data-storytelling

Transform raw data into goal-aligned narratives with confidence labels.

4|Updated Mar 16, 2018
One-click install
npx skills add https://github.com/InNoobWeTrust/dotfiles --skill data-storytelling-innoobwetrust
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: data-storytelling
Source: https://github.com/InNoobWeTrust/dotfiles/tree/main/.agents/skills/data-storytelling
Command: npx skills add https://github.com/InNoobWeTrust/dotfiles --skill data-storytelling-innoobwetrust

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and assets (resource) components.

What problem does it solve?

Analysts and AI agents often generate data dumps or under-specified narratives that fail to tie insights to a decision. The data-storytelling skill transforms raw data into goal-aligned, evidence-backed narratives that are calibrated by explicit confidence and potential corrections from humans.

Core Features & Use Cases

  • Multi-lens analysis: combine trend, comparison, distribution, driver, anomaly, and root-cause lenses to avoid single-pass summaries.
  • Evidence-backed storytelling: attach confidence profiles, baselines, and method details to each insight and preserve provenance through each artifact.
  • Human-in-the-loop and audience adaptation: supports continuous feedback, checkpoint modes, and template-driven rendering for exec, analyst, ops, or customer audiences.
  • Output templates: executive summary, analyst deep-dive, ops action brief, and structured markdown, with audience-adapted tone and density.

Quick Start

Turn a data source into a goal-aligned narrative using the recommended template and interpreted lenses.

Frequently Asked Questions about data-storytelling

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I transform raw data into goal-aligned narratives for decision making?

Transform raw data into goal-aligned narratives by applying multi-lens analysis, explicit confidence labeling, and template-driven rendering to generate audience-specific outputs that support decision making.

What is multi-lens data analysis and when do I need it for data storytelling?

Multi-lens data analysis combines trend, comparison, distribution, driver, anomaly, and root-cause perspectives to avoid single-pass summaries. You need it for data storytelling when under-specified narratives fail to tie insights to decisions.

Can I adapt data narratives for different audiences like executives and ops teams?

You can adapt data narratives for executives, analysts, ops, and customers using template-driven rendering. This adjusts tone and density to produce executive summaries, analyst deep-dives, and ops action briefs.

How do I add confidence profiles and provenance to data analysis insights?

Add confidence profiles, baselines, and method details to data analysis insights using evidence-backed storytelling. This preserves provenance through each artifact to calibrate narratives for human-in-the-loop corrections.

Does this data storytelling approach support continuous human-in-the-loop feedback?

The data storytelling approach supports continuous human-in-the-loop feedback through checkpoint modes and corrections. This allows analysts to refine goal-aligned narratives iteratively during the rendering process.