Building Claude Agent Skills

YAML
---
name: analyzing-data-trends
description: Analyzes time-series data to identify patterns and anomalies. Use when examining datasets for insights or trend detection.
---

# Data Trend Analysis

Python
import pandas as pd
import matplotlib.pyplot as plt

df = pd.read_csv('data.csv')
df['date'] = pd.to_datetime(df['date'])
df.set_index('date', inplace=True)
trend = df.rolling(window=7).mean()
plt.plot(df.index, df.values, alpha=0.3)
plt.plot(trend.index, trend.values, linewidth=2)
plt.show()

1. Load and clean data
2. Convert to time series format
3. Apply smoothing techniques
4. Identify patterns and outliers
5. Generate visualizations

Progress:

• Analyze the expertise/methodology to extract
• Create YAML frontmatter with gerund name and trigger-based description
• Write Quick Start with immediate actionable example
• Document step-by-step workflow with checklist format
• Provide concrete input/output examples
• List best practices and common pitfalls
• Keep under 500 lines, be concise and specific

Example 1: Input: "I help companies optimize their database queries for better performance" Output:

YAML
---
name: optimizing-database-queries
description: Analyzes and improves SQL query performance through indexing and restructuring. Use when queries are slow or database performance needs improvement.
---

# Database Query Optimization

SQL
-- Before: Slow query
SELECT * FROM orders WHERE customer_id = 123 AND order_date > '2024-01-01';

-- After: Optimized with index
CREATE INDEX idx_customer_date ON orders(customer_id, order_date);
SELECT order_id, total FROM orders WHERE customer_id = 123 AND order_date > '2024-01-01';

**Example 2:**
Input: "Expert in reviewing pull requests and ensuring code quality"
Output:
```yaml
---
name: reviewing-code-quality
description: Conducts thorough code reviews focusing on maintainability, security, and performance. Use when evaluating pull requests or auditing codebases.
---

# Code Quality Review

Review checklist:

• Code follows style guidelines
• No security vulnerabilities
• Proper error handling
• Unit tests included
• Documentation updated