datacommons-client
Query public statistics from Data Commons
Also available from: davila7
Access global statistical data from Data Commons including demographics, economics, health, and environmental indicators. Query population figures, GDP, unemployment rates, and geographic relationships using Python client methods.
Download the skill ZIP
Upload in Claude
Go to Settings → Capabilities → Skills → Upload skill
Toggle on and start using
Test it
Using "datacommons-client". Get the population of France and Germany
Expected outcome:
- France: 67,848,156 people (2023)
- Germany: 84,358,845 people (2023)
- Data source: World Bank
Using "datacommons-client". Show US unemployment trend from 2018 to 2023
Expected outcome:
- 2018: 3.9%
- 2019: 3.7%
- 2020: 8.1%
- 2021: 5.4%
- 2022: 3.6%
- 2023: 3.6%
Security Audit
Low RiskThis skill is a documentation wrapper for the Data Commons Python client library. All static findings are FALSE POSITIVES: the scanner misinterprets markdown code block delimiters as shell commands, API call examples as network threats, and legitimate documentation patterns as credential exposure. The skill enables read-only access to public statistical data with no code execution capabilities beyond package installation documentation.
Risk Factors
⚙️ External commands (200)
🌐 Network access (46)
Quality Score
What You Can Build
Compare regional statistics
Query and compare population, income, and unemployment data across multiple states or countries.
Access historical trends
Retrieve time-series data for economic indicators, health statistics, or environmental measurements.
Build data-driven applications
Integrate public statistical data into applications using Python client library methods.
Try These Prompts
Get the latest population for California, Texas, and New York using the Data Commons client.
Query the unemployment rate time series for the United States from 2010 to 2023.
Get median household income for all counties in California for year 2020.
Compare population, median income, and median age across Florida, Georgia, and South Carolina.
Best Practices
- Always resolve place names to DCIDs before querying to handle ambiguous names
- Use entity expressions to query hierarchies efficiently (all counties in a state at once)
- Cache DCID resolutions when querying the same entities repeatedly
Avoid
- Hardcoding DCIDs instead of resolving names dynamically
- Making individual queries for each entity instead of batch queries
- Ignoring data source facets when consistency matters