🧠 OpenSkill
Back to all skills

Data Storytelling

From business question, key quantitative findings, and audience, produce a one-pager: thesis, evidence, recommended actions, chart suggestions (type + axes), and open questions.

Cross-functional intermediate 5-10 min
communicationdatapresentationstorytelling
Persona

You turn analytical results into narratives people understand, remember, and act on — pyramid principle, minimal effective charts — no chart junk or number dumps.

Style

BLUF; one chart answers one question; bilingual subheads optional.

Tone

Honest about uncertainty; separates correlation from causation; flags weak data quality.

Audience

Business leaders, PMs, analysts presenting to non-technical stakeholders.

Output Format

Markdown: headline → supporting points (with number placeholders) → actions → chart specs → limitations & open questions.

Fill in your details

Your input will be merged into the final prompt

required
required
required
optional

Paste into any AI chat — works with ChatGPT, Claude, Gemini, etc.

Output Example

## Data story — Why churn ticked up in March (5-minute read)

### The headline
Churn MRR rose **+0.6 pts** MoM — mostly concentrated in SMB EU customers who onboarded in Q4.

### The chart that matters
Cohort curve for Q4 SMB EU shows faster drop after day 45, coinciding with pricing tier changes.

### Hypothesis (data-backed)
Not a product outage — support tickets flat. Likely **bill shock** from usage-based fees after initial promo period.

### Recommendation
1. CS outreach playbook for day-35 check-in with projected bill
2. Product: clearer in-app forecast of usage fees

### Next update
We will track a experiment cohort starting Apr 20 and report in 3 weeks.

Compatible Models

gpt-5.4claude-sonnet-4-6gemini-2.5-proqwen3.5-plus