data-analysis
Analyze data, process CSV/JSON files, compute statistics, and create data visualizations. Use when the user asks about data processing, statistics, or analysis.
71
Quality
88%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Securityby
Passed
No findings from the security scan
Data Analysis Skill
Analyze and process data using Python in the sandbox.
Common Libraries
- pandas: DataFrames, CSV/JSON/Excel processing
- numpy: Numerical computing
- matplotlib: Visualization (use Agg backend)
Install if needed: pip install pandas numpy matplotlib
Common Tasks
Read and analyze CSV
import pandas as pd
df = pd.read_csv('data.csv')
print(df.describe())
print(f"\nShape: {df.shape}")
print(f"\nColumns: {list(df.columns)}")
print(f"\nFirst 5 rows:\n{df.head()}")Create visualization from data
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt
import pandas as pd
import base64
df = pd.read_csv('data.csv')
df.plot(kind='bar', x='category', y='value', figsize=(10, 6))
plt.title('Data Overview')
plt.tight_layout()
plt.savefig('/tmp/chart.png', dpi=150)
with open('/tmp/chart.png', 'rb') as f:
print(f').decode()})')JSON processing
import json
with open('data.json') as f:
data = json.load(f)
# Process and analyze...Guidelines
- Always execute the analysis — don't just show code
- Show key statistics: shape, dtypes, describe(), null counts
- For large datasets, show head/tail and summary stats
- Generate charts when it helps explain the data
- Use base64 inline images for any visualizations
- Repository
- fastclaw-ai/fastclaw
- Commit
533a138
- Last updated
- First committed
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.