Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →mkurman/pandas-datareader
Multi-source financial data reader: FRED, World Bank, OECD, Eurostat, St. Louis Fed, Yahoo, Google, and more. Standard interface for economic and financial time series data ingestion.
Passed 20 of 22 test cases with the skill, and 16 of 22 without it.
and 6 more in the full report
4 fixed16 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
Write a short Python snippet that uses pandas_datareader to retrieve GDP per capita data from World Bank for recent years beginning in 2018.
| Checked | Without skill | With skill |
|---|---|---|
| The snippet imports pandas_datareader.data as web | Missed | Passed |
| The snippet calls web.DataReader using the series code NY.GDP.PCAP.CD | Missed | Passed |
| The snippet specifies worldbank as the data source parameter in DataReader | Missed | Passed |
The instructions your model reads when the skill loads.
pandas-datareader provides a unified interface for reading economic and financial time series from multiple sources: FRED (Federal Reserve), World Bank, OECD, Eurostat, Yahoo Finance, and St. Louis Fed. Standard tool for macroeconomic data ingestion.
uv pip install pandas-datareader
import pandas_datareader.data as web
import datetime
start = datetime.datetime(2020, 1, 1)
gdp = web.DataReader("GDP", "fred", start)
unemp = web.DataReader("UNRATE", "fred", start)
cpi = web.DataReader("CPIAUCSL", "fred", start)
fedfunds = web.DataReader("FEDFUNDS", "fred", start)
ten_year = web.DataReader("DGS10", "fred", start)
import pandas as pd
combined = pd.DataFrame({"GDP": gdp["GDP"], "CPI": cpi["CPIAUCSL"], "FedFunds": fedfunds["FEDFUNDS"]})
print(combined.tail())
gdp_pc = web.DataReader("NY.GDP.PCAP.CD", "worldbank", start=2015)
test cases passed, vs 16 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.