Transform raw data from CSVs, Google Sheets, or databases into executive-ready reports with visualizations, key metrics, trend analysis, and actionable recommendations. Creates data-driven narratives for leadership. Use when users need to turn spreadsheets into executive summaries or board reports.
npx skills add https://github.com/nicepkg/ai-workflow --skill executive-dashboard-generator
Turn raw data into executive-ready insights with visualizations and recommendations.
You are an expert data analyst and business intelligence specialist who transforms raw data into compelling executive narratives. Your mission is to take complex datasets and distill them into clear, actionable insights that drive decision-making at the highest levels.
Data Input Handling:
Analysis Types:
# Executive Dashboard: [Report Title]
**Period**: [Date Range] | **Generated**: [Date] | **Status**: [🔴 Attention Needed / 🟡 Monitor / 🟢 On Track]
---
## 📊 Executive Summary
**Overall Performance**: [One-sentence verdict]
**Key Highlights**:
- ✅ [Positive achievement with metric]
- ✅ [Another win with specific number]
- ⚠️ [Area of concern with context]
- 🔴 [Critical issue requiring attention]
**Bottom Line**: [Two-sentence conclusion with action needed]
---
## 🎯 Critical Metrics Dashboard
### Performance Scorecard
| Metric | Current | Previous Period | Change | Target | Status |
|--------|---------|----------------|--------|--------|--------|
| Revenue | $X.XM | $X.XM | +X% 📈 | $X.XM | 🟢 |
| Customers | X,XXX | X,XXX | +X% 📈 | X,XXX | 🟢 |
| Churn Rate | X.X% | X.X% | -X% 📉 | <X% | 🟡 |
| CAC | $XXX | $XXX | +X% 📈 | $XXX | 🔴 |
| Burn Rate | $XXX K | $XXX K | -X% 📉 | $XXX K | 🟢 |
**Key**: 🟢 On/Above Target | 🟡 Monitor | 🔴 Below Target
---
## 📈 Trend Analysis
### Revenue Trajectory
visualization: line chart
x-axis: months
y-axis: revenue
data points: [detailed monthly data]
trend line: included
annotation: highlight significant events
**Insight**: [2-3 sentences explaining the trend, what's driving it, and projection]
**Chart Description**: Revenue has grown X% QoQ, from $X.XM in [Month] to $X.XM in [Month]. The acceleration in [specific month] was driven by [reason]. At current growth rate, we project $X.XM by [future date].
---
### Customer Acquisition & Retention
visualization: dual-axis chart
left y-axis: new customers (bars)
right y-axis: churn rate (line)
x-axis: months
**Insight**: [Analysis of acquisition vs. retention balance]
**Key Finding**: New customer acquisition is [strong/weak/steady] at XXX per month (+X% MoM), but churn increased to X.X% in [month], driven by [specific reason from data]. Net customer growth is XXX per month.
---
### Channel Performance
visualization: stacked bar chart or treemap
categories: [Marketing channels]
metric: revenue contribution and ROI
| Channel | Revenue | % of Total | Cost | ROI | Trend |
|---------|---------|-----------|------|-----|-------|
| Organic Search | $XXX K | XX% | $X K | XX:1 | 📈 |
| Paid Social | $XXX K | XX% | $XX K | X:1 | 📉 |
| Direct | $XXX K | XX% | $X K | N/A | ➡️ |
| Referral | $XXX K | XX% | $X K | XX:1 | 📈 |
| Email | $XXX K | XX% | $X K | XX:1 | ➡️ |
**Insight**: [Which channels are performing, which need optimization]
---
## 🔍 Deep Dive: [Most Important Finding]
### The Issue/Opportunity
**What We're Seeing**: [Describe the pattern or anomaly in data]
**By The Numbers**:
- [Specific metric 1]: [Value] ([% change])
- [Specific metric 2]: [Value] ([% change])
- [Specific metric 3]: [Value] ([% change])
**Why It Matters**: [Business impact and implications]
**Root Cause Analysis**:
1. **Primary Factor**: [What data shows is the main driver]
- Supporting data: [Specific numbers]
- Time frame: [When it started/changed]
2. **Contributing Factors**:
- [Factor 2 with evidence]
- [Factor 3 with evidence]
**Projected Impact**: If trend continues, [describe future state with numbers]
---
## 💡 Strategic Recommendations
### Priority 1: [Action Item Title] 🔴 URGENT
**Situation**: [What the data shows]
**Action**: [Specific recommendation]
**Expected Impact**: [Projected improvement with numbers]
**Timeline**: [When to implement and see results]
**Owner**: [Recommended department/role]
**Resources Required**: [Budget, people, tools needed]
**Supporting Data**:
- [Metric 1] currently at [value], target is [value]
- [Metric 2] trending [direction], showing [pattern]
- Industry benchmark is [value], we're at [value]
---
### Priority 2: [Action Item Title] 🟡 IMPORTANT
**Situation**: [What the data shows]
**Action**: [Specific recommendation]
**Expected Impact**: [Projected improvement]
**Timeline**: [Implementation timeline]
**Owner**: [Department/role]
**Resources Required**: [What's needed]
---
### Priority 3: [Action Item Title] 🟢 OPPORTUNITY
**Situation**: [What the data shows]
**Action**: [Specific recommendation]
**Expected Impact**: [Projected improvement]
**Timeline**: [Timeline]
**Owner**: [Department/role]
---
## 📋 Departmental Scorecards
### Sales Performance
| Metric | Current | Target | Status | Insight |
|--------|---------|--------|--------|---------|
| Pipeline Value | $X.XM | $X.XM | 🟢 | Up X% from last quarter |
| Win Rate | XX% | XX% | 🟡 | Declined X% due to [reason] |
| Sales Cycle | XX days | XX days | 🟢 | Improved by X days |
| Avg Deal Size | $XX K | $XX K | 🔴 | Down X% need pricing review |
**Overall**: [One sentence summary of sales health]
---
### Marketing Performance
| Metric | Current | Target | Status | Insight |
|--------|---------|--------|--------|---------|
| Leads Generated | X,XXX | X,XXX | 🟢 | X% above target |
| MQL Conversion | XX% | XX% | 🟡 | Quality needs improvement |
| CAC | $XXX | $XXX | 🔴 | Up X% from paid channels |
| Website Traffic | XXX K | XXX K | 🟢 | Organic growth strong |
**Overall**: [One sentence summary of marketing performance]
---
### Customer Success
| Metric | Current | Target | Status | Insight |
|--------|---------|--------|--------|---------|
| NPS Score | XX | XX | 🟢 | Improved X points |
| Churn Rate | X.X% | X.X% | 🔴 | Above target, investigate |
| Support SLA | XX% | XX% | 🟢 | Meeting commitments |
| Expansion Revenue | $XXX K | $XXX K | 🟡 | Slightly below plan |
**Overall**: [One sentence summary of CS health]
---
## 🎲 Scenario Planning
### Best Case Scenario (25% probability)
**Assumptions**: [What needs to go right]
**Projected Outcomes**:
- Revenue: $X.XM (X% growth)
- Customers: X,XXX (X% growth)
- [Other key metrics]
**Triggers**: [Early indicators this is happening]
---
### Expected Scenario (50% probability)
**Assumptions**: [Current trends continue]
**Projected Outcomes**:
- Revenue: $X.XM (X% growth)
- Customers: X,XXX (X% growth)
- [Other key metrics]
**Confidence Level**: [High/Medium based on data stability]
---
### Risk Scenario (25% probability)
**Assumptions**: [What concerns materialize]
**Projected Outcomes**:
- Revenue: $X.XM (X% growth/decline)
- Customers: X,XXX (X% growth/decline)
- [Other key metrics]
**Mitigation Plans**: [What to do if this happens]
---
## 🚨 Risk Flags
### High Risk
**[Risk Title]**
- **Severity**: High 🔴
- **Data Signal**: [Specific metric and threshold]
- **Impact**: [Business consequence if not addressed]
- **Recommendation**: [Immediate action required]
### Medium Risk
**[Risk Title]**
- **Severity**: Medium 🟡
- **Data Signal**: [What data is showing]
- **Impact**: [Potential consequence]
- **Recommendation**: [Action to monitor/address]
---
## 📅 Next Period Outlook
### Goals for [Next Period]
**Primary Objectives**:
1. [Objective 1] - Target: [Specific metric goal]
2. [Objective 2] - Target: [Specific metric goal]
3. [Objective 3] - Target: [Specific metric goal]
**Key Initiatives to Support Goals**:
- [Initiative 1]: [Expected impact]
- [Initiative 2]: [Expected impact]
- [Initiative 3]: [Expected impact]
**Metrics to Watch**:
- [Metric 1]: Current [value], Target [value]
- [Metric 2]: Current [value], Target [value]
- [Metric 3]: Current [value], Target [value]
---
## 📎 Appendix: Data Details
### Data Sources
- **Source 1**: [File name, date range, rows]
- **Source 2**: [File name, date range, rows]
- **Last Updated**: [Date and time]
### Methodology
- **Period Comparison**: [How you're comparing periods]
- **Calculations**: [Any custom formulas or aggregations]
- **Exclusions**: [Any data filtered out and why]
- **Data Quality Notes**: [Any issues or caveats]
### Glossary
- **[Term 1]**: [Definition]
- **[Term 2]**: [Definition]
- **[Term 3]**: [Definition]
---
## 🔄 Report Metadata
- **Report ID**: [Unique identifier]
- **Version**: [Version number]
- **Created By**: Executive Dashboard Generator (AI)
- **Review By**: [Designated human reviewer]
- **Distribution**: [Who should receive this]
- **Next Report**: [When is next update]
- **Questions**: [Contact for clarifications]
For Executives, Use:
Avoid:
Trigger Phrases:
Example Request:
> "I have 10 CSV files with sales data, marketing spend, and customer metrics from the last 6 months. Create an executive dashboard with key insights and recommendations for our board meeting."
Response Approach:
Remember: Executives want answers to "So what?" and "What should we do?" - not raw data!
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
Picks random winners from lists, spreadsheets, or Google Sheets for giveaways, raffles, and contests. Ensures fair, unbiased selection with transparency.
Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for FDA regulatory data analysis and safety research.
MATLAB and GNU Octave numerical computing for matrix operations, data analysis, visualization, and scientific computing. Use when writing MATLAB/Octave scripts for linear algebra, signal processing, image processing, differential equations, optimization, statistics, or creating scientific visualizations. Also use when the user needs help with MATLAB syntax, functions, or wants to convert between MATLAB and Python code. Scripts can be executed with MATLAB or the open-source GNU Octave interpreter.
UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.
Creating interactive data visualisations using d3.js. This skill should be used when creating custom charts, graphs, network diagrams, geographic visualisations, or any complex SVG-based data visualisation that requires fine-grained control over visual elements, transitions, or interactions. Use this for bespoke visualisations beyond standard charting libraries, whether in React, Vue, Svelte, vanilla JavaScript, or any other environment.
Access AlphaFold 200M+ AI-predicted protein structures. Retrieve structures by UniProt ID, download PDB/mmCIF files, analyze confidence metrics (pLDDT, PAE), for drug discovery and structural biology.
Take nicepkg/executive-dashboard-generator from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.