Best use case
Report Generator is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
## Overview
Teams using Report Generator should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/report-generator/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How Report Generator Compares
| Feature / Agent | Report Generator | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
## Overview
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Report Generator
## Overview
Generate professional data reports combining narrative text, charts, tables, and key metrics. Outputs HTML reports (viewable in any browser) or PDF. Suitable for executive summaries, weekly dashboards, data analysis reports, and client deliverables.
## Instructions
When a user asks you to generate a report, follow this process:
### Step 1: Install dependencies
```bash
pip install pandas matplotlib seaborn jinja2 weasyprint
# weasyprint is optional, needed only for PDF export
```
### Step 2: Understand the report requirements
Determine:
- **Data source:** CSV, Excel, database query results, or manually provided data
- **Report type:** Executive summary, detailed analysis, dashboard, recurring report
- **Audience:** Executives (high-level), analysts (detailed), clients (polished)
- **Key metrics:** What numbers matter most?
- **Output format:** HTML (default, no extra deps) or PDF (requires weasyprint)
### Step 3: Load and analyze the data
```python
import pandas as pd
import matplotlib
matplotlib.use('Agg') # Non-interactive backend
import matplotlib.pyplot as plt
import seaborn as sns
from datetime import datetime
import base64
from io import BytesIO
# Load data
df = pd.read_csv("data.csv")
# Compute key metrics
metrics = {
"total_revenue": df["revenue"].sum(),
"avg_order_value": df["revenue"].mean(),
"total_orders": len(df),
"growth_rate": ((df[df["period"] == "current"]["revenue"].sum() /
df[df["period"] == "previous"]["revenue"].sum()) - 1) * 100,
}
```
### Step 4: Generate charts
Create charts and encode them as base64 for embedding in HTML:
```python
def fig_to_base64(fig):
"""Convert a matplotlib figure to a base64-encoded PNG string."""
buf = BytesIO()
fig.savefig(buf, format="png", dpi=150, bbox_inches="tight")
buf.seek(0)
return base64.b64encode(buf.read()).decode("utf-8")
# Chart 1: Revenue trend
fig, ax = plt.subplots(figsize=(10, 5))
monthly = df.groupby("month")["revenue"].sum()
monthly.plot(kind="line", marker="o", ax=ax, color="#2563eb")
ax.set_title("Monthly Revenue Trend")
ax.set_ylabel("Revenue ($)")
ax.grid(True, alpha=0.3)
chart_trend = fig_to_base64(fig)
plt.close()
# Chart 2: Category breakdown
fig, ax = plt.subplots(figsize=(8, 5))
category_data = df.groupby("category")["revenue"].sum().sort_values(ascending=True)
category_data.plot(kind="barh", ax=ax, color="#22c55e")
ax.set_title("Revenue by Category")
ax.set_xlabel("Revenue ($)")
chart_category = fig_to_base64(fig)
plt.close()
# Chart 3: Distribution
fig, ax = plt.subplots(figsize=(8, 5))
sns.histplot(df["order_value"], bins=30, ax=ax, color="#8b5cf6")
ax.set_title("Order Value Distribution")
chart_distribution = fig_to_base64(fig)
plt.close()
```
### Step 5: Build the HTML report
```python
from jinja2 import Template
report_template = Template("""
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8">
<title>{{ title }}</title>
<style>
body { font-family: 'Helvetica Neue', Arial, sans-serif; margin: 40px; color: #1a1a1a; line-height: 1.6; }
.header { border-bottom: 3px solid #2563eb; padding-bottom: 20px; margin-bottom: 30px; }
h1 { color: #1e293b; margin-bottom: 5px; }
.subtitle { color: #64748b; font-size: 14px; }
.metrics { display: grid; grid-template-columns: repeat(auto-fit, minmax(200px, 1fr)); gap: 20px; margin: 30px 0; }
.metric-card { background: #f8fafc; border-radius: 8px; padding: 20px; border-left: 4px solid #2563eb; }
.metric-value { font-size: 28px; font-weight: 700; color: #1e293b; }
.metric-label { font-size: 13px; color: #64748b; text-transform: uppercase; letter-spacing: 0.5px; }
.chart-section { margin: 40px 0; }
.chart-section img { max-width: 100%; border-radius: 8px; box-shadow: 0 1px 3px rgba(0,0,0,0.1); }
table { width: 100%; border-collapse: collapse; margin: 20px 0; }
th { background: #f1f5f9; padding: 12px; text-align: left; font-size: 13px; text-transform: uppercase; }
td { padding: 10px 12px; border-bottom: 1px solid #e2e8f0; }
.section { margin: 40px 0; }
.footer { margin-top: 60px; padding-top: 20px; border-top: 1px solid #e2e8f0; color: #94a3b8; font-size: 12px; }
</style>
</head>
<body>
<div class="header">
<h1>{{ title }}</h1>
<div class="subtitle">Generated on {{ date }} | Period: {{ period }}</div>
</div>
<div class="metrics">
{% for metric in metrics %}
<div class="metric-card">
<div class="metric-value">{{ metric.value }}</div>
<div class="metric-label">{{ metric.label }}</div>
</div>
{% endfor %}
</div>
{% for section in sections %}
<div class="section">
<h2>{{ section.title }}</h2>
<p>{{ section.description }}</p>
{% if section.chart %}
<div class="chart-section">
<img src="data:image/png;base64,{{ section.chart }}" alt="{{ section.title }}">
</div>
{% endif %}
{% if section.table %}
{{ section.table }}
{% endif %}
</div>
{% endfor %}
<div class="footer">
<p>This report was auto-generated. Data source: {{ data_source }}</p>
</div>
</body>
</html>
""")
html = report_template.render(
title="Monthly Performance Report",
date=datetime.now().strftime("%B %d, %Y"),
period="January 2025",
data_source="sales_data.csv",
metrics=[
{"label": "Total Revenue", "value": f"${metrics['total_revenue']:,.0f}"},
{"label": "Total Orders", "value": f"{metrics['total_orders']:,}"},
{"label": "Avg Order Value", "value": f"${metrics['avg_order_value']:,.2f}"},
{"label": "Growth Rate", "value": f"{metrics['growth_rate']:+.1f}%"},
],
sections=[
{
"title": "Revenue Trend",
"description": "Monthly revenue over the reporting period.",
"chart": chart_trend,
"table": None,
},
{
"title": "Category Breakdown",
"description": "Revenue distribution across product categories.",
"chart": chart_category,
"table": category_data.to_frame().to_html(classes="data-table"),
},
],
)
# Save HTML
with open("report.html", "w") as f:
f.write(html)
print("Report saved to report.html")
```
### Step 6: Convert to PDF (optional)
```python
# Using weasyprint
from weasyprint import HTML
HTML(string=html).write_pdf("report.pdf")
print("PDF saved to report.pdf")
```
Or use the browser-based approach:
```bash
# Using Chrome headless
google-chrome --headless --print-to-pdf=report.pdf report.html
```
## Examples
### Example 1: Weekly sales report
**User request:** "Generate a weekly sales report from this CSV"
**Actions:**
1. Load the CSV and filter to the current week
2. Compute KPIs: total revenue, orders, AOV, top product, conversion rate
3. Generate charts: daily revenue trend, top 10 products bar chart, channel pie chart
4. Build an HTML report with metric cards, charts, and a detailed transactions table
5. Save as report.html
**Output:** A polished HTML report with 4 KPI cards at the top, 3 charts, and a sortable table of transactions.
### Example 2: Executive summary from multiple data sources
**User request:** "Create an executive summary combining sales, support, and engagement data"
**Actions:**
1. Load three CSV files (sales.csv, support_tickets.csv, engagement.csv)
2. Compute cross-functional metrics: revenue, ticket resolution time, user retention
3. Generate a comparison chart showing month-over-month trends for all three areas
4. Write narrative summaries for each section highlighting key takeaways
5. Output as a PDF report
**Output:** A 3-page PDF with an overview dashboard, per-department sections, and a recommendations section.
### Example 3: Automated recurring report
**User request:** "Set up a monthly report template I can reuse"
**Actions:**
1. Create a Python script `generate_report.py` that accepts a CSV path and date range as arguments
2. Include all chart generation, metric computation, and HTML templating
3. Make it configurable via a `report_config.json` for title, metrics, and sections
4. Add CLI argument parsing for easy automation
**Output:** A reusable script the user can run monthly with `python generate_report.py --data sales.csv --period 2025-03`.
## Guidelines
- Always use the Agg backend for matplotlib (`matplotlib.use('Agg')`) to avoid display issues in headless environments.
- Embed charts as base64 in HTML so the report is a single self-contained file.
- Design for print: use readable fonts, sufficient contrast, and avoid overly wide layouts.
- Include the data source, generation date, and reporting period on every report.
- For metric cards, show both the value and the trend (up/down compared to prior period).
- Use consistent color schemes across all charts in a report.
- Keep executive summaries to one page of metrics and charts, with details in subsequent sections.
- For PDF output, test with weasyprint first. Fall back to Chrome headless if CSS rendering is problematic.
- Always validate data before generating reports. Missing or malformed data should be flagged, not silently ignored.Related Skills
game-test-case-generator
基于需求文档（xls/csv）生成专业游戏测试用例，支持完整用例和快速测试点两种模式。当用户提到"游戏测试"、"测试用例生成"、"需求转测试用例"、上传需求文档或原型时使用此技能。
viral-generator-builder
Expert in building shareable generator tools that go viral - name generators, quiz makers, avatar creators, personality tests, and calculator tools. Covers the psychology of sharing, viral mechanics, and building tools people can't resist sharing with friends. Use when: generator tool, quiz maker, name generator, avatar creator, viral tool.
k8s-manifest-generator
Create production-ready Kubernetes manifests for Deployments, Services, ConfigMaps, and Secrets following best practices and security standards. Use when generating Kubernetes YAML manifests, creating K8s resources, or implementing production-grade Kubernetes configurations.
daily-news-report
Scrapes content based on a preset URL list, filters high-quality technical information, and generates daily Markdown reports.
run-nx-generator
Run Nx generators with prioritization for workspace-plugin generators. Use this when generating code, scaffolding new features, or automating repetitive tasks in the monorepo.
nano-image-generator
Generate images using Nano Banana Pro (Gemini 3 Pro Preview). Use when creating app icons, logos, UI graphics, marketing banners, social media images, illustrations, diagrams, or any visual assets. Supports reference images for style transfer and character consistency. Triggers include phrases like 'generate an image', 'create a graphic', 'make an icon', 'design a logo', 'create a banner', 'same style as', 'keep the style', or any request needing visual content.
lark-workflow-standup-report
日程待办摘要：编排 calendar +agenda 和 task +get-my-tasks，生成指定日期的日程与未完成任务摘要。适用于了解今天/明天/本周的安排。
excalidraw-diagram-generator
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.
tasks-generator
Generate structured task roadmaps from project specifications. Use when the user asks to create tasks, sprint plans, roadmaps, or work breakdowns based on PRD (Product Requirements Document), Tech Specs, or UI/UX specs. Triggers include requests like "generate tasks from PRD", "create sprint plan", "break down this spec into tasks", "create a roadmap", or "plan the implementation".
reporting-sprints
Use this skill when you need to report on a sprint
reporting-issues
Use this skill when you need to report on a troubleshooting session
ghe-report
Generate detailed workflow reports with metrics, health assessments, and epic-specific analysis for GitHub Elements. Covers throughput, cycle times, compliance status, and thread history.