Summary
This is the workhorse analytics skill you'll want for turning CSVs into actual reports. It bundles a full toolkit: data quality audits, correlation exploration, outlier detection, statistical summaries, A/B test calculations, time series decomposition, and more. The smart part is it profiles your data first and picks the smallest useful analysis instead of running everything by default. Great for both quick exploratory work and polished executive summaries. The workflow pushes you to translate findings into plain English and call out data quality problems before drawing conclusions, which honestly should be table stakes but often isn't. If you're doing any kind of structured data analysis and need narrative output with charts, this covers the spread.
Install to Claude Code
npx -y skills add dkyazzentwatwa/chatgpt-skills --skill data-storyteller --agent claude-codeInstalls into .claude/skills of the current project.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Files
SKILL.mdView on GitHub
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.pywhen the user wants a cohesive report. - Reach for focused helpers when the task is narrow:
data_quality_auditor.pydataset_comparer.pycorrelation_explorer.pyoutlier_detective.pystatistical_analyzer.pysurvey_analyzer.pyts_decomposer.pypivot_table_generator.pyab_test_calc.pyroi_calculator.pybudget_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.
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →First SeenJun 3, 2026
