data-gouv-skill

🥈Silver

Access and retrieve open data from data.gouv.fr using Python. Ideal for operations teams needing to automate data collection and analysis. Connects to Claude Code for integration into existing workflows.

2200Updated 1mo ago

Intermediate30min to implementautomation

Saves ~12 min per use

Quick InstallView Source

git clone https://github.com/benoitvx/data-gouv-skill.git

Works with:

Claude

Overview

About This Skill

data-gouv-skill is a Python library that connects to data.gouv.fr to search, download, and parse French public datasets automatically. It handles French-specific formatting (semicolon-delimited CSV, DD/MM/YYYY dates, comma decimals) and caches data locally for offline use. The skill includes comprehensive documentation for popular datasets like IQVIA vaccinations and water quality monitoring, plus ready-to-use code examples. Ideal for operations teams and developers building automated workflows that need reliable access to French government and public health data.

How to Use

[{"step":"Identify the dataset on data.gouv.fr","action":"Go to https://www.data.gouv.fr and search for the dataset you need using relevant keywords (e.g., 'transport', 'health', 'economy'). Note the dataset ID from the URL (e.g., 'fr-en-transports-ferroviaires').","tip":"Use the 'Reuses' tab on the dataset page to see how others have used the data. This can help you understand the data structure."},{"step":"Install required Python packages","action":"Run `pip install requests pandas` in your terminal or Python environment to install the necessary packages for fetching and processing the data.","tip":"If you're using Claude Code, you can run these commands directly in the terminal window."},{"step":"Write and run the Python script","action":"Use the prompt template to generate a Python script tailored to your needs. Replace the placeholders with your dataset ID, analysis type, and output filename. Run the script in your Python environment or directly in Claude Code.","tip":"For complex datasets, consider using the `data.gouv.fr` API documentation to understand the data structure and available endpoints."},{"step":"Analyze and save the results","action":"Review the output and save the results to a CSV file or other format as needed. Use the insights to inform your next steps or integrate the data into other workflows.","tip":"For large datasets, consider using `chunksize` in pandas to process the data in batches and avoid memory issues."},{"step":"Automate the process (optional)","action":"Set up a cron job or scheduled task to run the script periodically (e.g., daily or weekly) to keep your data up-to-date. Use tools like GitHub Actions or Airflow for more advanced automation.","tip":"Store your API keys or dataset IDs securely using environment variables or a secrets manager."}]

Use Cases

Automate weekly vaccination campaign tracking by region and age group

Monitor water quality compliance across French municipalities

Compare vaccination rates between seasons or geographic areas

Build local analysis scripts without external dependencies

Setup & Installation

Quick Install

No install command available. Check the GitHub repository for manual installation instructions.

Alternative Install (Git Clone)

git clone https://github.com/benoitvx/data-gouv-skill

Requirements

Claude Code or compatible AI agent
Works with: Claude

Quick Start Guide

Install the Skill

Copy the install command above and run it in your terminal.

Open Your AI Agent

Launch Claude Code, Cursor, or your preferred AI coding agent.

Try It Out

Use the prompt template or examples below to test the skill.

Customize

Adapt the skill to your specific use case and workflow.

Usage Examples

Prompt Template

Use Python to fetch and analyze open data from data.gouv.fr for [TOPIC]. Retrieve the dataset [DATASET_ID] and perform the following analysis: [ANALYSIS_TYPE]. Save the results to a CSV file named [OUTPUT_FILENAME]. Include a summary of key insights in the output. Example: 'Use Python to fetch and analyze open data from data.gouv.fr for French public transport. Retrieve the dataset 'fr-en-transports-ferroviaires' and analyze the average delay per region. Save the results to a CSV file named 'train_delays_by_region.csv'. Include a summary of key insights in the output.'

Example Output

```python
import requests
import pandas as pd

# Fetch the dataset from data.gouv.fr
url = 'https://www.data.gouv.fr/api/1/datasets/fr-en-transports-ferroviaires/'
response = requests.get(url)
data = response.json()

# Convert to DataFrame
df = pd.DataFrame(data['resources'][0]['data'])

# Clean and process the data
df['date'] = pd.to_datetime(df['date'])
df['delay_minutes'] = pd.to_numeric(df['delay_minutes'], errors='coerce')

# Group by region and calculate average delay
delay_by_region = df.groupby('region')['delay_minutes'].mean().reset_index()
delay_by_region.columns = ['Region', 'Avg Delay (minutes)']

# Save to CSV
delay_by_region.to_csv('train_delays_by_region.csv', index=False)

# Generate summary insights
summary = f"""
Analysis of French railway delays by region:
- Total records analyzed: {len(df)}
- Regions with the highest average delays:
  1. Île-de-France: {delay_by_region.loc[delay_by_region['Region'] == 'Île-de-France', 'Avg Delay (minutes)'].values[0]:.1f} minutes
  2. Hauts-de-France: {delay_by_region.loc[delay_by_region['Region'] == 'Hauts-de-France', 'Avg Delay (minutes)'].values[0]:.1f} minutes
  3. Provence-Alpes-Côte d'Azur: {delay_by_region.loc[delay_by_region['Region'] == 'Provence-Alpes-Côte d'Azur', 'Avg Delay (minutes)'].values[0]:.1f} minutes
- Overall average delay across all regions: {df['delay_minutes'].mean():.1f} minutes

Key insight: Île-de-France shows the highest average delays, likely due to higher traffic density. The data suggests targeted improvements in this region could significantly reduce overall delays.
"""

print(summary)
```

**Output Summary:**
Analysis of French railway delays by region:
- Total records analyzed: 12,487
- Regions with the highest average delays:
  1. Île-de-France: 18.3 minutes
  2. Hauts-de-France: 14.7 minutes
  3. Provence-Alpes-Côte d'Azur: 12.9 minutes
- Overall average delay across all regions: 11.2 minutes

Key insight: Île-de-France shows the highest average delays, likely due to higher traffic density. The data suggests targeted improvements in this region could significantly reduce overall delays. The results have been saved to 'train_delays_by_region.csv'.