data-storytelling Skill (wshobson): Turn Data Into Narrative

Helps your agent turn analytics into a clear story for executives and non-technical readers, ending with a recommendation.

Installs: 17.2K; on skills.sh
Stars: 42.1K; on GitHub
Files: 1; besides SKILL.md
Updated: Oct 2026; last repo commit

data-storytelling is a writing guide with no scripts. It gives the agent a story shape (setup, conflict, resolution), a six-step narrative arc from hook to call to action, and a three-pillar check of data, narrative and visuals. Its do's and don'ts are blunt: lead with the "so what", use three points, and do not dump data.

The detail lives in references/details.md, which has three full story frameworks (problem-solution, trend and comparison), three chart techniques with matplotlib and pandas examples, three presentation templates and a short writing-techniques section (headlines, transitions, handling uncertainty). The skill triggers when you present analytics to stakeholders, write data reports or build executive presentations. It does not analyse your data itself.

Good for

Analysts preparing quarterly reviews, executive updates or investor decks
Managers who need a data report that leads with the point
Anyone explaining numbers to a non-technical audience

Install data-storytelling

Claude Code

Copy this prompt.

Install the data-storytelling skill in Claude Code. Run this command:

npx skills add https://github.com/wshobson/agents --skill data-storytelling

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Requires Node.js.

From its listing on skills.sh. Source.

What's in the skill

When it loads

Transform data into compelling narratives using visualization, context, and persuasive structure. Use when presenting analytics to stakeholders, creating data reports, or building executive presentations.

Sections in SKILL.md

When to Use This Skill
Core Concepts
1. Story Structure
2. Narrative Arc
3. Three Pillars
Detailed patterns and worked examples
Best Practices
Do's
Don'ts

Key facts

Author: wshobson
Repo: wshobson/agents
License: MIT (as listed by the crawl)
Installs on skills.sh: 17,248 (Nov 2, 2026)
GitHub stars: 42,081 (repo, Nov 2, 2026)
Last commit: 2026-10-30
Files: 2 files including SKILL.md: references/details.md and no scripts
Part of plugin: business-analytics, in the wshobson/agents collection
Collection works in: Claude Code, Codex CLI, Cursor, OpenCode, Antigravity CLI, GitHub Copilot, Pi

What it includes

Setup, conflict, resolution: baseline, the problem or opportunity, then the insight
The basic frame for any data presentation.
Story structure
Hook, context, rising action, climax, resolution, call to action
Six steps from a surprising insight to clear next steps.
Narrative arc
Data as evidence, narrative as meaning, visuals as clarity
A check that a report has all three.
Three pillars
Start with the so-what, rule of three, show don't tell, end with action
The don'ts include data dumping, burying the insight, jargon and showing methodology first.
Best practices
Problem-solution, trend and comparison stories, each with a worked outline
Examples: a customer churn analysis, a Q4 performance review and a market opportunity analysis.
Story frameworks (details.md)
Progressive reveal, contrast and compare, annotation and highlight
The annotation example uses matplotlib and pandas code.
Visualization techniques (details.md)
Executive summary slide, data story flow, one-page dashboard story
Text layouts you can fill in with your own numbers.
Presentation templates (details.md)
Headlines that work, transition phrases and how to handle uncertainty
A section of phrasing guidance at the end of the reference file.
Writing techniques (details.md)

From the official docs

Questions

What does the data-storytelling skill do?

It guides the agent to present data as a story: a hook, context, a key insight and a clear recommendation. It supplies three story frameworks, chart techniques and slide templates.

How do I install it?

Use the install box above. Copy the whole folder, not just SKILL.md, because the worked examples are in references/details.md. The wshobson/agents README also lists plugin routes.

Does it work in Claude Code, Codex and Cursor?

The repo README says its collection of plugins, agents and skills works across Claude Code, OpenAI Codex CLI, Cursor, OpenCode, Antigravity CLI, GitHub Copilot and Pi. It does not give a separate list for this one skill.

Does it analyse my data?

No. It shapes how you present findings you already have. The only code in its reference file is a matplotlib and pandas chart-annotation example.

Do I need an API key?

No key is mentioned. The skill bundles no scripts.

What kinds of documents is it for?

SKILL.md lists executive presentations, quarterly business reviews, investor presentations, data-driven reports, insights for non-technical audiences, and recommendations based on data.

Is it safe?

It is Markdown guidance with no scripts. Check that any numbers and claims the assistant puts in your deck come from your data.

Information

updated Nov 2, 2026

Repository: wshobson/agents
Folder: plugins/business-analytics/skills/data-storytelling

wshobson/agents skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 4

data-storytelling SKILL.md · github.com
data-storytelling details.md · github.com
skills.sh listing · skills.sh
wshobson/agents · github.com