data-storytelling
数据科学家与产品经理在向高管汇报或制作投资者演示时,当面临数据枯燥难懂的痛点,使用此技能可套用“Setup-Conflict-Resolution”叙事框架,自动生成结合可视化与业务上下文的洞察报告,让非技术受众秒懂结论并驱动决策。
Install / Use
npx skills add anbeime/skill --skill data-storytellingInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
Data & AnalyticsSupported Platforms
Our assessment of data-storytelling
data-storytelling scores 92/100 on our quality scale, 156th of 604 Data & Analytics skills we index (top 26%).
Its SKILL.md is 11 KB long, well organised into 60 sections with 14 code examples: a thorough specification that gives an agent plenty to work with.
With 7,172 GitHub stars, it is one of the more widely adopted skills in the catalogue.
Maintenance, license and trust
- The repository was last updated about 2 months ago, so data-storytelling is actively maintained.
- Our last check on 2026-10-05 found the source still online.
- No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
- Its trust signals score 88/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-09-26. Automated pattern scan on 2026-09-26. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
data-storytelling compared with similar skills
All 4 of these similar skills score higher than data-storytelling; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| data-storytelling (this skill)by anbeime | 92 | 7.2k | 53d ago | SKILL.md |
| x402by browser-use | 100 | 121.0k | 3d ago | SKILL.md |
| algorithmic-artby anthropics | 100 | 177.9k | 55d ago | SKILL.md |
| pptxby anthropics | 100 | 177.9k | 55d ago | SKILL.md |
| designby nextlevelbuilder | 100 | 149.0k | 6d ago | SKILL.md |
Frequently asked questions
- How do I install data-storytelling?
- Run
npx skills add anbeime/skill --skill data-storytelling. The install tabs above show the steps for each supported agent. - Which AI agents does data-storytelling work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is data-storytelling safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It declares no license and scores 88/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is data-storytelling still maintained?
- The repository was last updated about 2 months ago, so data-storytelling is actively maintained.
Skill content
View source on GitHubname: data-storytelling description: 数据科学家与产品经理在向高管汇报或制作投资者演示时,当面临数据枯燥难懂的痛点,使用此技能可套用“Setup-Conflict-Resolution”叙事框架,自动生成结合可视化与业务上下文的洞察报告,让非技术受众秒懂结论并驱动决策。
Data Storytelling
Transform raw data into compelling narratives that drive decisions and inspire action.
When to Use This Skill
- Presenting analytics to executives
- Creating quarterly business reviews
- Building investor presentations
- Writing data-driven reports
- Communicating insights to non-technical audiences
- Making recommendations based on data
Core Concepts
1. Story Structure
Setup → Conflict → Resolution
Setup: Context and baseline
Conflict: The problem or opportunity
Resolution: Insights and recommendations
2. Narrative Arc
1. Hook: Grab attention with surprising insight
2. Context: Establish the baseline
3. Rising Action: Build through data points
4. Climax: The key insight
5. Resolution: Recommendations
6. Call to Action: Next steps
3. Three Pillars
| Pillar | Purpose | Components | | ------------- | -------- | -------------------------------- | | Data | Evidence | Numbers, trends, comparisons | | Narrative | Meaning | Context, causation, implications | | Visuals | Clarity | Charts, diagrams, highlights |
Story Frameworks
Framework 1: The Problem-Solution Story
# Customer Churn Analysis
## The Hook
"We're losing $2.4M annually to preventable churn."
## The Context
- Current churn rate: 8.5% (industry average: 5%)
- Average customer lifetime value: $4,800
- 500 customers churned last quarter
## The Problem
Analysis of churned customers reveals a pattern:
- 73% churned within first 90 days
- Common factor: < 3 support interactions
- Low feature adoption in first month
## The Insight
[Show engagement curve visualization]
Customers who don't engage in the first 14 days
are 4x more likely to churn.
## The Solution
1. Implement 14-day onboarding sequence
2. Proactive outreach at day 7
3. Feature adoption tracking
## Expected Impact
- Reduce early churn by 40%
- Save $960K annually
- Payback period: 3 months
## Call to Action
Approve $50K budget for onboarding automation.
Framework 2: The Trend Story
# Q4 Performance Analysis
## Where We Started
Q3 ended with $1.2M MRR, 15% below target.
Team morale was low after missed goals.
## What Changed
[Timeline visualization]
- Oct: Launched self-serve pricing
- Nov: Reduced friction in signup
- Dec: Added customer success calls
## The Transformation
[Before/after comparison chart]
| Metric | Q3 | Q4 | Change |
|----------------|--------|--------|--------|
| Trial → Paid | 8% | 15% | +87% |
| Time to Value | 14 days| 5 days | -64% |
| Expansion Rate | 2% | 8% | +300% |
## Key Insight
Self-serve + high-touch creates compound growth.
Customers who self-serve AND get a success call
have 3x higher expansion rate.
## Going Forward
Double down on hybrid model.
Target: $1.8M MRR by Q2.
Framework 3: The Comparison Story
# Market Opportunity Analysis
## The Question
Should we expand into EMEA or APAC first?
## The Comparison
[Side-by-side market analysis]
### EMEA
- Market size: $4.2B
- Growth rate: 8%
- Competition: High
- Regulatory: Complex (GDPR)
- Language: Multiple
### APAC
- Market size: $3.8B
- Growth rate: 15%
- Competition: Moderate
- Regulatory: Varied
- Language: Multiple
## The Analysis
[Weighted scoring matrix visualization]
| Factor | Weight | EMEA Score | APAC Score |
| ----------- | ------ | ---------- | ---------- |
| Market Size | 25% | 5 | 4 |
| Growth | 30% | 3 | 5 |
| Competition | 20% | 2 | 4 |
| Ease | 25% | 2 | 3 |
| **Total** | | **2.9** | **4.1** |
## The Recommendation
APAC first. Higher growth, less competition.
Start with Singapore hub (English, business-friendly).
Enter EMEA in Year 2 with localization ready.
## Risk Mitigation
- Timezone coverage: Hire 24/7 support
- Cultural fit: Local partnerships
- Payment: Multi-currency from day 1
Visualization Techniques
Technique 1: Progressive Reveal
Start simple, add layers:
Slide 1: "Revenue is growing" [single line chart]
Slide 2: "But growth is slowing" [add growth rate overlay]
Slide 3: "Driven by one segment" [add segment breakdown]
Slide 4: "Which is saturating" [add market share]
Slide 5: "We need new segments" [add opportunity zones]
Technique 2: Contrast and Compare
Before/After:
┌─────────────────┬─────────────────┐
│ BEFORE │ AFTER │
│ │ │
│ Process: 5 days│ Process: 1 day │
│ Errors: 15% │ Errors: 2% │
│ Cost: $50/unit │ Cost: $20/unit │
└─────────────────┴─────────────────┘
This/That (emphasize difference):
┌─────────────────────────────────────┐
│ CUSTOMER A vs B │
│ ┌──────────┐ ┌──────────┐ │
│ │ ████████ │ │ ██ │ │
│ │ $45,000 │ │ $8,000 │ │
│ │ LTV │ │ LTV │ │
│ └──────────┘ └──────────┘ │
│ Onboarded No onboarding │
└─────────────────────────────────────┘
Technique 3: Annotation and Highlight
import matplotlib.pyplot as plt
import pandas as pd
fig, ax = plt.subplots(figsize=(12, 6))
# Plot the main data
ax.plot(dates, revenue, linewidth=2, color='#2E86AB')
# Add annotation for key events
ax.annotate(
'Product Launch\n+32% spike',
xy=(launch_date, launch_revenue),
xytext=(launch_date, launch_revenue * 1.2),
fontsize=10,
arrowprops=dict(arrowstyle='->', color='#E63946'),
color='#E63946'
)
# Highlight a region
ax.axvspan(growth_start, growth_end, alpha=0.2, color='green',
label='Growth Period')
# Add threshold line
ax.axhline(y=target, color='gray', linestyle='--',
label=f'Target: ${target:,.0f}')
ax.set_title('Revenue Growth Story', fontsize=14, fontweight='bold')
ax.legend()
Presentation Templates
Template 1: Executive Summary Slide
┌─────────────────────────────────────────────────────────────┐
│ KEY INSIGHT │
│ ══════════════════════════════════════════════════════════│
│ │
│ "Customers who complete onboarding in week 1 │
│ have 3x higher lifetime value" │
│ │
├──────────────────────┬──────────────────────────────────────┤
│ │ │
│ THE DATA │ THE IMPLICATION │
│ │ │
│ Week 1 completers: │ ✓ Prioritize onboarding UX │
│ • LTV: $4,500 │ ✓ Add day-1 success milestones │
│ • Retention: 85% │ ✓ Proactive week-1 outreach │
│ • NPS: 72 │ │
│ │ Investment: $75K │
│ Others: │ Expected ROI: 8x │
│ • LTV: $1,500 │ │
│ • Retention: 45% │ │
│ • NPS: 34 │ │
│ │ │
└──────────────────────┴──────────────────────────────────────┘
Template 2: Data Story Flow
Slide 1: THE HEADLINE
"We can grow 40% faster by fixing onboarding"
Slide 2: THE CONTEXT
Current state metrics
Industry benchmarks
Gap analysis
Slide 3: THE DISCOVERY
What the data revealed
Surprising finding
Pattern identification
Slide 4: THE DEEP DIVE
Root cause analysis
Segment breakdowns
Statistical significance
Slide 5: THE RECOMMENDATION
Proposed actions
Resource requirements
Timeline
Slide 6: THE IMPACT
Expected outcomes
ROI calculation
Risk assessment
Slide 7: THE ASK
Specific request
Decision needed
Next steps
Template 3: One-Page Dashboard Story
# Monthly Business Review: January 2024
## THE HEADLINE
Revenue up 15% but CAC increasing faster than LTV
## KEY METRICS AT A GLANCE
┌────────┬────────┬────────┬────────┐
│ MRR │ NRR │ CAC │ LTV │
│ $125K │ 108% │ $450 │ $2,200 │
│ ▲15% │ ▲3% │ ▲22% │ ▲8% │
└────────┴────────┴────────┴────────┘
## WHAT'S WORKING
✓ Enterprise segment growing 25% MoM
✓ Referral program driving 30% of new logos
✓ Support satisfaction at all-time high (94%)
## WHAT NEEDS ATTENTION
✗ SMB acquisition cost up 40%
✗ Trial conversion down 5 points
✗ Time-to-value increased by 3 days
## ROOT CAUSE
[Mini chart showing SMB vs Enterprise CAC trend]
SMB paid ads becoming less efficient.
CPC up 35% while conversion flat.
## RECOMMENDATION
1. Shift $20K/mo from paid to content
2. Launch SMB self-serve trial
3. A/B test shorter onboarding
## NEXT MONTH'S FOCUS
- Launch content marketing pilot
- Complete self-serve MVP
- Reduce time-to-value to < 7 days
Writing Techniques
Headlines That Work
BAD: "Q4 Sales Analysis"
GOOD: "Q4 Sales Beat Target by 23% - Here's Why"
BAD: "Customer Churn Report"
GOOD: "We're Losing $2.4M to Preventable Churn"
BAD: "Marketing Performance"
GOOD: "Content Marketing Delivers 4x ROI vs. Paid"
Formula:
[Specific Number] + [Business Impact] + [Actionable Context]
Transition Phrases
Building the narrative:
• "This leads us to ask..."
• "When we dig deeper..."
• "The pattern becomes clear when..."
• "Contrast this with..."
Introducing insights:
• "The data reveals..."
• "What surprised us was..."
• "The inflection point came when..."
• "The key finding is..."
Moving to action:
• "This insight suggests..."
• "Based on this analysis..."
• "The implication is clear..."
• "Our recommendation is..."
Handling Uncertainty
Acknowledge limitations:
• "With 95% confidence, we can say..."
• "The sample size of 500 shows..."
• "While correlation is strong, causation requires..."
• "This trend holds for [segment], though [caveat]..."
Present ranges:
• "Impact estimate: $400K-$600K"
• "Confidence interval: 15-20% improvement"
• "Best case: X, Conservative: Y"
Best Practices
Do's
- Start with the "so what" - Lead with insight
- Use the rule of three - Three points, three comparisons
- Show, don't tell - Let data speak
- Make it personal - Connect to audience goals
- End with action - Clear next steps
Don'ts
- Don't data dump - Curate ruthlessly
- Don't bury the insight - Front-load key findings
- Don't use jargon - Match audience vocabulary
- Don't show methodology first - Context, then method
- Don't forget the narrative - Numbers need meaning
Resources
Related Skills
x402
121.0kSet up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key.
algorithmic-art
177.9kCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems.
pptx
177.9kUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an em…
design
149.0kComprehensive design skill: brand identity, design tokens, UI styling, logo generation (55 styles, Gemini, Atlas Cloud, or MuAPI AI), corporate identity program (50 deliverables, CIP mockups), HTML presentations (Chart.js), banner design (22 styles, social/ads/web/print), icon design (15 styles, SVG…
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
