report-generator

Report Generator Skill

Generate professional markdown and HTML reports from data with charts, tables, and analysis.

Instructions

You are a report generation expert. When invoked:

1. Analyze Data:
2. Understand data structure and content
3. Identify key metrics and insights
4. Calculate statistics and trends
5. Detect patterns and anomalies
6. Generate executive summaries

1. Create Report Structure:
2. Design clear, logical sections
3. Create table of contents
4. Add executive summary
5. Include detailed analysis
6. Provide recommendations

1. Generate Visualizations:
2. Create tables for structured data
3. Generate charts (bar, line, pie, scatter)
4. Add badges and indicators
5. Include code blocks and examples
6. Format numbers and percentages

1. Format Output:
2. Generate markdown reports
3. Create HTML reports with styling
4. Export to PDF
5. Add branding and customization
6. Ensure responsive design

Usage Examples

@report-generator data.csv
@report-generator --format html
@report-generator --template executive-summary
@report-generator --charts --pdf
@report-generator --compare baseline.json current.json

Report Types

Executive Summary Report

def generate_executive_summary(data, title="Executive Summary"):
    """
    Generate high-level executive summary report
    """
    from datetime import datetime

    report = f"""# {title}
**Generated:** {datetime.now().strftime('%B %d, %Y at %I:%M %p')}

---

## Key Highlights

"""

    # Calculate key metrics
    metrics = calculate_key_metrics(data)

    for metric in metrics:
        icon = "✅" if metric['status'] == 'good' else "⚠️" if metric['status'] == 'warning' else "❌"
        report += f"{icon} **{metric['name']}**: {metric['value']}\n"

    report += f"""

---

## Performance Overview

| Metric | Current | Previous | Change |
|--------|---------|----------|--------|
"""

    for metric in metrics:
        if 'previous' in metric:
            change = calculate_change(metric['current'], metric['previous'])
            arrow = "↑" if change > 0 else "↓" if change < 0 else "→"
            color = "green" if change > 0 else "red" if change < 0 else "gray"

            report += f"| {metric['name']} | {metric['current']:,} | {metric['previous']:,} | {arrow} {abs(change):.1f}% |\n"

    report += """

---

## Recommendations

"""

    recommendations = generate_recommendations(metrics)
    for i, rec in enumerate(recommendations, 1):
        priority = rec.get('priority', 'medium')
        emoji = "🔴" if priority == 'high' else "🟡" if priority == 'medium' else "🟢"

        report += f"{i}. {emoji} **{rec['title']}**\n"
        report += f"   {rec['description']}\n\n"

    return report

Data Analysis Report

import pandas as pd
import numpy as np
from datetime import datetime

def generate_data_analysis_report(df, title="Data Analysis Report"):
    """
    Generate comprehensive data analysis report
    """

    report = f"""# {title}
**Date:** {datetime.now().strftime('%Y-%m-%d')}
**Dataset:** {len(df):,} rows × {len(df.columns)} columns

---

## Table of Contents
1. [Dataset Overview](#dataset-overview)
2. [Data Quality](#data-quality)
3. [Statistical Summary](#statistical-summary)
4. [Distributions](#distributions)
5. [Correlations](#correlations)
6. [Insights](#insights)

---

## Dataset Overview

### Basic Information
- **Total Rows:** {len(df):,}
- **Total Columns:** {len(df.columns)}
- **Memory Usage:** {df.memory_usage(deep=True).sum() / 1024**2:.2f} MB
- **Duplicate Rows:** {df.duplicated().sum():,}

### Column Information

| Column | Type | Non-Null | Unique | Sample Values |
|--------|------|----------|--------|---------------|
"""

    for col in df.columns:
        dtype = str(df[col].dtype)
        non_null = df[col].count()
        unique = df[col].nunique()
        samples = df[col].dropna().head(3).tolist()
        sample_str = ", ".join(str(s) for s in samples)

        report += f"| {col} | {dtype} | {non_null:,} | {unique:,} | {sample_str} |\n"

    report += """

---

## Data Quality

### Missing Values

"""

    missing = df.isnull().sum()
    if missing.sum() > 0:
        report += "| Column | Missing Count | Missing % |\n"
        report += "|--------|---------------|----------|\n"

        for col in missing[missing > 0].index:
            count = missing[col]
            pct = (count / len(df)) * 100
            report += f"| {col} | {count:,} | {pct:.1f}% |\n"
    else:
        report += "✅ No missing values detected.\n"

    report += "\n### Data Type Issues\n\n"

    # Check for potential type issues
    type_issues = []

    for col in df.select_dtypes(include=['object']):
        # Check if column should be numeric
        try:
            pd.to_numeric(df[col], errors='raise')
            type_issues.append(f"- `{col}` appears to be numeric but stored as string")
        except:
            pass

        # Check if column should be datetime
        try:
            pd.to_datetime(df[col], errors='raise')
            if df[col].str.contains(r'\d{4}-\d{2}-\d{2}').any():
                type_issues.append(f"- `{col}` appears to be datetime but stored as string")
        except:
            pass

    if type_issues:
        report += "\n".join(type_issues) + "\n"
    else:
        report += "✅ No data type issues detected.\n"

    report += """

---

## Statistical Summary

### Numeric Columns

"""

    # Add statistics for numeric columns
    numeric_cols = df.select_dtypes(include=[np.number]).columns

    if len(numeric_cols) > 0:
        stats = df[numeric_cols].describe()
        report += stats.to_markdown() + "\n"

        # Add additional statistics
        report += "\n### Additional Statistics\n\n"
        report += "| Column | Median | Mode | Std Dev | Variance |\n"
        report += "|--------|--------|------|---------|----------|\n"

        for col in numeric_cols:
            median = df[col].median()
            mode = df[col].mode().iloc[0] if not df[col].mode().empty else "N/A"
            std = df[col].std()
            var = df[col].var()

            report += f"| {col} | {median:.2f} | {mode} | {std:.2f} | {var:.2f} |\n"

    report += """

### Categorical Columns

"""

    categorical_cols = df.select_dtypes(include=['object']).columns

    if len(categorical_cols) > 0:
        for col in categorical_cols[:5]:  # Limit to first 5
            report += f"\n#### {col}\n\n"

            value_counts = df[col].value_counts().head(10)

            report += "| Value | Count | Percentage |\n"
            report += "|-------|-------|------------|\n"

            for value, count in value_counts.items():
                pct = (count / len(df)) * 100
                report += f"| {value} | {count:,} | {pct:.1f}% |\n"

    report += """

---

## Distributions

"""

    # Analyze distributions of numeric columns
    for col in numeric_cols[:5]:  # Limit to first 5
        report += f"\n### {col} Distribution\n\n"

        q1 = df[col].quantile(0.25)
        q2 = df[col].quantile(0.50)
        q3 = df[col].quantile(0.75)
        iqr = q3 - q1

        # Detect outliers
        lower_bound = q1 - 1.5 * iqr
        upper_bound = q3 + 1.5 * iqr
        outliers = df[(df[col] < lower_bound) | (df[col] > upper_bound)]

        report += f"""
**Quartiles:**
- Q1 (25%): {q1:.2f}
- Q2 (50%, Median): {q2:.2f}
- Q3 (75%): {q3:.2f}
- IQR: {iqr:.2f}

**Outliers:** {len(outliers)} ({len(outliers)/len(df)*100:.1f}%)
- Lower bound: {lower_bound:.2f}
- Upper bound: {upper_bound:.2f}

"""

    report += """

---

## Correlations

"""

    if len(numeric_cols) > 1:
        corr_matrix = df[numeric_cols].corr()

        report += "\n### Correlation Matrix\n\n"
        report += corr_matrix.to_markdown() + "\n"

        # Find strong correlations
        report += "\n### Strong Correlations (|r| > 0.7)\n\n"

        strong_corr = []
        for i in range(len(c