Data Storyteller
Turns a CSV into a narrative report: outliers, correlations, time-series trend, executive summary.
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 14, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 966e542
Ran the bundled data_storyteller.py on a synthetic 200-row sales CSV with one planted outlier: it caught exactly that row (outlier_pct 0.5%), flagged the resulting right-skew (skewness 7.13), found the real marketing-spend/revenue correlation (r=0.52), and wrote a clean plain-English executive summary - fully working, not a stub.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 9/10
- Docs & honesty 5/5
What Data Storyteller does
A bundle of eleven Python scripts (profiling, quality audit, correlation, outliers, stats, pivots, A/B tests, ROI, budget, surveys, time-series) fronted by one entrypoint that produces an HTML/PDF/JSON narrative report from a CSV or spreadsheet. Use for exploratory data analysis or executive-ready write-ups where you want auto-generated plain-English findings, not just numbers.
How to install Data Storyteller
git clone https://github.com/dkyazzentwatwa/chatgpt-skills
cd chatgpt-skills
mkdir -p ~/.claude/skills
cp -r data-storyteller ~/.claude/skills/data-storyteller
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Data Storyteller
-
/data-storytellerTurns a CSV into a narrative report: outliers, correlations, time-series trend, executive summary.
It also activates on plain-language prompts like these:
-
Turn this sales CSV into an executive report with key insights. -
Analyze this dataset for outliers and correlations, please. -
Can you write a narrative summary of the trends in this spreadsheet?
Frequently asked questions
- Is the Data Storyteller skill free?
- Yes. The skill itself is free from dkyazzentwatwa/chatgpt-skills. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Data Storyteller work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Tested · Works. Ran the bundled data_storyteller.py on a synthetic 200-row sales CSV with one planted outlier: it caught exactly that row (outlier_pct 0.5%), flagged the resulting right-skew (skewness 7.13), found the real marketing-spend/revenue correlation (r=0.52), and wrote a clean plain-English executive summary - fully working, not a stub.
- What is the Data Storyteller SkillProof Score?
- 9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.
- How do I install Data Storyteller?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Data Storyteller with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.