data-storytelling
Skill5 starsChanged 2 months agoMITView on GitHub
Data presentation and storytelling for data product operators. Narrative structures, chart selection, headline formulas, and anti-patterns. Use when presenting data to stakeholders, building a data presentation, writing an executive summary of findings, telling a data story, or making a case with data. For stakeholder alignment process, see stakeholder-alignment. For metric definitions, see metrics-definition.
17 other projects use a version of this.
Adopted by
Most recently taken up by
- dmoreq/agent-grimoiretheir own version, first seen Nov 8, 2026
- Harrypatria/data-mining-mltheir own version, first seen Nov 1, 2026
- xfstudio/skillstheir own version, first seen Oct 13, 2026
- Samueladewole/claude-skillstheir own version, first seen Oct 13, 2026
- Gopyr/gopyr-skills-hubtheir own version, first seen Oct 11, 2026
- zieang88888/zhskillstheir own version, first seen Oct 1, 2026
Used with
Projects with it also use data-visualization.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
AnthropicSkilldata-visualization
Create effective data visualizations with Python (matplotlib, seaborn, plotly). Use when building charts, choosing the right chart type for a dataset, creating publication-quality figures, or applying design principles like accessibility and color theory.
Also in 3 projects that use this
Other versions17 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 17
- anbeime/skill★ 7.9ksame name
- happycapy-ai/Happycapy-skills★ 137same name
- xfstudio/skills★ 9same name
- ai4brands-design/claude-skills★ 2same name
- CodeWithBehnam/cc-docs★ 2same name
- danielrosehill/Claude-Data-Visualisation-And-Publishing-Plugin★ 2same name
- dycnnnb/skills★ 2same name
- Harrypatria/data-mining-ml★ 2same name
- miptah21/skills★ 2same name
- Oceanjackson1/Claude-Skill★ 2same name
7 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository24 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- analystSkill
- arbitrage-audit-dataSkill
- dashboards-to-decisionsSkill
- databricks-data-product-reviewSkill
- data-consumer-discoverySkill
- data-model-designSkill
- data-pipeline-qualitySkill
- data-product-operatorSkill
- data-product-thinkingSkill
- data-product-validationSkill
- data-quality-assessmentSkill
- data-team-operating-modelSkill
- data-team-positioningSkill
- duckdb-data-profilingSkill
- ethical-risk-assessmentSkill
- grill-me-dataSkill
- healthcare-cohort-designSkill
- healthcare-data-domainSkill
- healthcare-data-readiness-debriefSkill
- healthcare-data-reconciliationSkill
- metrics-definitionSkill
- research-synthesis-dataSkill
- stakeholder-alignmentSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 8 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Every data finding needs a headline: [Specific Number] + [Business Impact] + [Actionable Context].
- Distinctive: line 35
Start with the finding, not the methodology.
- Distinctive: line 50
Use stacked bars, not pie charts.
- Distinctive: line 52
Never use dual Y-axes. Two metrics, two charts.
- Distinctive: line 58
Charts without a "so what.": Every chart needs a headline that states the finding.
- Distinctive: line 64
Hiding bad news in an appendix: If the data tells an inconvenient story, put it up front.
“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Headline Formula
Every data finding needs a headline: [Specific Number] + [Business Impact] + [Actionable Context].
"Readmission risk scores now flag 23% more high-risk patients, saving $2.1M annually." Not "We improved our model performance." Not "Results were statistically significant."
The number makes it concrete. The impact makes it relevant. The context makes it actionable.
Narrative Structures
Pick the structure that matches the situation:
| Structure | When to Use | Shape |
| Problem-Solution | Pitching new work | "Here's the gap, here's what we built" |
| Trend | Status updates | "Here's what changed and why it matters" |
| Comparison | Trade-off decisions | "Here are two options with costs" |
Narrative Arc for Presentations
Hook (the surprise or gap) → Context (what the audience needs to know) → Evidence (the data, 2-3 charts max) → Implication (so what?) → Recommendation (now what?)
Start with the finding, not the methodology. Executives care about the answer. They'll ask about the method if they want it.
Chart Selection
Match the metric type to the right chart:
| Metric Type | Chart | Example |
| Counts | Bar chart | Monthly patient encounters |
| Rates over time | Line chart | 30-day readmission rate by quarter |
| Part-of-whole | Stacked bar | Claim denials by category |
| Distribution | Histogram or box plot | Length of stay distribution |
| Correlation | Scatter plot | Cost vs complexity score |
| Ranking | Horizontal bar | Top 10 diagnoses by volume |
Use stacked bars, not pie charts; labels stay readable.
Never use dual Y-axes. Two metrics, two charts. Dual axes let you imply any correlation by scaling the axes.
Label data directly on the chart. A legend across the room is useless.
Presentation Anti-Patterns
Charts without a "so what." Every chart needs a headline that states the finding. "Figure 3: Revenue by Region" tells the audience nothing. "Northeast revenue dropped 12% after formulary change" tells them what to see.
Data dumps disguised as analysis. 47 metrics on one slide helps no one. Pick the 2-3 numbers that matter and make them big.
Leading with methodology. "We used a logistic regression with 47 features and cross-validated using..." Save it for the appendix. Lead with the result.
Hiding bad news in an appendix. If the data tells an inconvenient story, put it up front. Credibility compounds faster than any dashboard metric.
Cross-References
For stakeholder alignment process (getting agreement on what to build), see stakeholder-alignment. For metric definitions (what exactly does this number mean?), see metrics-definition. This skill covers how to present the results.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.