 | - Survey summaries and time-series decomposition |
| 11 | |
| 12 | ## Workflow |
| 13 | |
| 14 | 1. Profile the dataset shape, column types, and missing-value risk. |
| 15 | 2. Pick the smallest useful analysis path instead of running every script by default. |
| 16 | 3. Start with `scripts/data_storyteller.py` when the user wants a cohesive report. |
| 17 | 4. Reach for focused helpers when the task is narrow: |
| 18 | - `data_quality_auditor.py` |
| 19 | - `dataset_comparer.py` |
| 20 | - `correlation_explorer.py` |
| 21 | - `outlier_detective.py` |
| 22 | - `statistical_analyzer.py` |
| 23 | - `survey_analyzer.py` |
| 24 | - `ts_decomposer.py` |
| 25 | - `pivot_table_generator.py` |
| 26 | - `ab_test_calc.py` |
| 27 | - `roi_calculator.py` |
| 28 | - `budget_analyzer.py` |
| 29 | 5. Translate outputs into plain-English findings, risks, and next actions. |
| 30 | |
| 31 | ## Guardrails |
| 32 | |
| 33 | - Do not overstate causal claims from correlations. |
| 34 | - Call out data quality problems before presenting strong conclusions. |
| 35 | - Keep executive summaries short and move method detail behind them. |